| 4 4 1998 1999 6 6 6 6 5 6 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); write_seqlock(&fs->seq); old_root = fs->root; fs->root = *path; write_sequnlock(&fs->seq); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); write_seqlock(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_sequnlock(&fs->seq); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; write_seqlock(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); while (hits--) { count++; path_get(new_root); } write_sequnlock(&fs->seq); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); read_seqlock_excl(&fs->seq); tsk->fs = NULL; kill = !--fs->users; read_sequnlock_excl(&fs->seq); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; seqlock_init(&fs->seq); fs->umask = old->umask; read_seqlock_excl(&old->seq); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); read_sequnlock_excl(&old->seq); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); read_seqlock_excl(&fs->seq); kill = !--fs->users; current->fs = new_fs; read_sequnlock_excl(&fs->seq); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .seq = __SEQLOCK_UNLOCKED(init_fs.seq), .umask = 0022, }; |
| 156 148 15 481 490 3 477 7 7 7 7 3 4 7 7 3 4 335 337 7 7 7 1167 1166 1169 1168 454 328 330 326 794 795 795 343 125 221 221 214 215 212 211 211 212 212 458 373 34 350 4 16 50 279 467 9 461 458 459 353 353 350 2 305 147 443 406 387 135 136 356 2 356 391 391 43 352 357 84 1 3 85 389 58 383 84 84 204 205 206 456 457 457 2 4 513 504 4 2 4 4 167 4 4 332 500 333 167 374 1 254 120 7 7 233 233 170 63 233 146 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/balloc.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/time.h> #include <linux/capability.h> #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include "ext4.h" #include "ext4_jbd2.h" #include "mballoc.h" #include <trace/events/ext4.h> #include <kunit/static_stub.h> static unsigned ext4_num_base_meta_clusters(struct super_block *sb, ext4_group_t block_group); /* * balloc.c contains the blocks allocation and deallocation routines */ /* * Calculate block group number for a given block number */ ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_fsblk_t block) { ext4_group_t group; if (test_opt2(sb, STD_GROUP_SIZE)) group = (block - le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >> (EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3); else ext4_get_group_no_and_offset(sb, block, &group, NULL); return group; } /* * Calculate the block group number and offset into the block/cluster * allocation bitmap, given a block number */ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; ext4_grpblk_t offset; blocknr = blocknr - le32_to_cpu(es->s_first_data_block); offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >> EXT4_SB(sb)->s_cluster_bits; if (offsetp) *offsetp = offset; if (blockgrpp) *blockgrpp = blocknr; } /* * Check whether the 'block' lives within the 'block_group'. Returns 1 if so * and 0 otherwise. */ static inline int ext4_block_in_group(struct super_block *sb, ext4_fsblk_t block, ext4_group_t block_group) { ext4_group_t actual_group; actual_group = ext4_get_group_number(sb, block); return (actual_group == block_group) ? 1 : 0; } /* * Return the number of clusters used for file system metadata; this * represents the overhead needed by the file system. */ static unsigned ext4_num_overhead_clusters(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { unsigned base_clusters, num_clusters; int block_cluster = -1, inode_cluster; int itbl_cluster_start = -1, itbl_cluster_end = -1; ext4_fsblk_t start = ext4_group_first_block_no(sb, block_group); ext4_fsblk_t end = start + EXT4_BLOCKS_PER_GROUP(sb) - 1; ext4_fsblk_t itbl_blk_start, itbl_blk_end; struct ext4_sb_info *sbi = EXT4_SB(sb); /* This is the number of clusters used by the superblock, * block group descriptors, and reserved block group * descriptor blocks */ base_clusters = ext4_num_base_meta_clusters(sb, block_group); num_clusters = base_clusters; /* * Account and record inode table clusters if any cluster * is in the block group, or inode table cluster range is * [-1, -1] and won't overlap with block/inode bitmap cluster * accounted below. */ itbl_blk_start = ext4_inode_table(sb, gdp); itbl_blk_end = itbl_blk_start + sbi->s_itb_per_group - 1; if (itbl_blk_start <= end && itbl_blk_end >= start) { itbl_blk_start = max(itbl_blk_start, start); itbl_blk_end = min(itbl_blk_end, end); itbl_cluster_start = EXT4_B2C(sbi, itbl_blk_start - start); itbl_cluster_end = EXT4_B2C(sbi, itbl_blk_end - start); num_clusters += itbl_cluster_end - itbl_cluster_start + 1; /* check if border cluster is overlapped */ if (itbl_cluster_start == base_clusters - 1) num_clusters--; } /* * For the allocation bitmaps, we first need to check to see * if the block is in the block group. If it is, then check * to see if the cluster is already accounted for in the clusters * used for the base metadata cluster and inode tables cluster. * Normally all of these blocks are contiguous, so the special * case handling shouldn't be necessary except for *very* * unusual file system layouts. */ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) { block_cluster = EXT4_B2C(sbi, ext4_block_bitmap(sb, gdp) - start); if (block_cluster >= base_clusters && (block_cluster < itbl_cluster_start || block_cluster > itbl_cluster_end)) num_clusters++; } if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) { inode_cluster = EXT4_B2C(sbi, ext4_inode_bitmap(sb, gdp) - start); /* * Additional check if inode bitmap is in just accounted * block_cluster */ if (inode_cluster != block_cluster && inode_cluster >= base_clusters && (inode_cluster < itbl_cluster_start || inode_cluster > itbl_cluster_end)) num_clusters++; } return num_clusters; } static unsigned int num_clusters_in_group(struct super_block *sb, ext4_group_t block_group) { unsigned int blocks; if (block_group == ext4_get_groups_count(sb) - 1) { /* * Even though mke2fs always initializes the first and * last group, just in case some other tool was used, * we need to make sure we calculate the right free * blocks. */ blocks = ext4_blocks_count(EXT4_SB(sb)->s_es) - ext4_group_first_block_no(sb, block_group); } else blocks = EXT4_BLOCKS_PER_GROUP(sb); return EXT4_NUM_B2C(EXT4_SB(sb), blocks); } /* Initializes an uninitialized block bitmap */ static int ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, ext4_group_t block_group, struct ext4_group_desc *gdp) { unsigned int bit, bit_max; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start, tmp; ASSERT(buffer_locked(bh)); if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT | EXT4_GROUP_INFO_IBITMAP_CORRUPT); return -EFSBADCRC; } memset(bh->b_data, 0, sb->s_blocksize); bit_max = ext4_num_base_meta_clusters(sb, block_group); if ((bit_max >> 3) >= bh->b_size) return -EFSCORRUPTED; for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); start = ext4_group_first_block_no(sb, block_group); /* Set bits for block and inode bitmaps, and inode table */ tmp = ext4_block_bitmap(sb, gdp); if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_bitmap(sb, gdp); if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); tmp = ext4_inode_table(sb, gdp); for (; tmp < ext4_inode_table(sb, gdp) + sbi->s_itb_per_group; tmp++) { if (ext4_block_in_group(sb, tmp, block_group)) ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data); } /* * Also if the number of blocks within the group is less than * the blocksize * 8 ( which is the size of bitmap ), set rest * of the block bitmap to 1 */ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group), sb->s_blocksize * 8, bh->b_data); return 0; } /* Return the number of free blocks in a block group. It is used when * the block bitmap is uninitialized, so we can't just count the bits * in the bitmap. */ unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { return num_clusters_in_group(sb, block_group) - ext4_num_overhead_clusters(sb, block_group, gdp); } /* * The free blocks are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap * block for inodes, N blocks for the inode table and data blocks. * * The file system contains group descriptors which are located after the * super block. Each descriptor contains the number of the bitmap block and * the free blocks count in the block. The descriptors are loaded in memory * when a file system is mounted (see ext4_fill_super). */ /** * ext4_get_group_desc() -- load group descriptor from disk * @sb: super block * @block_group: given block group * @bh: pointer to the buffer head to store the block * group descriptor */ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, ext4_group_t block_group, struct buffer_head **bh) { unsigned int group_desc; unsigned int offset; ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh_p; KUNIT_STATIC_STUB_REDIRECT(ext4_get_group_desc, sb, block_group, bh); if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," " groups_count = %u", block_group, ngroups); return NULL; } group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc); /* * sbi_array_rcu_deref returns with rcu unlocked, this is ok since * the pointer being dereferenced won't be dereferenced again. By * looking at the usage in add_new_gdb() the value isn't modified, * just the pointer, and so it remains valid. */ if (!bh_p) { ext4_error(sb, "Group descriptor not loaded - " "block_group = %u, group_desc = %u, desc = %u", block_group, group_desc, offset); return NULL; } desc = (struct ext4_group_desc *)( (__u8 *)bh_p->b_data + offset * EXT4_DESC_SIZE(sb)); if (bh) *bh = bh_p; return desc; } static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh) { ext4_grpblk_t next_zero_bit; unsigned long bitmap_size = sb->s_blocksize * 8; unsigned int offset = num_clusters_in_group(sb, block_group); if (bitmap_size <= offset) return 0; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); return (next_zero_bit < bitmap_size ? next_zero_bit : 0); } struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { struct ext4_group_info **grp_info; long indexv, indexh; if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) return NULL; indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); return grp_info[indexh]; } /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. */ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, ext4_group_t block_group, struct buffer_head *bh) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb); ext4_fsblk_t blk; ext4_fsblk_t group_first_block; if (ext4_has_feature_flex_bg(sb)) { /* with FLEX_BG, the inode/block bitmaps and itable * blocks may not be in the group at all * so the bitmap validation will be skipped for those groups * or it has to also read the block group where the bitmaps * are located to verify they are set. */ return 0; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ blk = ext4_block_bitmap(sb, desc); offset = blk - group_first_block; if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ return blk; /* check whether the inode bitmap block number is set */ blk = ext4_inode_bitmap(sb, desc); offset = blk - group_first_block; if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ return blk; /* check whether the inode table block number is set */ blk = ext4_inode_table(sb, desc); offset = blk - group_first_block; if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) >= max_bit) return blk; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) + 1, EXT4_B2C(sbi, offset)); if (next_zero_bit < EXT4_B2C(sbi, offset + sbi->s_itb_per_group - 1) + 1) /* bad bitmap for inode tables */ return blk; return 0; } static int ext4_validate_block_bitmap(struct super_block *sb, struct ext4_group_desc *desc, ext4_group_t block_group, struct buffer_head *bh) { ext4_fsblk_t blk; struct ext4_group_info *grp; if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return 0; grp = ext4_get_group_info(sb, block_group); if (buffer_verified(bh)) return 0; if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); if (buffer_verified(bh)) goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, desc, bh) || ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSBADCRC; } blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); if (unlikely(blk != 0)) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: block %llu: invalid block bitmap", block_group, blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); if (unlikely(blk != 0)) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", block_group, blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); return 0; } /** * ext4_read_block_bitmap_nowait() * @sb: super block * @block_group: given block group * @ignore_locked: ignore locked buffers * * Read the bitmap for a given block_group,and validate the * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or an ERR_PTR in case of failure. */ struct buffer_head * ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, bool ignore_locked) { struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh; ext4_fsblk_t bitmap_blk; int err; KUNIT_STATIC_STUB_REDIRECT(ext4_read_block_bitmap_nowait, sb, block_group, ignore_locked); desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return ERR_PTR(-EFSCORRUPTED); bitmap_blk = ext4_block_bitmap(sb, desc); if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || (bitmap_blk >= ext4_blocks_count(sbi->s_es))) { ext4_error(sb, "Invalid block bitmap block %llu in " "block_group %u", bitmap_blk, block_group); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return ERR_PTR(-EFSCORRUPTED); } bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { ext4_warning(sb, "Cannot get buffer for block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, bitmap_blk); return ERR_PTR(-ENOMEM); } if (ignore_locked && buffer_locked(bh)) { /* buffer under IO already, return if called for prefetching */ put_bh(bh); return NULL; } if (bitmap_uptodate(bh)) goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); goto verify; } ext4_lock_group(sb, block_group); if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { if (block_group == 0) { ext4_unlock_group(sb, block_group); unlock_buffer(bh); ext4_error(sb, "Block bitmap for bg 0 marked " "uninitialized"); err = -EFSCORRUPTED; goto out; } err = ext4_init_block_bitmap(sb, bh, block_group, desc); if (err) { ext4_unlock_group(sb, block_group); unlock_buffer(bh); ext4_error(sb, "Failed to init block bitmap for group " "%u: %d", block_group, err); goto out; } set_bitmap_uptodate(bh); set_buffer_uptodate(bh); set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, * bitmap is also uptodate */ set_bitmap_uptodate(bh); unlock_buffer(bh); goto verify; } /* * submit the buffer_head for reading */ set_buffer_new(bh); trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked); ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO | (ignore_locked ? REQ_RAHEAD : 0), ext4_end_bitmap_read, ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_EIO)); return bh; verify: err = ext4_validate_block_bitmap(sb, desc, block_group, bh); if (err) goto out; return bh; out: put_bh(bh); return ERR_PTR(err); } /* Returns 0 on success, -errno on error */ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh) { struct ext4_group_desc *desc; KUNIT_STATIC_STUB_REDIRECT(ext4_wait_block_bitmap, sb, block_group, bh); if (!buffer_new(bh)) return 0; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return -EFSCORRUPTED; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext4_error_err(sb, EIO, "Cannot read block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, (unsigned long long) bh->b_blocknr); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EIO; } clear_buffer_new(bh); /* Panic or remount fs read-only if block bitmap is invalid */ return ext4_validate_block_bitmap(sb, desc, block_group, bh); } struct buffer_head * ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) { struct buffer_head *bh; int err; bh = ext4_read_block_bitmap_nowait(sb, block_group, false); if (IS_ERR(bh)) return bh; err = ext4_wait_block_bitmap(sb, block_group, bh); if (err) { put_bh(bh); return ERR_PTR(err); } return bh; } /** * ext4_has_free_clusters() * @sbi: in-core super block structure. * @nclusters: number of needed blocks * @flags: flags from ext4_mb_new_blocks() * * Check if filesystem has nclusters free & available for allocation. * On success return 1, return 0 on failure. */ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { s64 free_clusters, dirty_clusters, rsv, resv_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; free_clusters = percpu_counter_read_positive(fcc); dirty_clusters = percpu_counter_read_positive(dcc); resv_clusters = atomic64_read(&sbi->s_resv_clusters); /* * r_blocks_count should always be multiple of the cluster ratio so * we are safe to do a plane bit shift only. */ rsv = (ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits) + resv_clusters; if (free_clusters - (nclusters + rsv + dirty_clusters) < EXT4_FREECLUSTERS_WATERMARK) { free_clusters = percpu_counter_sum_positive(fcc); dirty_clusters = percpu_counter_sum_positive(dcc); } /* Check whether we have space after accounting for current * dirty clusters & root reserved clusters. */ if (free_clusters >= (rsv + nclusters + dirty_clusters)) return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ if (uid_eq(sbi->s_resuid, current_fsuid()) || (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || (flags & EXT4_MB_USE_ROOT_BLOCKS) || capable(CAP_SYS_RESOURCE)) { if (free_clusters >= (nclusters + dirty_clusters + resv_clusters)) return 1; } /* No free blocks. Let's see if we can dip into reserved pool */ if (flags & EXT4_MB_USE_RESERVED) { if (free_clusters >= (nclusters + dirty_clusters)) return 1; } return 0; } int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { if (ext4_has_free_clusters(sbi, nclusters, flags)) { percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters); return 0; } else return -ENOSPC; } /** * ext4_should_retry_alloc() - check if a block allocation should be retried * @sb: superblock * @retries: number of retry attempts made so far * * ext4_should_retry_alloc() is called when ENOSPC is returned while * attempting to allocate blocks. If there's an indication that a pending * journal transaction might free some space and allow another attempt to * succeed, this function will wait for the current or committing transaction * to complete and then return TRUE. */ int ext4_should_retry_alloc(struct super_block *sb, int *retries) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (!sbi->s_journal) return 0; if (++(*retries) > 3) { percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit); return 0; } /* * if there's no indication that blocks are about to be freed it's * possible we just missed a transaction commit that did so */ smp_mb(); if (atomic_read(&sbi->s_mb_free_pending) == 0) { if (test_opt(sb, DISCARD)) { atomic_inc(&sbi->s_retry_alloc_pending); flush_work(&sbi->s_discard_work); atomic_dec(&sbi->s_retry_alloc_pending); } return ext4_has_free_clusters(sbi, 1, 0); } /* * it's possible we've just missed a transaction commit here, * so ignore the returned status */ ext4_debug("%s: retrying operation after ENOSPC\n", sb->s_id); (void) jbd2_journal_force_commit_nested(sbi->s_journal); return 1; } /* * ext4_new_meta_blocks() -- allocate block for meta data (indexing) blocks * * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) * @count: pointer to total number of clusters needed * @errp: error code * * Return 1st allocated block number on success, *count stores total account * error stores in errp pointer */ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned int flags, unsigned long *count, int *errp) { struct ext4_allocation_request ar; ext4_fsblk_t ret; memset(&ar, 0, sizeof(ar)); /* Fill with neighbour allocated blocks */ ar.inode = inode; ar.goal = goal; ar.len = count ? *count : 1; ar.flags = flags; ret = ext4_mb_new_blocks(handle, &ar, errp); if (count) *count = ar.len; /* * Account for the allocated meta blocks. We will never * fail EDQUOT for metdata, but we do account for it. */ if (!(*errp) && (flags & EXT4_MB_DELALLOC_RESERVED)) { dquot_alloc_block_nofail(inode, EXT4_C2B(EXT4_SB(inode->i_sb), ar.len)); } return ret; } /** * ext4_count_free_clusters() -- count filesystem free clusters * @sb: superblock * * Adds up the number of free clusters from each block group. */ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) { ext4_fsblk_t desc_count; struct ext4_group_desc *gdp; ext4_group_t i; ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_info *grp; #ifdef EXT4FS_DEBUG struct ext4_super_block *es; ext4_fsblk_t bitmap_count; unsigned int x; struct buffer_head *bitmap_bh = NULL; es = EXT4_SB(sb)->s_es; desc_count = 0; bitmap_count = 0; gdp = NULL; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; grp = NULL; if (EXT4_SB(sb)->s_group_info) grp = ext4_get_group_info(sb, i); if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) desc_count += ext4_free_group_clusters(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_block_bitmap(sb, i); if (IS_ERR(bitmap_bh)) { bitmap_bh = NULL; continue; } x = ext4_count_free(bitmap_bh->b_data, EXT4_CLUSTERS_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", i, ext4_free_group_clusters(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu" ", computed = %llu, %llu\n", EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)), desc_count, bitmap_count); return bitmap_count; #else desc_count = 0; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; grp = NULL; if (EXT4_SB(sb)->s_group_info) grp = ext4_get_group_info(sb, i); if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) desc_count += ext4_free_group_clusters(sb, gdp); } return desc_count; #endif } static inline int test_root(ext4_group_t a, int b) { while (1) { if (a < b) return 0; if (a == b) return 1; if ((a % b) != 0) return 0; a = a / b; } } /** * ext4_bg_has_super - number of blocks used by the superblock in group * @sb: superblock for filesystem * @group: group number to check * * Return the number of blocks used by the superblock (primary or backup) * in this group. Currently this will be only 0 or 1. */ int ext4_bg_has_super(struct super_block *sb, ext4_group_t group) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (group == 0) return 1; if (ext4_has_feature_sparse_super2(sb)) { if (group == le32_to_cpu(es->s_backup_bgs[0]) || group == le32_to_cpu(es->s_backup_bgs[1])) return 1; return 0; } if ((group <= 1) || !ext4_has_feature_sparse_super(sb)) return 1; if (!(group & 1)) return 0; if (test_root(group, 3) || (test_root(group, 5)) || test_root(group, 7)) return 1; return 0; } static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, ext4_group_t group) { unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); ext4_group_t first = metagroup * EXT4_DESC_PER_BLOCK(sb); ext4_group_t last = first + EXT4_DESC_PER_BLOCK(sb) - 1; if (group == first || group == first + 1 || group == last) return 1; return 0; } static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, ext4_group_t group) { if (!ext4_bg_has_super(sb, group)) return 0; if (ext4_has_feature_meta_bg(sb)) return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); else return EXT4_SB(sb)->s_gdb_count; } /** * ext4_bg_num_gdb - number of blocks used by the group table in group * @sb: superblock for filesystem * @group: group number to check * * Return the number of blocks used by the group descriptor table * (primary or backup) in this group. In the future there may be a * different number of descriptor blocks in each group. */ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group) { unsigned long first_meta_bg = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb); if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) return ext4_bg_num_gdb_nometa(sb, group); return ext4_bg_num_gdb_meta(sb,group); } /* * This function returns the number of file system metadata blocks at * the beginning of a block group, including the reserved gdt blocks. */ unsigned int ext4_num_base_meta_blocks(struct super_block *sb, ext4_group_t block_group) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned num; /* Check for superblock and gdt backups in this group */ num = ext4_bg_has_super(sb, block_group); if (!ext4_has_feature_meta_bg(sb) || block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) * sbi->s_desc_per_block) { if (num) { num += ext4_bg_num_gdb_nometa(sb, block_group); num += le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); } } else { /* For META_BG_BLOCK_GROUPS */ num += ext4_bg_num_gdb_meta(sb, block_group); } return num; } static unsigned int ext4_num_base_meta_clusters(struct super_block *sb, ext4_group_t block_group) { return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group)); } /** * ext4_inode_to_goal_block - return a hint for block allocation * @inode: inode for block allocation * * Return the ideal location to start allocating blocks for a * newly created inode. */ ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_group_t block_group; ext4_grpblk_t colour; int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb)); ext4_fsblk_t bg_start; ext4_fsblk_t last_block; block_group = ei->i_block_group; if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) { /* * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME * block groups per flexgroup, reserve the first block * group for directories and special files. Regular * files will start at the second block group. This * tends to speed up directory access and improves * fsck times. */ block_group &= ~(flex_size-1); if (S_ISREG(inode->i_mode)) block_group++; } bg_start = ext4_group_first_block_no(inode->i_sb, block_group); last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; /* * If we are doing delayed allocation, we don't need take * colour into account. */ if (test_opt(inode->i_sb, DELALLOC)) return bg_start; if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) colour = (task_pid_nr(current) % 16) * (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); else colour = (task_pid_nr(current) % 16) * ((last_block - bg_start) / 16); return bg_start + colour; } |
| 1414 8940 8946 153 8926 2 2 3 3 3 8938 2 8931 3 8934 3 8934 8918 1 1133 636 1088 821 795 1007 1158 9 1158 1 1153 11 1159 1107 1106 8934 8949 1158 1162 23 23 23 127 28 106 135 107 27 127 5 13 128 23 23 23 23 23 22 23 130 12 105 22 2545 2543 2523 204 203 2529 2527 | 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-only /* * Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com> * * Author: * Casey Schaufler <casey@schaufler-ca.com> */ #include <linux/types.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/sched.h> #include "smack.h" struct smack_known smack_known_huh = { .smk_known = "?", .smk_secid = 2, }; struct smack_known smack_known_hat = { .smk_known = "^", .smk_secid = 3, }; struct smack_known smack_known_star = { .smk_known = "*", .smk_secid = 4, }; struct smack_known smack_known_floor = { .smk_known = "_", .smk_secid = 5, }; struct smack_known smack_known_web = { .smk_known = "@", .smk_secid = 7, }; LIST_HEAD(smack_known_list); /* * The initial value needs to be bigger than any of the * known values above. */ static u32 smack_next_secid = 10; #ifdef CONFIG_AUDIT /* * what events do we log * can be overwritten at run-time by /smack/logging */ int log_policy = SMACK_AUDIT_DENIED; #endif /* CONFIG_AUDIT */ /** * smk_access_entry - look up matching access rule * @subject_label: a pointer to the subject's Smack label * @object_label: a pointer to the object's Smack label * @rule_list: the list of rules to search * * This function looks up the subject/object pair in the * access rule list and returns the access mode. If no * entry is found returns -ENOENT. * * NOTE: * * Earlier versions of this function allowed for labels that * were not on the label list. This was done to allow for * labels to come over the network that had never been seen * before on this host. Unless the receiving socket has the * star label this will always result in a failure check. The * star labeled socket case is now handled in the networking * hooks so there is no case where the label is not on the * label list. Checking to see if the address of two labels * is the same is now a reliable test. * * Do the object check first because that is more * likely to differ. * * Allowing write access implies allowing locking. */ int smk_access_entry(char *subject_label, char *object_label, struct list_head *rule_list) { struct smack_rule *srp; list_for_each_entry_rcu(srp, rule_list, list) { if (srp->smk_object->smk_known == object_label && srp->smk_subject->smk_known == subject_label) { int may = srp->smk_access; /* * MAY_WRITE implies MAY_LOCK. */ if ((may & MAY_WRITE) == MAY_WRITE) may |= MAY_LOCK; return may; } } return -ENOENT; } /** * smk_access - determine if a subject has a specific access to an object * @subject: a pointer to the subject's Smack label entry * @object: a pointer to the object's Smack label entry * @request: the access requested, in "MAY" format * @a : a pointer to the audit data * * This function looks up the subject/object pair in the * access rule list and returns 0 if the access is permitted, * non zero otherwise. * * Smack labels are shared on smack_list */ int smk_access(struct smack_known *subject, struct smack_known *object, int request, struct smk_audit_info *a) { int may = MAY_NOT; int rc = 0; /* * Hardcoded comparisons. */ /* * A star subject can't access any object. */ if (subject == &smack_known_star) { rc = -EACCES; goto out_audit; } /* * An internet object can be accessed by any subject. * Tasks cannot be assigned the internet label. * An internet subject can access any object. */ if (object == &smack_known_web || subject == &smack_known_web) goto out_audit; /* * A star object can be accessed by any subject. */ if (object == &smack_known_star) goto out_audit; /* * An object can be accessed in any way by a subject * with the same label. */ if (subject->smk_known == object->smk_known) goto out_audit; /* * A hat subject can read or lock any object. * A floor object can be read or locked by any subject. */ if ((request & MAY_ANYREAD) == request || (request & MAY_LOCK) == request) { if (object == &smack_known_floor) goto out_audit; if (subject == &smack_known_hat) goto out_audit; } /* * Beyond here an explicit relationship is required. * If the requested access is contained in the available * access (e.g. read is included in readwrite) it's * good. A negative response from smk_access_entry() * indicates there is no entry for this pair. */ rcu_read_lock(); may = smk_access_entry(subject->smk_known, object->smk_known, &subject->smk_rules); rcu_read_unlock(); if (may <= 0 || (request & may) != request) { rc = -EACCES; goto out_audit; } #ifdef CONFIG_SECURITY_SMACK_BRINGUP /* * Return a positive value if using bringup mode. * This allows the hooks to identify checks that * succeed because of "b" rules. */ if (may & MAY_BRINGUP) rc = SMACK_BRINGUP_ALLOW; #endif out_audit: #ifdef CONFIG_SECURITY_SMACK_BRINGUP if (rc < 0) { if (object == smack_unconfined) rc = SMACK_UNCONFINED_OBJECT; if (subject == smack_unconfined) rc = SMACK_UNCONFINED_SUBJECT; } #endif #ifdef CONFIG_AUDIT if (a) smack_log(subject->smk_known, object->smk_known, request, rc, a); #endif return rc; } /** * smk_tskacc - determine if a task has a specific access to an object * @tsp: a pointer to the subject's task * @obj_known: a pointer to the object's label entry * @mode: the access requested, in "MAY" format * @a : common audit data * * This function checks the subject task's label/object label pair * in the access rule list and returns 0 if the access is permitted, * non zero otherwise. It allows that the task may have the capability * to override the rules. */ int smk_tskacc(struct task_smack *tsp, struct smack_known *obj_known, u32 mode, struct smk_audit_info *a) { struct smack_known *sbj_known = smk_of_task(tsp); int may; int rc; /* * Check the global rule list */ rc = smk_access(sbj_known, obj_known, mode, NULL); if (rc >= 0) { /* * If there is an entry in the task's rule list * it can further restrict access. */ may = smk_access_entry(sbj_known->smk_known, obj_known->smk_known, &tsp->smk_rules); if (may < 0) goto out_audit; if ((mode & may) == mode) goto out_audit; rc = -EACCES; } /* * Allow for privileged to override policy. */ if (rc != 0 && smack_privileged(CAP_MAC_OVERRIDE)) rc = 0; out_audit: #ifdef CONFIG_AUDIT if (a) smack_log(sbj_known->smk_known, obj_known->smk_known, mode, rc, a); #endif return rc; } /** * smk_curacc - determine if current has a specific access to an object * @obj_known: a pointer to the object's Smack label entry * @mode: the access requested, in "MAY" format * @a : common audit data * * This function checks the current subject label/object label pair * in the access rule list and returns 0 if the access is permitted, * non zero otherwise. It allows that current may have the capability * to override the rules. */ int smk_curacc(struct smack_known *obj_known, u32 mode, struct smk_audit_info *a) { struct task_smack *tsp = smack_cred(current_cred()); return smk_tskacc(tsp, obj_known, mode, a); } /** * smack_str_from_perm : helper to translate an int to a * readable string * @string : the string to fill * @access : the int * */ int smack_str_from_perm(char *string, int access) { int i = 0; if (access & MAY_READ) string[i++] = 'r'; if (access & MAY_WRITE) string[i++] = 'w'; if (access & MAY_EXEC) string[i++] = 'x'; if (access & MAY_APPEND) string[i++] = 'a'; if (access & MAY_TRANSMUTE) string[i++] = 't'; if (access & MAY_LOCK) string[i++] = 'l'; if (access & MAY_BRINGUP) string[i++] = 'b'; if (i == 0) string[i++] = '-'; string[i] = '\0'; return i; } #ifdef CONFIG_AUDIT /** * smack_log_callback - SMACK specific information * will be called by generic audit code * @ab : the audit_buffer * @a : audit_data * */ static void smack_log_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct smack_audit_data *sad = ad->smack_audit_data; audit_log_format(ab, "lsm=SMACK fn=%s action=%s", ad->smack_audit_data->function, sad->result ? "denied" : "granted"); audit_log_format(ab, " subject="); audit_log_untrustedstring(ab, sad->subject); audit_log_format(ab, " object="); audit_log_untrustedstring(ab, sad->object); if (sad->request[0] == '\0') audit_log_format(ab, " labels_differ"); else audit_log_format(ab, " requested=%s", sad->request); } /** * smack_log - Audit the granting or denial of permissions. * @subject_label : smack label of the requester * @object_label : smack label of the object being accessed * @request: requested permissions * @result: result from smk_access * @ad: auxiliary audit data * * Audit the granting or denial of permissions in accordance * with the policy. */ void smack_log(char *subject_label, char *object_label, int request, int result, struct smk_audit_info *ad) { #ifdef CONFIG_SECURITY_SMACK_BRINGUP char request_buffer[SMK_NUM_ACCESS_TYPE + 5]; #else char request_buffer[SMK_NUM_ACCESS_TYPE + 1]; #endif struct smack_audit_data *sad; struct common_audit_data *a = &ad->a; /* check if we have to log the current event */ if (result < 0 && (log_policy & SMACK_AUDIT_DENIED) == 0) return; if (result == 0 && (log_policy & SMACK_AUDIT_ACCEPT) == 0) return; sad = a->smack_audit_data; if (sad->function == NULL) sad->function = "unknown"; /* end preparing the audit data */ smack_str_from_perm(request_buffer, request); sad->subject = subject_label; sad->object = object_label; #ifdef CONFIG_SECURITY_SMACK_BRINGUP /* * The result may be positive in bringup mode. * A positive result is an allow, but not for normal reasons. * Mark it as successful, but don't filter it out even if * the logging policy says to do so. */ if (result == SMACK_UNCONFINED_SUBJECT) strcat(request_buffer, "(US)"); else if (result == SMACK_UNCONFINED_OBJECT) strcat(request_buffer, "(UO)"); if (result > 0) result = 0; #endif sad->request = request_buffer; sad->result = result; common_lsm_audit(a, smack_log_callback, NULL); } #else /* #ifdef CONFIG_AUDIT */ void smack_log(char *subject_label, char *object_label, int request, int result, struct smk_audit_info *ad) { } #endif DEFINE_MUTEX(smack_known_lock); struct hlist_head smack_known_hash[SMACK_HASH_SLOTS]; /** * smk_insert_entry - insert a smack label into a hash map, * @skp: smack label * * this function must be called under smack_known_lock */ void smk_insert_entry(struct smack_known *skp) { unsigned int hash; struct hlist_head *head; hash = full_name_hash(NULL, skp->smk_known, strlen(skp->smk_known)); head = &smack_known_hash[hash & (SMACK_HASH_SLOTS - 1)]; hlist_add_head_rcu(&skp->smk_hashed, head); list_add_rcu(&skp->list, &smack_known_list); } /** * smk_find_entry - find a label on the list, return the list entry * @string: a text string that might be a Smack label * * Returns a pointer to the entry in the label list that * matches the passed string or NULL if not found. */ struct smack_known *smk_find_entry(const char *string) { unsigned int hash; struct hlist_head *head; struct smack_known *skp; hash = full_name_hash(NULL, string, strlen(string)); head = &smack_known_hash[hash & (SMACK_HASH_SLOTS - 1)]; hlist_for_each_entry_rcu(skp, head, smk_hashed) if (strcmp(skp->smk_known, string) == 0) return skp; return NULL; } /** * smk_parse_smack - parse smack label from a text string * @string: a text string that might contain a Smack label * @len: the maximum size, or zero if it is NULL terminated. * * Returns a pointer to the clean label or an error code. */ char *smk_parse_smack(const char *string, int len) { char *smack; int i; if (len <= 0) len = strlen(string) + 1; /* * Reserve a leading '-' as an indicator that * this isn't a label, but an option to interfaces * including /smack/cipso and /smack/cipso2 */ if (string[0] == '-') return ERR_PTR(-EINVAL); for (i = 0; i < len; i++) if (string[i] > '~' || string[i] <= ' ' || string[i] == '/' || string[i] == '"' || string[i] == '\\' || string[i] == '\'') break; if (i == 0 || i >= SMK_LONGLABEL) return ERR_PTR(-EINVAL); smack = kstrndup(string, i, GFP_NOFS); if (!smack) return ERR_PTR(-ENOMEM); return smack; } /** * smk_netlbl_mls - convert a catset to netlabel mls categories * @level: MLS sensitivity level * @catset: the Smack categories * @sap: where to put the netlabel categories * @len: number of bytes for the levels in a CIPSO IP option * * Allocates and fills attr.mls * Returns 0 on success, error code on failure. */ int smk_netlbl_mls(int level, char *catset, struct netlbl_lsm_secattr *sap, int len) { unsigned char *cp; unsigned char m; int cat; int rc; int byte; sap->flags |= NETLBL_SECATTR_MLS_CAT; sap->attr.mls.lvl = level; sap->attr.mls.cat = NULL; for (cat = 1, cp = catset, byte = 0; byte < len; cp++, byte++) for (m = 0x80; m != 0; m >>= 1, cat++) { if ((m & *cp) == 0) continue; rc = netlbl_catmap_setbit(&sap->attr.mls.cat, cat, GFP_NOFS); if (rc < 0) { netlbl_catmap_free(sap->attr.mls.cat); return rc; } } return 0; } /** * smack_populate_secattr - fill in the smack_known netlabel information * @skp: pointer to the structure to fill * * Populate the netlabel secattr structure for a Smack label. * * Returns 0 unless creating the category mapping fails */ int smack_populate_secattr(struct smack_known *skp) { int slen; skp->smk_netlabel.attr.secid = skp->smk_secid; skp->smk_netlabel.domain = skp->smk_known; skp->smk_netlabel.cache = netlbl_secattr_cache_alloc(GFP_ATOMIC); if (skp->smk_netlabel.cache != NULL) { skp->smk_netlabel.flags |= NETLBL_SECATTR_CACHE; skp->smk_netlabel.cache->free = NULL; skp->smk_netlabel.cache->data = skp; } skp->smk_netlabel.flags |= NETLBL_SECATTR_SECID | NETLBL_SECATTR_MLS_LVL | NETLBL_SECATTR_DOMAIN; /* * If direct labeling works use it. * Otherwise use mapped labeling. */ slen = strlen(skp->smk_known); if (slen < SMK_CIPSOLEN) return smk_netlbl_mls(smack_cipso_direct, skp->smk_known, &skp->smk_netlabel, slen); return smk_netlbl_mls(smack_cipso_mapped, (char *)&skp->smk_secid, &skp->smk_netlabel, sizeof(skp->smk_secid)); } /** * smk_import_entry - import a label, return the list entry * @string: a text string that might be a Smack label * @len: the maximum size, or zero if it is NULL terminated. * * Returns a pointer to the entry in the label list that * matches the passed string, adding it if necessary, * or an error code. */ struct smack_known *smk_import_entry(const char *string, int len) { struct smack_known *skp; char *smack; int rc; smack = smk_parse_smack(string, len); if (IS_ERR(smack)) return ERR_CAST(smack); mutex_lock(&smack_known_lock); skp = smk_find_entry(smack); if (skp != NULL) goto freeout; skp = kzalloc(sizeof(*skp), GFP_NOFS); if (skp == NULL) { skp = ERR_PTR(-ENOMEM); goto freeout; } skp->smk_known = smack; skp->smk_secid = smack_next_secid++; rc = smack_populate_secattr(skp); if (rc >= 0) { INIT_LIST_HEAD(&skp->smk_rules); mutex_init(&skp->smk_rules_lock); /* * Make sure that the entry is actually * filled before putting it on the list. */ smk_insert_entry(skp); goto unlockout; } kfree(skp); skp = ERR_PTR(rc); freeout: kfree(smack); unlockout: mutex_unlock(&smack_known_lock); return skp; } /** * smack_from_secid - find the Smack label associated with a secid * @secid: an integer that might be associated with a Smack label * * Returns a pointer to the appropriate Smack label entry if there is one, * otherwise a pointer to the invalid Smack label. */ struct smack_known *smack_from_secid(const u32 secid) { struct smack_known *skp; rcu_read_lock(); list_for_each_entry_rcu(skp, &smack_known_list, list) { if (skp->smk_secid == secid) { rcu_read_unlock(); return skp; } } /* * If we got this far someone asked for the translation * of a secid that is not on the list. */ rcu_read_unlock(); return &smack_known_huh; } /* * Unless a process is running with one of these labels * even having CAP_MAC_OVERRIDE isn't enough to grant * privilege to violate MAC policy. If no labels are * designated (the empty list case) capabilities apply to * everyone. */ LIST_HEAD(smack_onlycap_list); DEFINE_MUTEX(smack_onlycap_lock); /** * smack_privileged_cred - are all privilege requirements met by cred * @cap: The requested capability * @cred: the credential to use * * Is the task privileged and allowed to be privileged * by the onlycap rule. * * Returns true if the task is allowed to be privileged, false if it's not. */ bool smack_privileged_cred(int cap, const struct cred *cred) { struct task_smack *tsp = smack_cred(cred); struct smack_known *skp = tsp->smk_task; struct smack_known_list_elem *sklep; int rc; rc = cap_capable(cred, &init_user_ns, cap, CAP_OPT_NONE); if (rc) return false; rcu_read_lock(); if (list_empty(&smack_onlycap_list)) { rcu_read_unlock(); return true; } list_for_each_entry_rcu(sklep, &smack_onlycap_list, list) { if (sklep->smk_label == skp) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /** * smack_privileged - are all privilege requirements met * @cap: The requested capability * * Is the task privileged and allowed to be privileged * by the onlycap rule. * * Returns true if the task is allowed to be privileged, false if it's not. */ bool smack_privileged(int cap) { /* * All kernel tasks are privileged */ if (unlikely(current->flags & PF_KTHREAD)) return true; return smack_privileged_cred(cap, current_cred()); } |
| 1 1 1 1 1 1 1 1 1 11 11 11 9 9 9 1 1 1 1 1 1 1 1 1 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Memory Manager * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> * 2000 by Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/mm.h> #include <sound/core.h> #include <sound/seq_kernel.h> #include "seq_memory.h" #include "seq_queue.h" #include "seq_info.h" #include "seq_lock.h" static inline int snd_seq_pool_available(struct snd_seq_pool *pool) { return pool->total_elements - atomic_read(&pool->counter); } static inline int snd_seq_output_ok(struct snd_seq_pool *pool) { return snd_seq_pool_available(pool) >= pool->room; } /* * Variable length event: * The event like sysex uses variable length type. * The external data may be stored in three different formats. * 1) kernel space * This is the normal case. * ext.data.len = length * ext.data.ptr = buffer pointer * 2) user space * When an event is generated via read(), the external data is * kept in user space until expanded. * ext.data.len = length | SNDRV_SEQ_EXT_USRPTR * ext.data.ptr = userspace pointer * 3) chained cells * When the variable length event is enqueued (in prioq or fifo), * the external data is decomposed to several cells. * ext.data.len = length | SNDRV_SEQ_EXT_CHAINED * ext.data.ptr = the additiona cell head * -> cell.next -> cell.next -> .. */ /* * exported: * call dump function to expand external data. */ static int get_var_len(const struct snd_seq_event *event) { if ((event->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) return -EINVAL; return event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; } static int dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data, int offset, int maxlen) { int len, err; struct snd_seq_event_cell *cell; len = get_var_len(event); if (len <= 0) return len; if (len <= offset) return 0; if (maxlen && len > offset + maxlen) len = offset + maxlen; if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { char buf[32]; char __user *curptr = (char __force __user *)event->data.ext.ptr; curptr += offset; len -= offset; while (len > 0) { int size = sizeof(buf); if (len < size) size = len; if (copy_from_user(buf, curptr, size)) return -EFAULT; err = func(private_data, buf, size); if (err < 0) return err; curptr += size; len -= size; } return 0; } if (!(event->data.ext.len & SNDRV_SEQ_EXT_CHAINED)) return func(private_data, event->data.ext.ptr + offset, len - offset); cell = (struct snd_seq_event_cell *)event->data.ext.ptr; for (; len > 0 && cell; cell = cell->next) { int size = sizeof(struct snd_seq_event); char *curptr = (char *)&cell->event; if (offset >= size) { offset -= size; len -= size; continue; } if (len < size) size = len; err = func(private_data, curptr + offset, size - offset); if (err < 0) return err; offset = 0; len -= size; } return 0; } int snd_seq_dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data) { return dump_var_event(event, func, private_data, 0, 0); } EXPORT_SYMBOL(snd_seq_dump_var_event); /* * exported: * expand the variable length event to linear buffer space. */ static int seq_copy_in_kernel(void *ptr, void *src, int size) { char **bufptr = ptr; memcpy(*bufptr, src, size); *bufptr += size; return 0; } static int seq_copy_in_user(void *ptr, void *src, int size) { char __user **bufptr = ptr; if (copy_to_user(*bufptr, src, size)) return -EFAULT; *bufptr += size; return 0; } static int expand_var_event(const struct snd_seq_event *event, int offset, int size, char *buf, bool in_kernel) { if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { if (! in_kernel) return -EINVAL; if (copy_from_user(buf, (char __force __user *)event->data.ext.ptr + offset, size)) return -EFAULT; return 0; } return dump_var_event(event, in_kernel ? seq_copy_in_kernel : seq_copy_in_user, &buf, offset, size); } int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char *buf, int in_kernel, int size_aligned) { int len, newlen, err; len = get_var_len(event); if (len < 0) return len; newlen = len; if (size_aligned > 0) newlen = roundup(len, size_aligned); if (count < newlen) return -EAGAIN; err = expand_var_event(event, 0, len, buf, in_kernel); if (err < 0) return err; if (len != newlen) { if (in_kernel) memset(buf + len, 0, newlen - len); else if (clear_user((__force void __user *)buf + len, newlen - len)) return -EFAULT; } return newlen; } EXPORT_SYMBOL(snd_seq_expand_var_event); int snd_seq_expand_var_event_at(const struct snd_seq_event *event, int count, char *buf, int offset) { int len, err; len = get_var_len(event); if (len < 0) return len; if (len <= offset) return 0; len -= offset; if (len > count) len = count; err = expand_var_event(event, offset, count, buf, true); if (err < 0) return err; return len; } EXPORT_SYMBOL_GPL(snd_seq_expand_var_event_at); /* * release this cell, free extended data if available */ static inline void free_cell(struct snd_seq_pool *pool, struct snd_seq_event_cell *cell) { cell->next = pool->free; pool->free = cell; atomic_dec(&pool->counter); } void snd_seq_cell_free(struct snd_seq_event_cell * cell) { struct snd_seq_pool *pool; if (snd_BUG_ON(!cell)) return; pool = cell->pool; if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); free_cell(pool, cell); if (snd_seq_ev_is_variable(&cell->event)) { if (cell->event.data.ext.len & SNDRV_SEQ_EXT_CHAINED) { struct snd_seq_event_cell *curp, *nextptr; curp = cell->event.data.ext.ptr; for (; curp; curp = nextptr) { nextptr = curp->next; curp->next = pool->free; free_cell(pool, curp); } } } if (waitqueue_active(&pool->output_sleep)) { /* has enough space now? */ if (snd_seq_output_ok(pool)) wake_up(&pool->output_sleep); } } /* * allocate an event cell. */ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { struct snd_seq_event_cell *cell; unsigned long flags; int err = -EAGAIN; wait_queue_entry_t wait; if (pool == NULL) return -EINVAL; *cellp = NULL; init_waitqueue_entry(&wait, current); spin_lock_irqsave(&pool->lock, flags); if (pool->ptr == NULL) { /* not initialized */ pr_debug("ALSA: seq: pool is not initialized\n"); err = -EINVAL; goto __error; } while (pool->free == NULL && ! nonblock && ! pool->closing) { set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&pool->output_sleep, &wait); spin_unlock_irqrestore(&pool->lock, flags); if (mutexp) mutex_unlock(mutexp); schedule(); if (mutexp) mutex_lock(mutexp); spin_lock_irqsave(&pool->lock, flags); remove_wait_queue(&pool->output_sleep, &wait); /* interrupted? */ if (signal_pending(current)) { err = -ERESTARTSYS; goto __error; } } if (pool->closing) { /* closing.. */ err = -ENOMEM; goto __error; } cell = pool->free; if (cell) { int used; pool->free = cell->next; atomic_inc(&pool->counter); used = atomic_read(&pool->counter); if (pool->max_used < used) pool->max_used = used; pool->event_alloc_success++; /* clear cell pointers */ cell->next = NULL; err = 0; } else pool->event_alloc_failures++; *cellp = cell; __error: spin_unlock_irqrestore(&pool->lock, flags); return err; } /* * duplicate the event to a cell. * if the event has external data, the data is decomposed to additional * cells. */ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { int ncells, err; unsigned int extlen; struct snd_seq_event_cell *cell; int size; *cellp = NULL; ncells = 0; extlen = 0; if (snd_seq_ev_is_variable(event)) { extlen = event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; ncells = DIV_ROUND_UP(extlen, sizeof(struct snd_seq_event)); } if (ncells >= pool->total_elements) return -ENOMEM; err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp); if (err < 0) return err; /* copy the event */ size = snd_seq_event_packet_size(event); memcpy(&cell->ump, event, size); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (size < sizeof(cell->event)) cell->ump.raw.extra = 0; #endif /* decompose */ if (snd_seq_ev_is_variable(event)) { int len = extlen; int is_chained = event->data.ext.len & SNDRV_SEQ_EXT_CHAINED; int is_usrptr = event->data.ext.len & SNDRV_SEQ_EXT_USRPTR; struct snd_seq_event_cell *src, *tmp, *tail; char *buf; cell->event.data.ext.len = extlen | SNDRV_SEQ_EXT_CHAINED; cell->event.data.ext.ptr = NULL; src = (struct snd_seq_event_cell *)event->data.ext.ptr; buf = (char *)event->data.ext.ptr; tail = NULL; while (ncells-- > 0) { size = sizeof(struct snd_seq_event); if (len < size) size = len; err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, mutexp); if (err < 0) goto __error; if (cell->event.data.ext.ptr == NULL) cell->event.data.ext.ptr = tmp; if (tail) tail->next = tmp; tail = tmp; /* copy chunk */ if (is_chained && src) { tmp->event = src->event; src = src->next; } else if (is_usrptr) { if (copy_from_user(&tmp->event, (char __force __user *)buf, size)) { err = -EFAULT; goto __error; } } else { memcpy(&tmp->event, buf, size); } buf += size; len -= size; } } *cellp = cell; return 0; __error: snd_seq_cell_free(cell); return err; } /* poll wait */ int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait) { poll_wait(file, &pool->output_sleep, wait); guard(spinlock_irq)(&pool->lock); return snd_seq_output_ok(pool); } /* allocate room specified number of events */ int snd_seq_pool_init(struct snd_seq_pool *pool) { int cell; struct snd_seq_event_cell *cellptr; if (snd_BUG_ON(!pool)) return -EINVAL; cellptr = kvmalloc_array(pool->size, sizeof(struct snd_seq_event_cell), GFP_KERNEL); if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ guard(spinlock_irq)(&pool->lock); if (pool->ptr) { kvfree(cellptr); return 0; } pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { cellptr = pool->ptr + cell; cellptr->pool = pool; cellptr->next = pool->free; pool->free = cellptr; } pool->room = (pool->size + 1) / 2; /* init statistics */ pool->max_used = 0; pool->total_elements = pool->size; return 0; } /* refuse the further insertion to the pool */ void snd_seq_pool_mark_closing(struct snd_seq_pool *pool) { if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); pool->closing = 1; } /* remove events */ int snd_seq_pool_done(struct snd_seq_pool *pool) { struct snd_seq_event_cell *ptr; if (snd_BUG_ON(!pool)) return -EINVAL; /* wait for closing all threads */ if (waitqueue_active(&pool->output_sleep)) wake_up(&pool->output_sleep); while (atomic_read(&pool->counter) > 0) schedule_timeout_uninterruptible(1); /* release all resources */ scoped_guard(spinlock_irq, &pool->lock) { ptr = pool->ptr; pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; } kvfree(ptr); guard(spinlock_irq)(&pool->lock); pool->closing = 0; return 0; } /* init new memory pool */ struct snd_seq_pool *snd_seq_pool_new(int poolsize) { struct snd_seq_pool *pool; /* create pool block */ pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return NULL; spin_lock_init(&pool->lock); pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; atomic_set(&pool->counter, 0); pool->closing = 0; init_waitqueue_head(&pool->output_sleep); pool->size = poolsize; /* init statistics */ pool->max_used = 0; return pool; } /* remove memory pool */ int snd_seq_pool_delete(struct snd_seq_pool **ppool) { struct snd_seq_pool *pool = *ppool; *ppool = NULL; if (pool == NULL) return 0; snd_seq_pool_mark_closing(pool); snd_seq_pool_done(pool); kfree(pool); return 0; } /* exported to seq_clientmgr.c */ void snd_seq_info_pool(struct snd_info_buffer *buffer, struct snd_seq_pool *pool, char *space) { if (pool == NULL) return; snd_iprintf(buffer, "%sPool size : %d\n", space, pool->total_elements); snd_iprintf(buffer, "%sCells in use : %d\n", space, atomic_read(&pool->counter)); snd_iprintf(buffer, "%sPeak cells in use : %d\n", space, pool->max_used); snd_iprintf(buffer, "%sAlloc success : %d\n", space, pool->event_alloc_success); snd_iprintf(buffer, "%sAlloc failures : %d\n", space, pool->event_alloc_failures); } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_state.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * YOSHIFUJI Hideaki @USAGI * Split up af-specific functions * Derek Atkins <derek@ihtfp.com> * Add UDP Encapsulation * */ #include <linux/compat.h> #include <linux/workqueue.h> #include <net/xfrm.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <crypto/aead.h> #include "xfrm_hash.h" #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) #define xfrm_state_deref_check(table, net) \ rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) 2. Hash table by (daddr,family,reqid) to find what SAs exist for given destination/tunnel endpoint. (output) */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static HLIST_HEAD(xfrm_state_dev_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } #define XFRM_STATE_INSERT(by, _n, _h, _type) \ { \ struct xfrm_state *_x = NULL; \ \ if (_type != XFRM_DEV_OFFLOAD_PACKET) { \ hlist_for_each_entry_rcu(_x, _h, by) { \ if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ continue; \ break; \ } \ } \ \ if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ /* SAD is empty or consist from HW SAs only */ \ hlist_add_head_rcu(_n, _h); \ else \ hlist_add_before_rcu(_n, &_x->by); \ } static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_state *x; hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h, x->xso.type); } if (x->km.seq) { h = __xfrm_seq_hash(x->km.seq, nhashmask); XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h, x->xso.type); } } } static unsigned long xfrm_hash_new_size(unsigned int state_hmask) { return ((state_hmask + 1) << 1) * sizeof(struct hlist_head); } static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; nsize = xfrm_hash_new_size(net->xfrm.state_hmask); ndst = xfrm_hash_alloc(nsize); if (!ndst) return; nsrc = xfrm_hash_alloc(nsize); if (!nsrc) { xfrm_hash_free(ndst, nsize); return; } nspi = xfrm_hash_alloc(nsize); if (!nspi) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); return; } nseq = xfrm_hash_alloc(nsize); if (!nseq) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); xfrm_hash_free(nspi, nsize); return; } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); synchronize_rcu(); xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); static bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (!afinfo) return -EAFNOSUPPORT; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name); \ (afi)->type_ ## name = (T); \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } #undef X rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name != (T)); \ (afi)->type_ ## name = NULL; \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); break; } #undef X rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type); static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) { const struct xfrm_type *type = NULL; struct xfrm_state_afinfo *afinfo; int modload_attempted = 0; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_COMP: type = afinfo->type_comp; break; case IPPROTO_AH: type = afinfo->type_ah; break; case IPPROTO_ESP: type = afinfo->type_esp; break; case IPPROTO_IPIP: type = afinfo->type_ipip; break; case IPPROTO_DSTOPTS: type = afinfo->type_dstopts; break; case IPPROTO_ROUTING: type = afinfo->type_routing; break; case IPPROTO_IPV6: type = afinfo->type_ipip6; break; default: break; } if (unlikely(type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && !modload_attempted) { request_module("xfrm-type-%d-%d", family, proto); modload_attempted = 1; goto retry; } return type; } static void xfrm_put_type(const struct xfrm_type *type) { module_put(type->owner); } int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp); afinfo->type_offload_esp = type; break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type_offload); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp != type); afinfo->type_offload_esp = NULL; break; default: WARN_ON(1); break; } rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type_offload); void xfrm_set_type_offload(struct xfrm_state *x, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; retry: afinfo = xfrm_state_get_afinfo(x->props.family); if (unlikely(afinfo == NULL)) goto out; switch (x->id.proto) { case IPPROTO_ESP: type = afinfo->type_offload_esp; break; default: break; } if ((type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && try_load) { request_module("xfrm-offload-%d-%d", x->props.family, x->id.proto); try_load = false; goto retry; } out: x->type_offload = type; } EXPORT_SYMBOL(xfrm_set_type_offload); static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_IPTFS] = { .encap = XFRM_MODE_IPTFS, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, }; static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_ROUTEOPTIMIZATION] = { .encap = XFRM_MODE_ROUTEOPTIMIZATION, .family = AF_INET6, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET6, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_IPTFS] = { .encap = XFRM_MODE_IPTFS, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, }; static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) { const struct xfrm_mode *mode; if (unlikely(encap >= XFRM_MODE_MAX)) return NULL; switch (family) { case AF_INET: mode = &xfrm4_mode_map[encap]; if (mode->family == family) return mode; break; case AF_INET6: mode = &xfrm6_mode_map[encap]; if (mode->family == family) return mode; break; default: break; } return NULL; } static const struct xfrm_mode_cbs __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX]; static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock); int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs) { if (mode >= XFRM_MODE_MAX) return -EINVAL; spin_lock_bh(&xfrm_mode_cbs_map_lock); rcu_assign_pointer(xfrm_mode_cbs_map[mode], mode_cbs); spin_unlock_bh(&xfrm_mode_cbs_map_lock); return 0; } EXPORT_SYMBOL(xfrm_register_mode_cbs); void xfrm_unregister_mode_cbs(u8 mode) { if (mode >= XFRM_MODE_MAX) return; spin_lock_bh(&xfrm_mode_cbs_map_lock); RCU_INIT_POINTER(xfrm_mode_cbs_map[mode], NULL); spin_unlock_bh(&xfrm_mode_cbs_map_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_mode_cbs); static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode) { const struct xfrm_mode_cbs *cbs; bool try_load = true; if (mode >= XFRM_MODE_MAX) return NULL; retry: rcu_read_lock(); cbs = rcu_dereference(xfrm_mode_cbs_map[mode]); if (cbs && !try_module_get(cbs->owner)) cbs = NULL; rcu_read_unlock(); if (mode == XFRM_MODE_IPTFS && !cbs && try_load) { request_module("xfrm-iptfs"); try_load = false; goto retry; } return cbs; } void xfrm_state_free(struct xfrm_state *x) { kmem_cache_free(xfrm_state_cache, x); } EXPORT_SYMBOL(xfrm_state_free); static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); hrtimer_cancel(&x->mtimer); timer_delete_sync(&x->rtimer); kfree_sensitive(x->aead); kfree_sensitive(x->aalg); kfree_sensitive(x->ealg); kfree(x->calg); kfree(x->encap); kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); xfrm_unset_type_offload(x); xfrm_state_delete_tunnel(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); } if (x->xfrag.page) put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) { struct xfrm_state *x; struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&xfrm_state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); enum hrtimer_restart ret = HRTIMER_NORESTART; time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int err = 0; spin_lock(&x->lock); xfrm_dev_state_update_stats(x); if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { /* enter hard expire without soft expire first?! * setting a new date could trigger this. * workaround: fix x->curflt.add_time by below: */ x->curlft.add_time = now - x->saved_tmo - 1; tmo = x->lft.hard_add_expires_seconds - x->saved_tmo; } else goto expired; } if (tmo < next) next = tmo; } if (x->lft.hard_use_expires_seconds) { time64_t tmo = x->lft.hard_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; x->xflags &= ~XFRM_SOFT_EXPIRE; } else if (tmo < next) { next = tmo; x->xflags |= XFRM_SOFT_EXPIRE; x->saved_tmo = tmo; } } if (x->lft.soft_use_expires_seconds) { time64_t tmo = x->lft.soft_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) next = tmo; } x->km.dying = warn; if (warn) km_state_expired(x, 0, 0); resched: if (next != TIME64_MAX) { hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); ret = HRTIMER_RESTART; } goto out; expired: if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; err = __xfrm_state_delete(x); if (!err) km_state_expired(x, 1, 0); xfrm_audit_state_delete(x, err ? 0 : 1, true); out: spin_unlock(&x->lock); return ret; } static void xfrm_replay_timer_handler(struct timer_list *t); struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC); if (x) { write_pnet(&x->xs_net, net); refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->state_cache); INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); INIT_HLIST_NODE(&x->byseq); hrtimer_setup(&x->mtimer, xfrm_timer_handler, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; x->pcpu_num = UINT_MAX; spin_lock_init(&x->lock); x->mode_data = NULL; } return x; } EXPORT_SYMBOL(xfrm_state_alloc); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_state_delete(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev) { dev->xfrmdev_ops->xdo_dev_state_delete(dev, x); spin_lock_bh(&xfrm_state_dev_gc_lock); hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list); spin_unlock_bh(&xfrm_state_dev_gc_lock); } } EXPORT_SYMBOL_GPL(xfrm_dev_state_delete); void xfrm_dev_state_free(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev && dev->xfrmdev_ops) { spin_lock_bh(&xfrm_state_dev_gc_lock); if (!hlist_unhashed(&x->dev_gclist)) hlist_del(&x->dev_gclist); spin_unlock_bh(&xfrm_state_dev_gc_lock); if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(dev, x); WRITE_ONCE(xso->dev, NULL); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; netdev_put(dev, &xso->dev_tracker); } } #endif void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); spin_lock_bh(&xfrm_state_gc_lock); hlist_add_head(&x->gclist, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); int err = -ESRCH; if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del_rcu(&x->bydst); hlist_del_rcu(&x->bysrc); if (x->km.seq) hlist_del_rcu(&x->byseq); if (!hlist_unhashed(&x->state_cache)) hlist_del_rcu(&x->state_cache); if (!hlist_unhashed(&x->state_cache_input)) hlist_del_rcu(&x->state_cache_input); if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); xfrm_dev_state_delete(x); xfrm_state_delete_tunnel(x); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. */ xfrm_state_put(x); err = 0; } return err; } EXPORT_SYMBOL(__xfrm_state_delete); int xfrm_state_delete(struct xfrm_state *x) { int err; spin_lock_bh(&x->lock); err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; struct xfrm_dev_offload *xso; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (xso->dev == dev && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } #else static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) err = 0; return err; } EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { struct xfrm_state *x; struct hlist_node *tmp; struct xfrm_dev_offload *xso; int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_dev_state_free(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } if (cnt) err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); spin_lock_bh(&xfrm_state_dev_gc_lock); restart_gc: hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) { xso = &x->xso; if (xso->dev == dev) { spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_dev_state_free(x); spin_lock_bh(&xfrm_state_dev_gc_lock); goto restart_gc; } } spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_flush_gc(); return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); static void __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; sel->daddr.a4 = fl4->daddr; sel->saddr.a4 = fl4->saddr; sel->dport = xfrm_flowi_dport(fl, &fl4->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl4->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET; sel->prefixlen_d = 32; sel->prefixlen_s = 32; sel->proto = fl4->flowi4_proto; sel->ifindex = fl4->flowi4_oif; } static void __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; /* Initialize temporary selector matching only to current session. */ *(struct in6_addr *)&sel->daddr = fl6->daddr; *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET6; sel->prefixlen_d = 128; sel->prefixlen_s = 128; sel->proto = fl6->flowi6_proto; sel->ifindex = fl6->flowi6_oif; } static void xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: __xfrm4_init_tempsel(&x->sel, fl); break; case AF_INET6: __xfrm6_init_tempsel(&x->sel, fl); break; } x->id = tmpl->id; switch (tmpl->encap_family) { case AF_INET: if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; break; case AF_INET6: if (ipv6_addr_any((struct in6_addr *)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr *)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); break; } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = tmpl->encap_family; } struct xfrm_hash_state_ptrs { const struct hlist_head *bydst; const struct hlist_head *bysrc; const struct hlist_head *byspi; unsigned int hmask; }; static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs) { unsigned int sequence; do { sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net); ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net); ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net); ptrs->hmask = net->xfrm.state_hmask; } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)); } static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, struct xfrm_dev_offload *xdo) { unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { #ifdef CONFIG_XFRM_OFFLOAD if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (xdo->dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct hlist_head *state_cache_input; struct xfrm_state *x = NULL; state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input); rcu_read_lock(); hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; goto out; } xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); if (x && x->km.state == XFRM_STATE_VALID) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (hlist_unhashed(&x->state_cache_input)) { hlist_add_head_rcu(&x->state_cache_input, state_cache_input); } else { hlist_del_rcu(&x->state_cache_input); hlist_add_head_rcu(&x->state_cache_input, state_cache_input); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); } out: rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_input_state_lookup); static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; xfrm_hash_ptrs_get(net, &state_ptrs); if (use_spi) return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else return __xfrm_state_lookup_byaddr(&state_ptrs, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); } static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) { if (have_hash_collision && (net->xfrm.state_hmask + 1) < xfrm_state_hashmax && net->xfrm.state_num > net->xfrm.state_hmask) schedule_work(&net->xfrm.state_hash_work); } static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, int *error, unsigned int pcpu_id) { /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. * * Entering area of "sysdeps". * * 3. If state is not valid, selector is temporary, it selects * only session which triggered previous resolution. Key * manager will do something to install a state with proper * selector. */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && (x->sel.family != family || !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) return; if (x->pcpu_num != UINT_MAX && x->pcpu_num != pcpu_id) return; if (!*best || ((*best)->pcpu_num == UINT_MAX && x->pcpu_num == pcpu_id) || (*best)->km.dying > x->km.dying || ((*best)->km.dying == x->km.dying && (*best)->curlft.add_time < x->curlft.add_time)) *best = x; } else if (x->km.state == XFRM_STATE_ACQ) { if (!*best || x->pcpu_num == pcpu_id) *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if ((!x->sel.family || (x->sel.family == family && xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) *error = -ESRCH; } } struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; unsigned int pcpu_id; bool cached = false; /* We need the cpu id just as a lookup key, * we don't require it to be stable. */ pcpu_id = raw_smp_processor_id(); to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, encap_family, &best, &acquire_in_progress, &error, pcpu_id); } if (best) goto cached; hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } cached: cached = true; if (best) goto found; else if (error) best = NULL; else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } if (best || acquire_in_progress) goto found; h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } found: if (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) || (best && (best->pcpu_num == pcpu_id))) x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family, &pol->xdo)) != NULL) { to_put = x0; error = -EEXIST; goto out; } c.net = net; /* If the KMs have no listeners (yet...), avoid allocating an SA * for each and every packet - garbage collection might not * handle the flood. */ if (!km_is_alive(&c)) { error = -ESRCH; goto out; } x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; goto out; } /* Initialize temporary state matching only * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); x->if_id = if_id; if ((pol->flags & XFRM_POLICY_CPU_ACQUIRE) && best) x->pcpu_num = pcpu_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { struct xfrm_dev_offload *xdo = &pol->xdo; struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = xdo->dev; xso->type = XFRM_DEV_OFFLOAD_PACKET; xso->dir = xdo->dir; xso->dev = dev; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; netdev_hold(dev, &xso->dev_tracker, GFP_ATOMIC); error = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, NULL); if (error) { xso->dir = 0; netdev_put(dev, &xso->dev_tracker); xso->dev = NULL; xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } } #endif if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; x->dir = XFRM_SA_DIR_OUT; list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); INIT_HLIST_NODE(&x->state_cache); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { #ifdef CONFIG_XFRM_OFFLOAD struct xfrm_dev_offload *xso = &x->xso; if (xso->type == XFRM_DEV_OFFLOAD_PACKET) { xfrm_dev_state_delete(x); xfrm_dev_state_free(x); } #endif x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; error = -ESRCH; } /* Use the already installed 'fallback' while the CPU-specific * SA acquire is handled*/ if (best) x = best; } out: if (x) { if (!xfrm_state_hold_rcu(x)) { *err = -EAGAIN; x = NULL; } } else { *err = acquire_in_progress ? -EAGAIN : error; } if (x && x->km.state == XFRM_STATE_VALID && !cached && (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) || x->pcpu_num == pcpu_id)) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (hlist_unhashed(&x->state_cache)) hlist_add_head_rcu(&x->state_cache, &pol->state_cache_list); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } rcu_read_unlock(); if (to_put) xfrm_state_put(to_put); if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); x = NULL; } } return x; } struct xfrm_state * xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && proto == x->id.proto && x->km.state == XFRM_STATE_VALID) { rx = x; break; } } if (rx) xfrm_state_hold(rx); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family) { struct xfrm_state *x; struct xfrm_state_walk *w; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_for_each_entry(w, &net->xfrm.state_all, all) { x = container_of(w, struct xfrm_state, km); if (x->props.family != family || x->id.spi != spi) continue; xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return NULL; } EXPORT_SYMBOL(xfrm_state_lookup_byspi); static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 spi, u8 proto) { struct xfrm_state *x; unsigned int i; rcu_read_lock(); for (i = 0; i <= net->xfrm.state_hmask; i++) { hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) { if (x->id.spi == spi && x->id.proto == proto) { if (!xfrm_state_hold_rcu(x)) continue; rcu_read_unlock(); return x; } } } rcu_read_unlock(); return NULL; } static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); unsigned int h; list_add(&x->km.all, &net->xfrm.state_all); /* Sanitize mark before store */ x->mark.v &= x->mark.m; h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, x->xso.type); } hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; u32 if_id = xnew->if_id; u32 cpu_id = xnew->pcpu_num; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && x->pcpu_num == cpu_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) x->genid++; } } void xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); /* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct xfrm_state *x; u32 mark = m->v & m->m; hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || x->id.proto != proto || (mark & x->mark.m) != x->mark.v || x->pcpu_num != pcpu_num || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; xfrm_state_hold(x); return x; } if (!create) return NULL; x = xfrm_state_alloc(net); if (likely(x)) { switch (family) { case AF_INET: x->sel.daddr.a4 = daddr->a4; x->sel.saddr.a4 = saddr->a4; x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->props.saddr.a4 = saddr->a4; x->id.daddr.a4 = daddr->a4; break; case AF_INET6: x->sel.daddr.in6 = daddr->in6; x->sel.saddr.in6 = saddr->in6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->props.saddr.in6 = saddr->in6; x->id.daddr.in6 = daddr->in6; break; } x->pcpu_num = pcpu_num; x->km.state = XFRM_STATE_ACQ; x->id.proto = proto; x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } return x; } static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_add(struct xfrm_state *x) { struct net *net = xs_net(x); struct xfrm_state *x1, *to_put; int family; int err; u32 mark = x->mark.v & x->mark.m; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); family = x->props.family; to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { to_put = x1; x1 = NULL; err = -EEXIST; goto out; } if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq, x->pcpu_num); if (x1 && ((x1->id.proto != x->id.proto) || !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; x1 = NULL; } } if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, x->props.reqid, x->if_id, x->pcpu_num, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); xfrm_state_put(x1); } if (to_put) xfrm_state_put(to_put); return err; } EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) { struct xfrm_user_sec_ctx *uctx; int size = sizeof(*uctx) + security->ctx_len; int err; uctx = kmalloc(size, GFP_KERNEL); if (!uctx) return -ENOMEM; uctx->exttype = XFRMA_SEC_CTX; uctx->len = size; uctx->ctx_doi = security->ctx_doi; uctx->ctx_alg = security->ctx_alg; uctx->ctx_len = security->ctx_len; memcpy(uctx + 1, security->ctx_str, security->ctx_len); err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) return err; return 0; } static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap, struct xfrm_migrate *m) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; memcpy(&x->id, &orig->id, sizeof(x->id)); memcpy(&x->sel, &orig->sel, sizeof(x->sel)); memcpy(&x->lft, &orig->lft, sizeof(x->lft)); x->props.mode = orig->props.mode; x->props.replay_window = orig->props.replay_window; x->props.reqid = orig->props.reqid; x->props.family = orig->props.family; x->props.saddr = orig->props.saddr; if (orig->aalg) { x->aalg = xfrm_algo_auth_clone(orig->aalg); if (!x->aalg) goto error; } x->props.aalgo = orig->props.aalgo; if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); x->geniv = orig->geniv; if (!x->aead) goto error; } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) goto error; } x->props.ealgo = orig->props.ealgo; if (orig->calg) { x->calg = xfrm_algo_clone(orig->calg); if (!x->calg) goto error; } x->props.calgo = orig->props.calgo; if (encap || orig->encap) { if (encap) x->encap = kmemdup(encap, sizeof(*x->encap), GFP_KERNEL); else x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL); if (!x->encap) goto error; } if (orig->security) if (clone_security(x, orig->security)) goto error; if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); if (!x->coaddr) goto error; } if (orig->replay_esn) { if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; x->pcpu_num = orig->pcpu_num; x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; x->preplay = orig->preplay; x->mapping_maxage = orig->mapping_maxage; x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; x->dir = orig->dir; x->mode_cbs = orig->mode_cbs; if (x->mode_cbs && x->mode_cbs->clone_state) { if (x->mode_cbs->clone_state(x, orig)) goto error; } x->props.family = m->new_family; memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr)); memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr)); return x; error: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); out: return NULL; } struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (m->reqid && x->props.reqid != m->reqid) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap, struct net *net, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { struct xfrm_state *xc; xc = xfrm_state_clone_and_setup(x, encap, m); if (!xc) return NULL; if (xfrm_init_state(xc) < 0) goto error; /* configure the hardware if offload is requested */ if (xuo && xfrm_dev_state_add(net, xc, xuo, extack)) goto error; /* add state */ if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) { /* a care is needed when the destination address of the state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) goto error_add; } return xc; error_add: if (xuo) xfrm_dev_state_delete(xc); error: xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return NULL; } EXPORT_SYMBOL(xfrm_state_migrate); #endif int xfrm_state_update(struct xfrm_state *x) { struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); struct net *net = xs_net(x); to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; if (!x1) goto out; if (xfrm_state_kern(x1)) { to_put = x1; err = -EEXIST; goto out; } if (x1->km.state == XFRM_STATE_ACQ) { if (x->dir && x1->dir != x->dir) { to_put = x1; goto out; } __xfrm_state_insert(x); x = NULL; } else { if (x1->dir != x->dir) { to_put = x1; goto out; } } err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); if (err) return err; if (!x) { xfrm_state_delete(x1); xfrm_state_put(x1); return 0; } err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { if (x->encap && x1->encap && x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); else if (x->encap || x1->encap) goto fail; if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel))) memcpy(&x1->sel, &x->sel, sizeof(x1->sel)); memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (x->props.smark.m || x->props.smark.v) x1->props.smark = x->props.smark; if (x->if_id) x1->if_id = x->if_id; __xfrm_state_bump_genids(x1); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); return err; } EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { /* All counters which are needed to decide if state is expired * are handled by SW for non-packet offload modes. Simply skip * the following update and save extra boilerplate in drivers. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; } if (!x->km.dying && (x->curlft.bytes >= x->lft.soft_byte_limit || x->curlft.packets >= x->lft.soft_packet_limit)) { x->km.dying = 1; km_state_expired(x, 0, 0); } return 0; } EXPORT_SYMBOL(xfrm_state_check_expire); void xfrm_state_update_stats(struct net *net) { struct xfrm_state *x; int i; spin_lock_bh(&net->xfrm.xfrm_state_lock); for (i = 0; i <= net->xfrm.state_hmask; i++) { hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst) xfrm_dev_state_update_stats(x); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); } struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, if_id, pcpu_num, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY #if IS_ENABLED(CONFIG_IPV6) /* distribution counting sort function for xfrm_state and xfrm_tmpl */ static void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; int i; for (i = 0; i < n; i++) { int c = cmp(src[i]); class[i] = c; count[c]++; } for (i = 2; i < maxclass; i++) count[i] += count[i - 1]; for (i = 0; i < n; i++) { dst[count[class[i] - 1]++] = src[i]; src[i] = NULL; } } /* Rule for xfrm_state: * * rule 1: select IPsec transport except AH * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec transport AH * rule 4: select IPsec tunnel * rule 5: others */ static int __xfrm6_state_sort_cmp(const void *p) { const struct xfrm_state *v = p; switch (v->props.mode) { case XFRM_MODE_TRANSPORT: if (v->id.proto != IPPROTO_AH) return 1; else return 3; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: return 4; } return 5; } /* Rule for xfrm_tmpl: * * rule 1: select IPsec transport * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec tunnel * rule 4: others */ static int __xfrm6_tmpl_sort_cmp(const void *p) { const struct xfrm_tmpl *v = p; switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: return 3; } return 4; } #else static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; } static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; } static inline void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int i; for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* CONFIG_IPV6 */ void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_tmpl_sort_cmp, 5); else for (i = 0; i < n; i++) dst[i] = src[i]; } void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_state_sort_cmp, 6); else for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* Silly enough, but I'm lazy to build resolution list */ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num) { unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->pcpu_num == pcpu_num && x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); return x; } } return NULL; } struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq, pcpu_num); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); u32 xfrm_get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } EXPORT_SYMBOL(xfrm_get_acqseq); int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: break; case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ if (max >= 0x10000) { NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535"); return -EINVAL; } break; default: NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP"); return -EINVAL; } if (min > max) { NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max"); return -EINVAL; } return 0; } EXPORT_SYMBOL(verify_spi_info); int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, struct netlink_ext_ack *extack) { struct net *net = xs_net(x); unsigned int h; struct xfrm_state *x0; int err = -ENOENT; u32 range = high - low + 1; __be32 newspi = 0; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_DEAD) { NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state"); goto unlock; } err = 0; if (x->id.spi) goto unlock; err = -ENOENT; for (h = 0; h < range; h++) { u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high); if (spi == 0) goto next; newspi = htonl(spi); spin_lock_bh(&net->xfrm.xfrm_state_lock); x0 = xfrm_state_lookup_spi_proto(net, newspi, x->id.proto); if (!x0) { x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; goto unlock; } xfrm_state_put(x0); spin_unlock_bh(&net->xfrm.xfrm_state_lock); next: if (signal_pending(current)) { err = -ERESTARTSYS; goto unlock; } if (low == high) break; } if (err) NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); unlock: spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_alloc_spi); static bool __xfrm_state_filter_match(struct xfrm_state *x, struct xfrm_address_filter *filter) { if (filter) { if ((filter->family == AF_INET || filter->family == AF_INET6) && x->props.family != filter->family) return false; return addr_match(&x->props.saddr, &filter->saddr, filter->splen) && addr_match(&x->id.daddr, &filter->daddr, filter->dplen); } return true; } int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) { struct xfrm_state *state; struct xfrm_state_walk *x; int err = 0; if (walk->seq != 0 && list_empty(&walk->all)) return 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; if (!__xfrm_state_filter_match(state, walk->filter)) continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { err = -ENOENT; goto out; } list_del_init(&walk->all); out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { kfree(walk->filter); if (list_empty(&walk->all)) return; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(struct timer_list *t) { struct xfrm_state *x = timer_container_of(x, t, rtimer); spin_lock(&x->lock); if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } spin_unlock(&x->lock); } static LIST_HEAD(xfrm_km_list); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); } EXPORT_SYMBOL(km_state_expired); /* * We send to all registered managers regardless of failure * We are happy with one success */ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { int err = -EINVAL, acqret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } rcu_read_unlock(); return err; } int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int ret = 0; if (x->mapping_maxage) { if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || x->new_mapping_sport != sport) { x->new_mapping_sport = sport; x->new_mapping = jiffies / HZ; ret = __km_new_mapping(x, ipaddr, sport); } } else { ret = __km_new_mapping(x, ipaddr, sport); } return ret; } EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); } EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k, encap); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); #endif int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); static bool km_is_alive(const struct km_event *c) { struct xfrm_mgr *km; bool is_alive = false; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->is_alive && km->is_alive(c)) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) static DEFINE_SPINLOCK(xfrm_translator_lock); static struct xfrm_translator __rcu *xfrm_translator; struct xfrm_translator *xfrm_get_translator(void) { struct xfrm_translator *xtr; rcu_read_lock(); xtr = rcu_dereference(xfrm_translator); if (unlikely(!xtr)) goto out; if (!try_module_get(xtr->owner)) xtr = NULL; out: rcu_read_unlock(); return xtr; } EXPORT_SYMBOL_GPL(xfrm_get_translator); void xfrm_put_translator(struct xfrm_translator *xtr) { module_put(xtr->owner); } EXPORT_SYMBOL_GPL(xfrm_put_translator); int xfrm_register_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (unlikely(xfrm_translator != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_translator, xtr); spin_unlock_bh(&xfrm_translator_lock); return err; } EXPORT_SYMBOL_GPL(xfrm_register_translator); int xfrm_unregister_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (likely(xfrm_translator != NULL)) { if (rcu_access_pointer(xfrm_translator) != xtr) err = -EINVAL; else RCU_INIT_POINTER(xfrm_translator, NULL); } spin_unlock_bh(&xfrm_translator_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(xfrm_unregister_translator); #endif int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { int err; u8 *data; struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); __sk_dst_reset(sk); return 0; } if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE; data = memdup_sockptr(optval, optlen); if (IS_ERR(data)) return PTR_ERR(data); if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); if (!xtr) { kfree(data); return -EOPNOTSUPP; } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); if (err) { kfree(data); return err; } } err = -EINVAL; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); __sk_dst_reset(sk); err = 0; } kfree(data); return err; } EXPORT_SYMBOL(xfrm_user_policy); static DEFINE_SPINLOCK(xfrm_km_lock); void xfrm_register_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_add_tail_rcu(&km->list, &xfrm_km_list); spin_unlock_bh(&xfrm_km_lock); } EXPORT_SYMBOL(xfrm_register_km); void xfrm_unregister_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_del_rcu(&km->list); spin_unlock_bh(&xfrm_km_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_km); int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0, family = afinfo->family; if (WARN_ON(family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo) err = -EINVAL; else RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } spin_unlock_bh(&xfrm_state_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family) { if (unlikely(family >= NPROTO)) return NULL; return rcu_dereference(xfrm_state_afinfo[family]); } EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } void xfrm_flush_gc(void) { flush_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(xfrm_flush_gc); static void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; if (atomic_dec_return(&t->tunnel_users) == 1) xfrm_state_delete(t); xfrm_state_put(t); x->tunnel = NULL; } } u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; u32 blksize, net_adj = 0; if (x->km.state != XFRM_STATE_VALID || !type || type->proto != IPPROTO_ESP) return mtu - x->props.header_len; aead = x->data; blksize = ALIGN(crypto_aead_blocksize(aead), 4); switch (x->props.mode) { case XFRM_MODE_TRANSPORT: case XFRM_MODE_BEET: if (x->props.family == AF_INET) net_adj = sizeof(struct iphdr); else if (x->props.family == AF_INET6) net_adj = sizeof(struct ipv6hdr); break; case XFRM_MODE_TUNNEL: break; default: if (x->mode_cbs && x->mode_cbs->get_inner_mtu) return x->mode_cbs->get_inner_mtu(x, mtu); WARN_ON_ONCE(1); break; } return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { const struct xfrm_mode *inner_mode; const struct xfrm_mode *outer_mode; int family = x->props.family; int err; if (family == AF_INET && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; if (x->sel.family != AF_UNSPEC) { inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && family != x->sel.family) { NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family"); goto error; } x->inner_mode = *inner_mode; } else { const struct xfrm_mode *inner_mode_iaf; int iafamily = AF_INET; inner_mode = xfrm_get_mode(x->props.mode, x->props.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } x->inner_mode = *inner_mode; if (x->props.family == AF_INET) iafamily = AF_INET6; inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily); if (inner_mode_iaf) { if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL) x->inner_mode_iaf = *inner_mode_iaf; } } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) { NL_SET_ERR_MSG(extack, "Requested type not found"); goto error; } err = x->type->init_state(x, extack); if (err) goto error; outer_mode = xfrm_get_mode(x->props.mode, family); if (!outer_mode) { NL_SET_ERR_MSG(extack, "Requested mode not found"); err = -EPROTONOSUPPORT; goto error; } x->outer_mode = *outer_mode; if (x->nat_keepalive_interval) { if (x->dir != XFRM_SA_DIR_OUT) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); err = -EINVAL; goto error; } if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for UDP encapsulation"); err = -EINVAL; goto error; } } x->mode_cbs = xfrm_get_mode_cbs(x->props.mode); if (x->mode_cbs) { if (x->mode_cbs->init_state) err = x->mode_cbs->init_state(x); module_put(x->mode_cbs->owner); } error: return err; } EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { int err; err = __xfrm_init_state(x, NULL); if (err) return err; err = xfrm_init_replay(x, NULL); if (err) return err; x->km.state = XFRM_STATE_VALID; return 0; } EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { unsigned int sz; if (net_eq(net, &init_net)) xfrm_state_cache = KMEM_CACHE(xfrm_state, SLAB_HWCACHE_ALIGN | SLAB_PANIC); INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; net->xfrm.state_bydst = xfrm_hash_alloc(sz); if (!net->xfrm.state_bydst) goto out_bydst; net->xfrm.state_bysrc = xfrm_hash_alloc(sz); if (!net->xfrm.state_bysrc) goto out_bysrc; net->xfrm.state_byspi = xfrm_hash_alloc(sz); if (!net->xfrm.state_byspi) goto out_byspi; net->xfrm.state_byseq = xfrm_hash_alloc(sz); if (!net->xfrm.state_byseq) goto out_byseq; net->xfrm.state_cache_input = alloc_percpu(struct hlist_head); if (!net->xfrm.state_cache_input) goto out_state_cache_input; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, &net->xfrm.xfrm_state_lock); return 0; out_state_cache_input: xfrm_hash_free(net->xfrm.state_byseq, sz); out_byseq: xfrm_hash_free(net->xfrm.state_byspi, sz); out_byspi: xfrm_hash_free(net->xfrm.state_bysrc, sz); out_bysrc: xfrm_hash_free(net->xfrm.state_bydst, sz); out_bydst: return -ENOMEM; } void xfrm_state_fini(struct net *net) { unsigned int sz; int i; flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); for (i = 0; i <= net->xfrm.state_hmask; i++) { WARN_ON(!hlist_empty(net->xfrm.state_byseq + i)); WARN_ON(!hlist_empty(net->xfrm.state_byspi + i)); WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i)); WARN_ON(!hlist_empty(net->xfrm.state_bydst + i)); } sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); xfrm_hash_free(net->xfrm.state_byseq, sz); xfrm_hash_free(net->xfrm.state_byspi, sz); xfrm_hash_free(net->xfrm.state_bysrc, sz); xfrm_hash_free(net->xfrm.state_bydst, sz); free_percpu(net->xfrm.state_cache_input); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_helper_sainfo(struct xfrm_state *x, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = x->security; u32 spi = ntohl(x->id.spi); if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6 dst=%pI6", x->props.saddr.a6, x->id.daddr.a6); break; } audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); } static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, struct audit_buffer *audit_buf) { const struct iphdr *iph4; const struct ipv6hdr *iph6; switch (family) { case AF_INET: iph4 = ip_hdr(skb); audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &iph4->saddr, &iph4->daddr); break; case AF_INET6: iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); break; } } void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_add); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_delete); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replay-overflow"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); /* don't record the sequence number because it's inherent in this kind * of audit message */ spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replayed-pkt"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { struct audit_buffer *audit_buf; __be32 net_spi; __be32 net_seq; audit_buf = xfrm_audit_start("SA-icv-failure"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) { u32 spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); } audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail); #endif /* CONFIG_AUDITSYSCALL */ |
| 19 8 10 16 3 18 4 14 42 11 35 2346 2341 9 31 7 31 29 4 3 1 4 2 2 4 7 7 3 1 2 2 2 1 1 4 2 2 4 2 2 2 1 4 1 1 1 1 1 1 1 1 1 1 2 1 214 114 1 4 1 2 1 3 1 19 1 37 1 63 3 4 5 6 1 1 3 4 24 18 1 4 1 9 8 1 222 20 206 8 212 214 39 39 39 39 39 39 37 1 1 41 1 39 39 39 1 33 25 11 19 13 23 21 4 12 44 33 12 15 5 10 15 930 916 15 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #include "internal.h" #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } /* * Allocate an file->f_owner struct if it doesn't exist, handling racing * allocations correctly. */ int file_f_owner_allocate(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) return 0; f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); if (!f_owner) return -ENOMEM; rwlock_init(&f_owner->lock); f_owner->file = file; /* If someone else raced us, drop our allocation. */ if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) kfree(f_owner); return 0; } EXPORT_SYMBOL(file_f_owner_allocate); void file_f_owner_release(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) { put_pid(f_owner->pid); kfree(f_owner); } } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (WARN_ON_ONCE(!f_owner)) return; write_lock_irq(&f_owner->lock); if (force || !f_owner->pid) { put_pid(f_owner->pid); f_owner->pid = get_pid(pid); f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); f_owner->uid = cred->uid; f_owner->euid = cred->euid; } } write_unlock_irq(&f_owner->lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; might_sleep(); type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (!f_owner) return pid; read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) { pid = pid_vnr(f_owner->pid); if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&f_owner->lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; struct fown_struct *f_owner; enum pid_type pid_type = PIDTYPE_PID; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) owner.pid = pid_vnr(f_owner->pid); rcu_read_unlock(); pid_type = f_owner->pid_type; } switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } if (f_owner) read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; uid_t src[2] = {0, 0}; int err; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); src[0] = from_kuid(user_ns, f_owner->uid); src[1] = from_kuid(user_ns, f_owner->euid); read_unlock_irq(&f_owner->lock); } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return fd_file(f) == filp; } /* Let the caller figure out whether a given file was just created. */ static long f_created_query(const struct file *filp) { return !!(filp->f_mode & FMODE_CREATED); } static int f_owner_sig(struct file *filp, int signum, bool setsig) { int ret = 0; struct fown_struct *f_owner; might_sleep(); if (setsig) { if (!valid_signal(signum)) return -EINVAL; ret = file_f_owner_allocate(filp); if (ret) return ret; } f_owner = file_f_owner(filp); if (setsig) f_owner->signum = signum; else if (f_owner) ret = f_owner->signum; return ret; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; struct delegation deleg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_CREATED_QUERY: err = f_created_query(filp); break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = f_owner_sig(filp, 0, false); break; case F_SETSIG: err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, arg); break; case F_GETDELEG: if (copy_from_user(&deleg, argp, sizeof(deleg))) return -EFAULT; err = fcntl_getdeleg(filp, &deleg); if (!err && copy_to_user(argp, &deleg, sizeof(deleg))) return -EFAULT; break; case F_SETDELEG: if (copy_from_user(&deleg, argp, sizeof(deleg))) return -EFAULT; err = fcntl_setdeleg(fd, filp, &deleg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd_raw, f)(fd); long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, fd_file(f)); return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; CLASS(fd_raw, f)(fd); struct flock64 flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { CLASS(fd_raw, f)(fd); struct flock flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct file *file) { struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; fown = file_f_owner(file); if (!fown) return 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = file_f_owner(fa->fa_file); if (!fown) goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | #ifndef _LINUX_GENERIC_RADIX_TREE_H #define _LINUX_GENERIC_RADIX_TREE_H /** * DOC: Generic radix trees/sparse arrays * * Very simple and minimalistic, supporting arbitrary size entries up to * GENRADIX_NODE_SIZE. * * A genradix is defined with the type it will store, like so: * * static GENRADIX(struct foo) foo_genradix; * * The main operations are: * * - genradix_init(radix) - initialize an empty genradix * * - genradix_free(radix) - free all memory owned by the genradix and * reinitialize it * * - genradix_ptr(radix, idx) - gets a pointer to the entry at idx, returning * NULL if that entry does not exist * * - genradix_ptr_alloc(radix, idx, gfp) - gets a pointer to an entry, * allocating it if necessary * * - genradix_for_each(radix, iter, p) - iterate over each entry in a genradix * * The radix tree allocates one page of entries at a time, so entries may exist * that were never explicitly allocated - they will be initialized to all * zeroes. * * Internally, a genradix is just a radix tree of pages, and indexing works in * terms of byte offsets. The wrappers in this header file use sizeof on the * type the radix contains to calculate a byte offset from the index - see * __idx_to_offset. */ #include <asm/page.h> #include <linux/bug.h> #include <linux/limits.h> #include <linux/log2.h> #include <linux/math.h> #include <linux/slab.h> #include <linux/types.h> struct genradix_root; #define GENRADIX_NODE_SHIFT 9 #define GENRADIX_NODE_SIZE (1U << GENRADIX_NODE_SHIFT) #define GENRADIX_ARY (GENRADIX_NODE_SIZE / sizeof(struct genradix_node *)) #define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) /* depth that's needed for a genradix that can address up to ULONG_MAX: */ #define GENRADIX_MAX_DEPTH \ DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT) #define GENRADIX_DEPTH_MASK \ ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) static inline int genradix_depth_shift(unsigned depth) { return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth; } /* * Returns size (of data, in bytes) that a tree of a given depth holds: */ static inline size_t genradix_depth_size(unsigned depth) { return 1UL << genradix_depth_shift(depth); } static inline unsigned genradix_root_to_depth(struct genradix_root *r) { return (unsigned long) r & GENRADIX_DEPTH_MASK; } static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) { return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); } struct __genradix { struct genradix_root *root; }; struct genradix_node { union { /* Interior node: */ struct genradix_node *children[GENRADIX_ARY]; /* Leaf: */ u8 data[GENRADIX_NODE_SIZE]; }; }; static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) { return kzalloc(GENRADIX_NODE_SIZE, gfp_mask); } static inline void genradix_free_node(struct genradix_node *node) { kfree(node); } /* * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE: */ #define __GENRADIX_INITIALIZER \ { \ .tree = { \ .root = NULL, \ } \ } /* * We use a 0 size array to stash the type we're storing without taking any * space at runtime - then the various accessor macros can use typeof() to get * to it for casts/sizeof - we also force the alignment so that storing a type * with a ridiculous alignment doesn't blow up the alignment or size of the * genradix. */ #define GENRADIX(_type) \ struct { \ struct __genradix tree; \ _type type[0] __aligned(1); \ } #define DEFINE_GENRADIX(_name, _type) \ GENRADIX(_type) _name = __GENRADIX_INITIALIZER /** * genradix_init - initialize a genradix * @_radix: genradix to initialize * * Does not fail */ #define genradix_init(_radix) \ do { \ *(_radix) = (typeof(*_radix)) __GENRADIX_INITIALIZER; \ } while (0) void __genradix_free(struct __genradix *); /** * genradix_free: free all memory owned by a genradix * @_radix: the genradix to free * * After freeing, @_radix will be reinitialized and empty */ #define genradix_free(_radix) __genradix_free(&(_radix)->tree) static inline size_t __idx_to_offset(size_t idx, size_t obj_size) { if (__builtin_constant_p(obj_size)) BUILD_BUG_ON(obj_size > GENRADIX_NODE_SIZE); else BUG_ON(obj_size > GENRADIX_NODE_SIZE); if (!is_power_of_2(obj_size)) { size_t objs_per_page = GENRADIX_NODE_SIZE / obj_size; return (idx / objs_per_page) * GENRADIX_NODE_SIZE + (idx % objs_per_page) * obj_size; } else { return idx * obj_size; } } #define __genradix_cast(_radix) (typeof((_radix)->type[0]) *) #define __genradix_obj_size(_radix) sizeof((_radix)->type[0]) #define __genradix_objs_per_page(_radix) \ (GENRADIX_NODE_SIZE / sizeof((_radix)->type[0])) #define __genradix_page_remainder(_radix) \ (GENRADIX_NODE_SIZE % sizeof((_radix)->type[0])) #define __genradix_idx_to_offset(_radix, _idx) \ __idx_to_offset(_idx, __genradix_obj_size(_radix)) static inline void *__genradix_ptr_inlined(struct __genradix *radix, size_t offset) { struct genradix_root *r = READ_ONCE(radix->root); struct genradix_node *n = genradix_root_to_node(r); unsigned level = genradix_root_to_depth(r); unsigned shift = genradix_depth_shift(level); if (unlikely(ilog2(offset) >= genradix_depth_shift(level))) return NULL; while (n && shift > GENRADIX_NODE_SHIFT) { shift -= GENRADIX_ARY_SHIFT; n = n->children[offset >> shift]; offset &= (1UL << shift) - 1; } return n ? &n->data[offset] : NULL; } #define genradix_ptr_inlined(_radix, _idx) \ (__genradix_cast(_radix) \ __genradix_ptr_inlined(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx))) void *__genradix_ptr(struct __genradix *, size_t); /** * genradix_ptr - get a pointer to a genradix entry * @_radix: genradix to access * @_idx: index to fetch * * Returns a pointer to entry at @_idx, or NULL if that entry does not exist. */ #define genradix_ptr(_radix, _idx) \ (__genradix_cast(_radix) \ __genradix_ptr(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx))) void *__genradix_ptr_alloc(struct __genradix *, size_t, struct genradix_node **, gfp_t); #define genradix_ptr_alloc_inlined(_radix, _idx, _gfp) \ (__genradix_cast(_radix) \ (__genradix_ptr_inlined(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx)) ?: \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ NULL, _gfp))) #define genradix_ptr_alloc_preallocated_inlined(_radix, _idx, _new_node, _gfp)\ (__genradix_cast(_radix) \ (__genradix_ptr_inlined(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx)) ?: \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ _new_node, _gfp))) /** * genradix_ptr_alloc - get a pointer to a genradix entry, allocating it * if necessary * @_radix: genradix to access * @_idx: index to fetch * @_gfp: gfp mask * * Returns a pointer to entry at @_idx, or NULL on allocation failure */ #define genradix_ptr_alloc(_radix, _idx, _gfp) \ (__genradix_cast(_radix) \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ NULL, _gfp)) #define genradix_ptr_alloc_preallocated(_radix, _idx, _new_node, _gfp)\ (__genradix_cast(_radix) \ __genradix_ptr_alloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _idx), \ _new_node, _gfp)) struct genradix_iter { size_t offset; size_t pos; }; /** * genradix_iter_init - initialize a genradix_iter * @_radix: genradix that will be iterated over * @_idx: index to start iterating from */ #define genradix_iter_init(_radix, _idx) \ ((struct genradix_iter) { \ .pos = (_idx), \ .offset = __genradix_idx_to_offset((_radix), (_idx)),\ }) void *__genradix_iter_peek(struct genradix_iter *, struct __genradix *, size_t); /** * genradix_iter_peek - get first entry at or above iterator's current * position * @_iter: a genradix_iter * @_radix: genradix being iterated over * * If no more entries exist at or above @_iter's current position, returns NULL */ #define genradix_iter_peek(_iter, _radix) \ (__genradix_cast(_radix) \ __genradix_iter_peek(_iter, &(_radix)->tree, \ __genradix_objs_per_page(_radix))) void *__genradix_iter_peek_prev(struct genradix_iter *, struct __genradix *, size_t, size_t); /** * genradix_iter_peek_prev - get first entry at or below iterator's current * position * @_iter: a genradix_iter * @_radix: genradix being iterated over * * If no more entries exist at or below @_iter's current position, returns NULL */ #define genradix_iter_peek_prev(_iter, _radix) \ (__genradix_cast(_radix) \ __genradix_iter_peek_prev(_iter, &(_radix)->tree, \ __genradix_objs_per_page(_radix), \ __genradix_obj_size(_radix) + \ __genradix_page_remainder(_radix))) static inline void __genradix_iter_advance(struct genradix_iter *iter, size_t obj_size) { if (iter->offset + obj_size < iter->offset) { iter->offset = SIZE_MAX; iter->pos = SIZE_MAX; return; } iter->offset += obj_size; if (!is_power_of_2(obj_size) && (iter->offset & (GENRADIX_NODE_SIZE - 1)) + obj_size > GENRADIX_NODE_SIZE) iter->offset = round_up(iter->offset, GENRADIX_NODE_SIZE); iter->pos++; } #define genradix_iter_advance(_iter, _radix) \ __genradix_iter_advance(_iter, __genradix_obj_size(_radix)) static inline void __genradix_iter_rewind(struct genradix_iter *iter, size_t obj_size) { if (iter->offset == 0 || iter->offset == SIZE_MAX) { iter->offset = SIZE_MAX; return; } if ((iter->offset & (GENRADIX_NODE_SIZE - 1)) == 0) iter->offset -= GENRADIX_NODE_SIZE % obj_size; iter->offset -= obj_size; iter->pos--; } #define genradix_iter_rewind(_iter, _radix) \ __genradix_iter_rewind(_iter, __genradix_obj_size(_radix)) #define genradix_for_each_from(_radix, _iter, _p, _start) \ for (_iter = genradix_iter_init(_radix, _start); \ (_p = genradix_iter_peek(&_iter, _radix)) != NULL; \ genradix_iter_advance(&_iter, _radix)) /** * genradix_for_each - iterate over entry in a genradix * @_radix: genradix to iterate over * @_iter: a genradix_iter to track current position * @_p: pointer to genradix entry type * * On every iteration, @_p will point to the current entry, and @_iter.pos * will be the current entry's index. */ #define genradix_for_each(_radix, _iter, _p) \ genradix_for_each_from(_radix, _iter, _p, 0) #define genradix_last_pos(_radix) \ (SIZE_MAX / GENRADIX_NODE_SIZE * __genradix_objs_per_page(_radix) - 1) /** * genradix_for_each_reverse - iterate over entry in a genradix, reverse order * @_radix: genradix to iterate over * @_iter: a genradix_iter to track current position * @_p: pointer to genradix entry type * * On every iteration, @_p will point to the current entry, and @_iter.pos * will be the current entry's index. */ #define genradix_for_each_reverse(_radix, _iter, _p) \ for (_iter = genradix_iter_init(_radix, genradix_last_pos(_radix));\ (_p = genradix_iter_peek_prev(&_iter, _radix)) != NULL;\ genradix_iter_rewind(&_iter, _radix)) int __genradix_prealloc(struct __genradix *, size_t, gfp_t); /** * genradix_prealloc - preallocate entries in a generic radix tree * @_radix: genradix to preallocate * @_nr: number of entries to preallocate * @_gfp: gfp mask * * Returns 0 on success, -ENOMEM on failure */ #define genradix_prealloc(_radix, _nr, _gfp) \ __genradix_prealloc(&(_radix)->tree, \ __genradix_idx_to_offset(_radix, _nr + 1),\ _gfp) #endif /* _LINUX_GENERIC_RADIX_TREE_H */ |
| 51 53 53 4 54 52 53 1 49 4 51 55 1 54 54 54 53 1 143 142 55 1 54 55 55 55 55 1 54 54 54 54 54 53 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 | // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/recovery.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1999-2000 Red Hat Software --- All Rights Reserved * * Journal recovery routines for the generic filesystem journaling code; * part of the ext2fs journaling system. */ #ifndef __KERNEL__ #include "jfs_user.h" #else #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/crc32.h> #include <linux/blkdev.h> #include <linux/string_choices.h> #endif /* * Maintain information about the progress of the recovery job, so that * the different passes can carry information between them. */ struct recovery_info { tid_t start_transaction; tid_t end_transaction; unsigned long head_block; int nr_replays; int nr_revokes; int nr_revoke_hits; }; static int do_one_pass(journal_t *journal, struct recovery_info *info, enum passtype pass); static int scan_revoke_records(journal_t *, enum passtype, struct buffer_head *, tid_t, struct recovery_info *); #ifdef __KERNEL__ /* Release readahead buffers after use */ static void journal_brelse_array(struct buffer_head *b[], int n) { while (--n >= 0) brelse (b[n]); } /* * When reading from the journal, we are going through the block device * layer directly and so there is no readahead being done for us. We * need to implement any readahead ourselves if we want it to happen at * all. Recovery is basically one long sequential read, so make sure we * do the IO in reasonably large chunks. * * This is not so critical that we need to be enormously clever about * the readahead size, though. 128K is a purely arbitrary, good-enough * fixed value. */ #define MAXBUF 8 static void do_readahead(journal_t *journal, unsigned int start) { unsigned int max, nbufs, next; unsigned long long blocknr; struct buffer_head *bh; struct buffer_head * bufs[MAXBUF]; /* Do up to 128K of readahead */ max = start + (128 * 1024 / journal->j_blocksize); if (max > journal->j_total_len) max = journal->j_total_len; /* Do the readahead itself. We'll submit MAXBUF buffer_heads at * a time to the block device IO layer. */ nbufs = 0; for (next = start; next < max; next++) { int err = jbd2_journal_bmap(journal, next, &blocknr); if (err) { printk(KERN_ERR "JBD2: bad block at offset %u\n", next); goto failed; } bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) goto failed; if (!buffer_uptodate(bh) && !buffer_locked(bh)) { bufs[nbufs++] = bh; if (nbufs == MAXBUF) { bh_readahead_batch(nbufs, bufs, 0); journal_brelse_array(bufs, nbufs); nbufs = 0; } } else brelse(bh); } if (nbufs) bh_readahead_batch(nbufs, bufs, 0); failed: if (nbufs) journal_brelse_array(bufs, nbufs); } #endif /* __KERNEL__ */ /* * Read a block from the journal */ static int jread(struct buffer_head **bhp, journal_t *journal, unsigned int offset) { int err; unsigned long long blocknr; struct buffer_head *bh; *bhp = NULL; if (offset >= journal->j_total_len) { printk(KERN_ERR "JBD2: corrupted journal superblock\n"); return -EFSCORRUPTED; } err = jbd2_journal_bmap(journal, offset, &blocknr); if (err) { printk(KERN_ERR "JBD2: bad block at offset %u\n", offset); return err; } bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) return -ENOMEM; if (!buffer_uptodate(bh)) { /* * If this is a brand new buffer, start readahead. * Otherwise, we assume we are already reading it. */ bool need_readahead = !buffer_req(bh); bh_read_nowait(bh, 0); if (need_readahead) do_readahead(journal, offset); wait_on_buffer(bh); } if (!buffer_uptodate(bh)) { printk(KERN_ERR "JBD2: Failed to read block at offset %u\n", offset); brelse(bh); return -EIO; } *bhp = bh; return 0; } static int jbd2_descriptor_block_csum_verify(journal_t *j, void *buf) { struct jbd2_journal_block_tail *tail; __be32 provided; __u32 calculated; if (!jbd2_journal_has_csum_v2or3(j)) return 1; tail = (struct jbd2_journal_block_tail *)((char *)buf + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); provided = tail->t_checksum; tail->t_checksum = 0; calculated = jbd2_chksum(j->j_csum_seed, buf, j->j_blocksize); tail->t_checksum = provided; return provided == cpu_to_be32(calculated); } /* * Count the number of in-use tags in a journal descriptor block. */ static int count_tags(journal_t *journal, struct buffer_head *bh) { char * tagp; journal_block_tag_t tag; int nr = 0, size = journal->j_blocksize; int tag_bytes = journal_tag_bytes(journal); if (jbd2_journal_has_csum_v2or3(journal)) size -= sizeof(struct jbd2_journal_block_tail); tagp = &bh->b_data[sizeof(journal_header_t)]; while ((tagp - bh->b_data + tag_bytes) <= size) { memcpy(&tag, tagp, sizeof(tag)); nr++; tagp += tag_bytes; if (!(tag.t_flags & cpu_to_be16(JBD2_FLAG_SAME_UUID))) tagp += 16; if (tag.t_flags & cpu_to_be16(JBD2_FLAG_LAST_TAG)) break; } return nr; } /* Make sure we wrap around the log correctly! */ #define wrap(journal, var) \ do { \ if (var >= (journal)->j_last) \ var -= ((journal)->j_last - (journal)->j_first); \ } while (0) static int fc_do_one_pass(journal_t *journal, struct recovery_info *info, enum passtype pass) { unsigned int expected_commit_id = info->end_transaction; unsigned long next_fc_block; struct buffer_head *bh; int err = 0; next_fc_block = journal->j_fc_first; if (!journal->j_fc_replay_callback) return 0; while (next_fc_block <= journal->j_fc_last) { jbd2_debug(3, "Fast commit replay: next block %ld\n", next_fc_block); err = jread(&bh, journal, next_fc_block); if (err) { jbd2_debug(3, "Fast commit replay: read error\n"); break; } err = journal->j_fc_replay_callback(journal, bh, pass, next_fc_block - journal->j_fc_first, expected_commit_id); brelse(bh); next_fc_block++; if (err < 0 || err == JBD2_FC_REPLAY_STOP) break; err = 0; } if (err) jbd2_debug(3, "Fast commit replay failed, err = %d\n", err); return err; } /** * jbd2_journal_recover - recovers a on-disk journal * @journal: the journal to recover * * The primary function for recovering the log contents when mounting a * journaled device. * * Recovery is done in three passes. In the first pass, we look for the * end of the log. In the second, we assemble the list of revoke * blocks. In the third and final pass, we replay any un-revoked blocks * in the log. */ int jbd2_journal_recover(journal_t *journal) { int err, err2; struct recovery_info info; memset(&info, 0, sizeof(info)); /* * The journal superblock's s_start field (the current log head) * is always zero if, and only if, the journal was cleanly * unmounted. We use its in-memory version j_tail here because * jbd2_journal_wipe() could have updated it without updating journal * superblock. */ if (!journal->j_tail) { journal_superblock_t *sb = journal->j_superblock; jbd2_debug(1, "No recovery required, last transaction %d, head block %u\n", be32_to_cpu(sb->s_sequence), be32_to_cpu(sb->s_head)); journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1; journal->j_head = be32_to_cpu(sb->s_head); return 0; } err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); if (!err) err = do_one_pass(journal, &info, PASS_REPLAY); jbd2_debug(1, "JBD2: recovery, exit status %d, " "recovered transactions %u to %u\n", err, info.start_transaction, info.end_transaction); jbd2_debug(1, "JBD2: Replayed %d and revoked %d/%d blocks\n", info.nr_replays, info.nr_revoke_hits, info.nr_revokes); /* Restart the log at the next transaction ID, thus invalidating * any existing commit records in the log. */ journal->j_transaction_sequence = ++info.end_transaction; journal->j_head = info.head_block; jbd2_debug(1, "JBD2: last transaction %d, head block %lu\n", journal->j_transaction_sequence, journal->j_head); jbd2_journal_clear_revoke(journal); /* Free revoke table allocated for replay */ if (journal->j_revoke != journal->j_revoke_table[0] && journal->j_revoke != journal->j_revoke_table[1]) { jbd2_journal_destroy_revoke_table(journal->j_revoke); journal->j_revoke = journal->j_revoke_table[1]; } err2 = sync_blockdev(journal->j_fs_dev); if (!err) err = err2; err2 = jbd2_check_fs_dev_write_error(journal); if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ if (journal->j_flags & JBD2_BARRIER) { err2 = blkdev_issue_flush(journal->j_fs_dev); if (!err) err = err2; } return err; } /** * jbd2_journal_skip_recovery - Start journal and wipe exiting records * @journal: journal to startup * * Locate any valid recovery information from the journal and set up the * journal structures in memory to ignore it (presumably because the * caller has evidence that it is out of date). * This function doesn't appear to be exported.. * * We perform one pass over the journal to allow us to tell the user how * much recovery information is being erased, and to let us initialise * the journal transaction sequence numbers to the next unused ID. */ int jbd2_journal_skip_recovery(journal_t *journal) { int err; struct recovery_info info; memset (&info, 0, sizeof(info)); err = do_one_pass(journal, &info, PASS_SCAN); if (err) { printk(KERN_ERR "JBD2: error %d scanning journal\n", err); ++journal->j_transaction_sequence; journal->j_head = journal->j_first; } else { #ifdef CONFIG_JBD2_DEBUG int dropped = info.end_transaction - be32_to_cpu(journal->j_superblock->s_sequence); jbd2_debug(1, "JBD2: ignoring %d transaction%s from the journal.\n", dropped, str_plural(dropped)); #endif journal->j_transaction_sequence = ++info.end_transaction; journal->j_head = info.head_block; } journal->j_tail = 0; return err; } static inline unsigned long long read_tag_block(journal_t *journal, journal_block_tag_t *tag) { unsigned long long block = be32_to_cpu(tag->t_blocknr); if (jbd2_has_feature_64bit(journal)) block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; return block; } /* * calc_chksums calculates the checksums for the blocks described in the * descriptor block. */ static int calc_chksums(journal_t *journal, struct buffer_head *bh, unsigned long *next_log_block, __u32 *crc32_sum) { int i, num_blks, err; unsigned long io_block; struct buffer_head *obh; num_blks = count_tags(journal, bh); /* Calculate checksum of the descriptor block. */ *crc32_sum = crc32_be(*crc32_sum, (void *)bh->b_data, bh->b_size); for (i = 0; i < num_blks; i++) { io_block = (*next_log_block)++; wrap(journal, *next_log_block); err = jread(&obh, journal, io_block); if (err) { printk(KERN_ERR "JBD2: IO error %d recovering block " "%lu in log\n", err, io_block); return 1; } else { *crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data, obh->b_size); } put_bh(obh); } return 0; } static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) { struct commit_header *h; __be32 provided; __u32 calculated; if (!jbd2_journal_has_csum_v2or3(j)) return 1; h = buf; provided = h->h_chksum[0]; h->h_chksum[0] = 0; calculated = jbd2_chksum(j->j_csum_seed, buf, j->j_blocksize); h->h_chksum[0] = provided; return provided == cpu_to_be32(calculated); } static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf) { struct commit_header *h; __be32 provided; __u32 calculated; void *tmpbuf; tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL); if (!tmpbuf) return false; memcpy(tmpbuf, buf, sizeof(struct commit_header)); h = tmpbuf; provided = h->h_chksum[0]; h->h_chksum[0] = 0; calculated = jbd2_chksum(j->j_csum_seed, tmpbuf, j->j_blocksize); kfree(tmpbuf); return provided == cpu_to_be32(calculated); } static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, journal_block_tag3_t *tag3, void *buf, __u32 sequence) { __u32 csum32; __be32 seq; if (!jbd2_journal_has_csum_v2or3(j)) return 1; seq = cpu_to_be32(sequence); csum32 = jbd2_chksum(j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); csum32 = jbd2_chksum(csum32, buf, j->j_blocksize); if (jbd2_has_feature_csum3(j)) return tag3->t_checksum == cpu_to_be32(csum32); else return tag->t_checksum == cpu_to_be16(csum32); } static __always_inline int jbd2_do_replay(journal_t *journal, struct recovery_info *info, struct buffer_head *bh, unsigned long *next_log_block, unsigned int next_commit_ID) { char *tagp; int flags; int ret = 0; int tag_bytes = journal_tag_bytes(journal); int descr_csum_size = 0; unsigned long io_block; journal_block_tag_t tag; struct buffer_head *obh; struct buffer_head *nbh; if (jbd2_journal_has_csum_v2or3(journal)) descr_csum_size = sizeof(struct jbd2_journal_block_tail); tagp = &bh->b_data[sizeof(journal_header_t)]; while (tagp - bh->b_data + tag_bytes <= journal->j_blocksize - descr_csum_size) { int err; memcpy(&tag, tagp, sizeof(tag)); flags = be16_to_cpu(tag.t_flags); io_block = (*next_log_block)++; wrap(journal, *next_log_block); err = jread(&obh, journal, io_block); if (err) { /* Recover what we can, but report failure at the end. */ ret = err; pr_err("JBD2: IO error %d recovering block %lu in log\n", err, io_block); } else { unsigned long long blocknr; J_ASSERT(obh != NULL); blocknr = read_tag_block(journal, &tag); /* If the block has been revoked, then we're all done here. */ if (jbd2_journal_test_revoke(journal, blocknr, next_commit_ID)) { brelse(obh); ++info->nr_revoke_hits; goto skip_write; } /* Look for block corruption */ if (!jbd2_block_tag_csum_verify(journal, &tag, (journal_block_tag3_t *)tagp, obh->b_data, next_commit_ID)) { brelse(obh); ret = -EFSBADCRC; pr_err("JBD2: Invalid checksum recovering data block %llu in journal block %lu\n", blocknr, io_block); goto skip_write; } /* Find a buffer for the new data being restored */ nbh = __getblk(journal->j_fs_dev, blocknr, journal->j_blocksize); if (nbh == NULL) { pr_err("JBD2: Out of memory during recovery.\n"); brelse(obh); return -ENOMEM; } lock_buffer(nbh); memcpy(nbh->b_data, obh->b_data, journal->j_blocksize); if (flags & JBD2_FLAG_ESCAPE) { *((__be32 *)nbh->b_data) = cpu_to_be32(JBD2_MAGIC_NUMBER); } BUFFER_TRACE(nbh, "marking dirty"); set_buffer_uptodate(nbh); mark_buffer_dirty(nbh); BUFFER_TRACE(nbh, "marking uptodate"); ++info->nr_replays; unlock_buffer(nbh); brelse(obh); brelse(nbh); } skip_write: tagp += tag_bytes; if (!(flags & JBD2_FLAG_SAME_UUID)) tagp += 16; if (flags & JBD2_FLAG_LAST_TAG) break; } return ret; } static int do_one_pass(journal_t *journal, struct recovery_info *info, enum passtype pass) { unsigned int first_commit_ID, next_commit_ID; unsigned long next_log_block, head_block; int err, success = 0; journal_superblock_t * sb; journal_header_t * tmp; struct buffer_head *bh = NULL; unsigned int sequence; int blocktype; __u32 crc32_sum = ~0; /* Transactional Checksums */ bool need_check_commit_time = false; __u64 last_trans_commit_time = 0, commit_time; /* * First thing is to establish what we expect to find in the log * (in terms of transaction IDs), and where (in terms of log * block offsets): query the superblock. */ sb = journal->j_superblock; next_commit_ID = be32_to_cpu(sb->s_sequence); next_log_block = be32_to_cpu(sb->s_start); head_block = next_log_block; first_commit_ID = next_commit_ID; if (pass == PASS_SCAN) info->start_transaction = first_commit_ID; else if (pass == PASS_REVOKE) { /* * Would the default revoke table have too long hash chains * during replay? */ if (info->nr_revokes > JOURNAL_REVOKE_DEFAULT_HASH * 16) { unsigned int hash_size; /* * Aim for average chain length of 8, limit at 1M * entries to avoid problems with malicious * filesystems. */ hash_size = min(roundup_pow_of_two(info->nr_revokes / 8), 1U << 20); journal->j_revoke = jbd2_journal_init_revoke_table(hash_size); if (!journal->j_revoke) { printk(KERN_ERR "JBD2: failed to allocate revoke table for replay with %u entries. " "Journal replay may be slow.\n", hash_size); journal->j_revoke = journal->j_revoke_table[1]; } } } jbd2_debug(1, "Starting recovery pass %d\n", pass); /* * Now we walk through the log, transaction by transaction, * making sure that each transaction has a commit block in the * expected place. Each complete transaction gets replayed back * into the main filesystem. */ while (1) { cond_resched(); /* If we already know where to stop the log traversal, * check right now that we haven't gone past the end of * the log. */ if (pass != PASS_SCAN) if (tid_geq(next_commit_ID, info->end_transaction)) break; jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", next_commit_ID, next_log_block, journal->j_last); /* Skip over each chunk of the transaction looking * either the next descriptor block or the final commit * record. */ jbd2_debug(3, "JBD2: checking block %ld\n", next_log_block); brelse(bh); bh = NULL; err = jread(&bh, journal, next_log_block); if (err) goto failed; next_log_block++; wrap(journal, next_log_block); /* What kind of buffer is it? * * If it is a descriptor block, check that it has the * expected sequence number. Otherwise, we're all done * here. */ tmp = (journal_header_t *)bh->b_data; if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) break; blocktype = be32_to_cpu(tmp->h_blocktype); sequence = be32_to_cpu(tmp->h_sequence); jbd2_debug(3, "Found magic %d, sequence %d\n", blocktype, sequence); if (sequence != next_commit_ID) break; /* OK, we have a valid descriptor block which matches * all of the sequence number checks. What are we going * to do with it? That depends on the pass... */ switch(blocktype) { case JBD2_DESCRIPTOR_BLOCK: /* Verify checksum first */ if (!jbd2_descriptor_block_csum_verify(journal, bh->b_data)) { /* * PASS_SCAN can see stale blocks due to lazy * journal init. Don't error out on those yet. */ if (pass != PASS_SCAN) { pr_err("JBD2: Invalid checksum recovering block %lu in log\n", next_log_block); err = -EFSBADCRC; goto failed; } need_check_commit_time = true; jbd2_debug(1, "invalid descriptor block found in %lu\n", next_log_block); } /* If it is a valid descriptor block, replay it * in pass REPLAY; if journal_checksums enabled, then * calculate checksums in PASS_SCAN, otherwise, * just skip over the blocks it describes. */ if (pass != PASS_REPLAY) { if (pass == PASS_SCAN && jbd2_has_feature_checksum(journal) && !info->end_transaction) { if (calc_chksums(journal, bh, &next_log_block, &crc32_sum)) break; continue; } next_log_block += count_tags(journal, bh); wrap(journal, next_log_block); continue; } /* * A descriptor block: we can now write all of the * data blocks. Yay, useful work is finally getting * done here! */ err = jbd2_do_replay(journal, info, bh, &next_log_block, next_commit_ID); if (err) { if (err == -ENOMEM) goto failed; success = err; } continue; case JBD2_COMMIT_BLOCK: if (pass != PASS_SCAN) { next_commit_ID++; continue; } /* How to differentiate between interrupted commit * and journal corruption ? * * {nth transaction} * Checksum Verification Failed * | * ____________________ * | | * async_commit sync_commit * | | * | GO TO NEXT "Journal Corruption" * | TRANSACTION * | * {(n+1)th transanction} * | * _______|______________ * | | * Commit block found Commit block not found * | | * "Journal Corruption" | * _____________|_________ * | | * nth trans corrupt OR nth trans * and (n+1)th interrupted interrupted * before commit block * could reach the disk. * (Cannot find the difference in above * mentioned conditions. Hence assume * "Interrupted Commit".) */ commit_time = be64_to_cpu( ((struct commit_header *)bh->b_data)->h_commit_sec); /* * If need_check_commit_time is set, it means we are in * PASS_SCAN and csum verify failed before. If * commit_time is increasing, it's the same journal, * otherwise it is stale journal block, just end this * recovery. */ if (need_check_commit_time) { if (commit_time >= last_trans_commit_time) { pr_err("JBD2: Invalid checksum found in transaction %u\n", next_commit_ID); err = -EFSBADCRC; goto failed; } ignore_crc_mismatch: /* * It likely does not belong to same journal, * just end this recovery with success. */ jbd2_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n", next_commit_ID); goto done; } /* * Found an expected commit block: if checksums * are present, verify them in PASS_SCAN; else not * much to do other than move on to the next sequence * number. */ if (jbd2_has_feature_checksum(journal)) { struct commit_header *cbh = (struct commit_header *)bh->b_data; unsigned found_chksum = be32_to_cpu(cbh->h_chksum[0]); if (info->end_transaction) { journal->j_failed_commit = info->end_transaction; break; } /* Neither checksum match nor unused? */ if (!((crc32_sum == found_chksum && cbh->h_chksum_type == JBD2_CRC32_CHKSUM && cbh->h_chksum_size == JBD2_CRC32_CHKSUM_SIZE) || (cbh->h_chksum_type == 0 && cbh->h_chksum_size == 0 && found_chksum == 0))) goto chksum_error; crc32_sum = ~0; goto chksum_ok; } if (jbd2_commit_block_csum_verify(journal, bh->b_data)) goto chksum_ok; if (jbd2_commit_block_csum_verify_partial(journal, bh->b_data)) { pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n", next_commit_ID, next_log_block); goto chksum_ok; } chksum_error: if (commit_time < last_trans_commit_time) goto ignore_crc_mismatch; info->end_transaction = next_commit_ID; info->head_block = head_block; if (!jbd2_has_feature_async_commit(journal)) { journal->j_failed_commit = next_commit_ID; break; } chksum_ok: last_trans_commit_time = commit_time; head_block = next_log_block; next_commit_ID++; continue; case JBD2_REVOKE_BLOCK: /* * If we aren't in the SCAN or REVOKE pass, then we can * just skip over this block. */ if (pass != PASS_REVOKE && pass != PASS_SCAN) continue; /* * Check revoke block crc in pass_scan, if csum verify * failed, check commit block time later. */ if (pass == PASS_SCAN && !jbd2_descriptor_block_csum_verify(journal, bh->b_data)) { jbd2_debug(1, "JBD2: invalid revoke block found in %lu\n", next_log_block); need_check_commit_time = true; } err = scan_revoke_records(journal, pass, bh, next_commit_ID, info); if (err) goto failed; continue; default: jbd2_debug(3, "Unrecognised magic %d, end of scan.\n", blocktype); goto done; } } done: brelse(bh); /* * We broke out of the log scan loop: either we came to the * known end of the log or we found an unexpected block in the * log. If the latter happened, then we know that the "current" * transaction marks the end of the valid log. */ if (pass == PASS_SCAN) { if (!info->end_transaction) info->end_transaction = next_commit_ID; if (!info->head_block) info->head_block = head_block; } else { /* It's really bad news if different passes end up at * different places (but possible due to IO errors). */ if (info->end_transaction != next_commit_ID) { printk(KERN_ERR "JBD2: recovery pass %d ended at " "transaction %u, expected %u\n", pass, next_commit_ID, info->end_transaction); if (!success) success = -EIO; } } if (jbd2_has_feature_fast_commit(journal) && pass != PASS_REVOKE) { err = fc_do_one_pass(journal, info, pass); if (err) success = err; } return success; failed: brelse(bh); return err; } /* Scan a revoke record, marking all blocks mentioned as revoked. */ static int scan_revoke_records(journal_t *journal, enum passtype pass, struct buffer_head *bh, tid_t sequence, struct recovery_info *info) { jbd2_journal_revoke_header_t *header; int offset, max; unsigned csum_size = 0; __u32 rcount; int record_len = 4; header = (jbd2_journal_revoke_header_t *) bh->b_data; offset = sizeof(jbd2_journal_revoke_header_t); rcount = be32_to_cpu(header->r_count); if (jbd2_journal_has_csum_v2or3(journal)) csum_size = sizeof(struct jbd2_journal_block_tail); if (rcount > journal->j_blocksize - csum_size) return -EINVAL; max = rcount; if (jbd2_has_feature_64bit(journal)) record_len = 8; if (pass == PASS_SCAN) { info->nr_revokes += (max - offset) / record_len; return 0; } while (offset + record_len <= max) { unsigned long long blocknr; int err; if (record_len == 4) blocknr = be32_to_cpu(* ((__be32 *) (bh->b_data+offset))); else blocknr = be64_to_cpu(* ((__be64 *) (bh->b_data+offset))); offset += record_len; err = jbd2_journal_set_revoke(journal, blocknr, sequence); if (err) return err; } return 0; } |
| 5 6 7 4 2 1 3 2 2 1 1 8 8 7 1 1 7 1 6 6 7 7 7 17 2 16 4 1 7 1 1 2 3 3 3 1 1 1 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ceph/ceph_debug.h> #include <linux/backing-dev.h> #include <linux/ctype.h> #include <linux/fs.h> #include <linux/inet.h> #include <linux/in6.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/statfs.h> #include <linux/string.h> #include "super.h" #include "mds_client.h" #include "cache.h" #include "crypto.h" #include <linux/ceph/ceph_features.h> #include <linux/ceph/decode.h> #include <linux/ceph/mon_client.h> #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> #include <uapi/linux/magic.h> static DEFINE_SPINLOCK(ceph_fsc_lock); static LIST_HEAD(ceph_fsc_list); /* * Ceph superblock operations * * Handle the basics of mounting, unmounting. */ /* * super ops */ static void ceph_put_super(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s); doutc(fsc->client, "begin\n"); ceph_fscrypt_free_dummy_policy(fsc); ceph_mdsc_close_sessions(fsc->mdsc); doutc(fsc->client, "done\n"); } static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) { struct ceph_fs_client *fsc = ceph_inode_to_fs_client(d_inode(dentry)); struct ceph_mon_client *monc = &fsc->client->monc; struct ceph_statfs st; int i, err; u64 data_pool; doutc(fsc->client, "begin\n"); if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) { data_pool = fsc->mdsc->mdsmap->m_data_pg_pools[0]; } else { data_pool = CEPH_NOPOOL; } err = ceph_monc_do_statfs(monc, data_pool, &st); if (err < 0) return err; /* fill in kstatfs */ buf->f_type = CEPH_SUPER_MAGIC; /* ?? */ /* * Express utilization in terms of large blocks to avoid * overflow on 32-bit machines. */ buf->f_frsize = 1 << CEPH_BLOCK_SHIFT; /* * By default use root quota for stats; fallback to overall filesystem * usage if using 'noquotadf' mount option or if the root dir doesn't * have max_bytes quota set. */ if (ceph_test_mount_opt(fsc, NOQUOTADF) || !ceph_quota_update_statfs(fsc, buf)) { buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10); buf->f_bfree = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10); buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10); } /* * NOTE: for the time being, we make bsize == frsize to humor * not-yet-ancient versions of glibc that are broken. * Someday, we will probably want to report a real block * size... whatever that may mean for a network file system! */ buf->f_bsize = buf->f_frsize; buf->f_files = le64_to_cpu(st.num_objects); buf->f_ffree = -1; buf->f_namelen = NAME_MAX; /* Must convert the fsid, for consistent values across arches */ buf->f_fsid.val[0] = 0; mutex_lock(&monc->mutex); for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i) buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]); mutex_unlock(&monc->mutex); /* fold the fs_cluster_id into the upper bits */ buf->f_fsid.val[1] = monc->fs_cluster_id; doutc(fsc->client, "done\n"); return 0; } static int ceph_sync_fs(struct super_block *sb, int wait) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; if (!wait) { doutc(cl, "(non-blocking)\n"); ceph_flush_dirty_caps(fsc->mdsc); ceph_flush_cap_releases(fsc->mdsc); doutc(cl, "(non-blocking) done\n"); return 0; } doutc(cl, "(blocking)\n"); ceph_osdc_sync(&fsc->client->osdc); ceph_mdsc_sync(fsc->mdsc); doutc(cl, "(blocking) done\n"); return 0; } /* * mount options */ enum { Opt_wsize, Opt_rsize, Opt_rasize, Opt_caps_wanted_delay_min, Opt_caps_wanted_delay_max, Opt_caps_max, Opt_readdir_max_entries, Opt_readdir_max_bytes, Opt_congestion_kb, /* int args above */ Opt_snapdirname, Opt_mds_namespace, Opt_recover_session, Opt_source, Opt_mon_addr, Opt_test_dummy_encryption, /* string args above */ Opt_dirstat, Opt_rbytes, Opt_asyncreaddir, Opt_dcache, Opt_ino32, Opt_fscache, Opt_poolperm, Opt_require_active_mds, Opt_acl, Opt_quotadf, Opt_copyfrom, Opt_wsync, Opt_pagecache, Opt_sparseread, }; enum ceph_recover_session_mode { ceph_recover_session_no, ceph_recover_session_clean }; static const struct constant_table ceph_param_recover[] = { { "no", ceph_recover_session_no }, { "clean", ceph_recover_session_clean }, {} }; static const struct fs_parameter_spec ceph_mount_parameters[] = { fsparam_flag_no ("acl", Opt_acl), fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir), fsparam_s32 ("caps_max", Opt_caps_max), fsparam_u32 ("caps_wanted_delay_max", Opt_caps_wanted_delay_max), fsparam_u32 ("caps_wanted_delay_min", Opt_caps_wanted_delay_min), fsparam_u32 ("write_congestion_kb", Opt_congestion_kb), fsparam_flag_no ("copyfrom", Opt_copyfrom), fsparam_flag_no ("dcache", Opt_dcache), fsparam_flag_no ("dirstat", Opt_dirstat), fsparam_flag_no ("fsc", Opt_fscache), // fsc|nofsc fsparam_string ("fsc", Opt_fscache), // fsc=... fsparam_flag_no ("ino32", Opt_ino32), fsparam_string ("mds_namespace", Opt_mds_namespace), fsparam_string ("mon_addr", Opt_mon_addr), fsparam_flag_no ("poolperm", Opt_poolperm), fsparam_flag_no ("quotadf", Opt_quotadf), fsparam_u32 ("rasize", Opt_rasize), fsparam_flag_no ("rbytes", Opt_rbytes), fsparam_u32 ("readdir_max_bytes", Opt_readdir_max_bytes), fsparam_u32 ("readdir_max_entries", Opt_readdir_max_entries), fsparam_enum ("recover_session", Opt_recover_session, ceph_param_recover), fsparam_flag_no ("require_active_mds", Opt_require_active_mds), fsparam_u32 ("rsize", Opt_rsize), fsparam_string ("snapdirname", Opt_snapdirname), fsparam_string ("source", Opt_source), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_u32 ("wsize", Opt_wsize), fsparam_flag_no ("wsync", Opt_wsync), fsparam_flag_no ("pagecache", Opt_pagecache), fsparam_flag_no ("sparseread", Opt_sparseread), {} }; struct ceph_parse_opts_ctx { struct ceph_options *copts; struct ceph_mount_options *opts; }; /* * Remove adjacent slashes and then the trailing slash, unless it is * the only remaining character. * * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/". */ static void canonicalize_path(char *path) { int i, j = 0; for (i = 0; path[i] != '\0'; i++) { if (path[i] != '/' || j < 1 || path[j - 1] != '/') path[j++] = path[i]; } if (j > 1 && path[j - 1] == '/') j--; path[j] = '\0'; } static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { int r; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; if (*dev_name_end != ':') return invalfc(fc, "separator ':' missing in source"); r = ceph_parse_mon_ips(dev_name, dev_name_end - dev_name, pctx->copts, fc->log.log, ','); if (r) return r; fsopt->new_dev_syntax = false; return 0; } static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { size_t len; struct ceph_fsid fsid; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_options *opts = pctx->copts; struct ceph_mount_options *fsopt = pctx->opts; const char *name_start = dev_name; const char *fsid_start, *fs_name_start; if (*dev_name_end != '=') { dout("separator '=' missing in source"); return -EINVAL; } fsid_start = strchr(dev_name, '@'); if (!fsid_start) return invalfc(fc, "missing cluster fsid"); len = fsid_start - name_start; kfree(opts->name); opts->name = kstrndup(name_start, len, GFP_KERNEL); if (!opts->name) return -ENOMEM; dout("using %s entity name", opts->name); ++fsid_start; /* start of cluster fsid */ fs_name_start = strchr(fsid_start, '.'); if (!fs_name_start) return invalfc(fc, "missing file system name"); if (ceph_parse_fsid(fsid_start, &fsid)) return invalfc(fc, "Invalid FSID"); ++fs_name_start; /* start of file system name */ len = dev_name_end - fs_name_start; if (!namespace_equals(fsopt, fs_name_start, len)) return invalfc(fc, "Mismatching mds_namespace"); kfree(fsopt->mds_namespace); fsopt->mds_namespace = kstrndup(fs_name_start, len, GFP_KERNEL); if (!fsopt->mds_namespace) return -ENOMEM; dout("file system (mds namespace) '%s'\n", fsopt->mds_namespace); fsopt->new_dev_syntax = true; return 0; } /* * Parse the source parameter for new device format. Distinguish the device * spec from the path. Try parsing new device format and fallback to old * format if needed. * * New device syntax will looks like: * <device_spec>=/<path> * where * <device_spec> is name@fsid.fsname * <path> is optional, but if present must begin with '/' * (monitor addresses are passed via mount option) * * Old device syntax is: * <server_spec>[,<server_spec>...]:[<path>] * where * <server_spec> is <ip>[:<port>] * <path> is optional, but if present must begin with '/' */ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; char *dev_name = param->string, *dev_name_end; int ret; dout("'%s'\n", dev_name); if (!dev_name || !*dev_name) return invalfc(fc, "Empty source"); dev_name_end = strchr(dev_name, '/'); if (dev_name_end) { /* * The server_path will include the whole chars from userland * including the leading '/'. */ kfree(fsopt->server_path); fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); if (!fsopt->server_path) return -ENOMEM; canonicalize_path(fsopt->server_path); } else { dev_name_end = dev_name + strlen(dev_name); } dev_name_end--; /* back up to separator */ if (dev_name_end < dev_name) return invalfc(fc, "Path missing in source"); dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); if (fsopt->server_path) dout("server path '%s'\n", fsopt->server_path); dout("trying new device syntax"); ret = ceph_parse_new_source(dev_name, dev_name_end, fc); if (ret) { if (ret != -EINVAL) return ret; dout("trying old device syntax"); ret = ceph_parse_old_source(dev_name, dev_name_end, fc); if (ret) return ret; } fc->source = param->string; param->string = NULL; return 0; } static int ceph_parse_mon_addr(struct fs_parameter *param, struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; kfree(fsopt->mon_addr); fsopt->mon_addr = param->string; param->string = NULL; return ceph_parse_mon_ips(fsopt->mon_addr, strlen(fsopt->mon_addr), pctx->copts, fc->log.log, '/'); } static int ceph_parse_mount_param(struct fs_context *fc, struct fs_parameter *param) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct fs_parse_result result; unsigned int mode; int token, ret; ret = ceph_parse_param(param, pctx->copts, fc->log.log); if (ret != -ENOPARAM) return ret; token = fs_parse(fc, ceph_mount_parameters, param, &result); dout("%s: fs_parse '%s' token %d\n",__func__, param->key, token); if (token < 0) return token; switch (token) { case Opt_snapdirname: if (strlen(param->string) > NAME_MAX) return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; break; case Opt_mds_namespace: if (!namespace_equals(fsopt, param->string, strlen(param->string))) return invalfc(fc, "Mismatching mds_namespace"); kfree(fsopt->mds_namespace); fsopt->mds_namespace = param->string; param->string = NULL; break; case Opt_recover_session: mode = result.uint_32; if (mode == ceph_recover_session_no) fsopt->flags &= ~CEPH_MOUNT_OPT_CLEANRECOVER; else if (mode == ceph_recover_session_clean) fsopt->flags |= CEPH_MOUNT_OPT_CLEANRECOVER; else BUG(); break; case Opt_source: if (fc->source) return invalfc(fc, "Multiple sources specified"); return ceph_parse_source(param, fc); case Opt_mon_addr: return ceph_parse_mon_addr(param, fc); case Opt_wsize: if (result.uint_32 < PAGE_SIZE || result.uint_32 > CEPH_MAX_WRITE_SIZE) goto out_of_range; fsopt->wsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rsize: if (result.uint_32 < PAGE_SIZE || result.uint_32 > CEPH_MAX_READ_SIZE) goto out_of_range; fsopt->rsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rasize: fsopt->rasize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_caps_wanted_delay_min: if (result.uint_32 < 1) goto out_of_range; fsopt->caps_wanted_delay_min = result.uint_32; break; case Opt_caps_wanted_delay_max: if (result.uint_32 < 1) goto out_of_range; fsopt->caps_wanted_delay_max = result.uint_32; break; case Opt_caps_max: if (result.int_32 < 0) goto out_of_range; fsopt->caps_max = result.int_32; break; case Opt_readdir_max_entries: if (result.uint_32 < 1) goto out_of_range; fsopt->max_readdir = result.uint_32; break; case Opt_readdir_max_bytes: if (result.uint_32 < PAGE_SIZE && result.uint_32 != 0) goto out_of_range; fsopt->max_readdir_bytes = result.uint_32; break; case Opt_congestion_kb: if (result.uint_32 < 1024) /* at least 1M */ goto out_of_range; fsopt->congestion_kb = result.uint_32; break; case Opt_dirstat: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; else fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; break; case Opt_rbytes: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; else fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; break; case Opt_asyncreaddir: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; else fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; break; case Opt_dcache: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; else fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; break; case Opt_ino32: if (!result.negated) fsopt->flags |= CEPH_MOUNT_OPT_INO32; else fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; case Opt_fscache: #ifdef CONFIG_CEPH_FSCACHE kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; if (result.negated) { fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; } else { fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; fsopt->fscache_uniq = param->string; param->string = NULL; } break; #else return invalfc(fc, "fscache support is disabled"); #endif case Opt_poolperm: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; else fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; break; case Opt_require_active_mds: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; else fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; break; case Opt_quotadf: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; else fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; break; case Opt_copyfrom: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; else fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; break; case Opt_acl: if (!result.negated) { #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #else return invalfc(fc, "POSIX ACL support is disabled"); #endif } else { fc->sb_flags &= ~SB_POSIXACL; } break; case Opt_wsync: if (!result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_ASYNC_DIROPS; else fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS; break; case Opt_pagecache: if (result.negated) fsopt->flags |= CEPH_MOUNT_OPT_NOPAGECACHE; else fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE; break; case Opt_sparseread: if (result.negated) fsopt->flags &= ~CEPH_MOUNT_OPT_SPARSEREAD; else fsopt->flags |= CEPH_MOUNT_OPT_SPARSEREAD; break; case Opt_test_dummy_encryption: #ifdef CONFIG_FS_ENCRYPTION fscrypt_free_dummy_policy(&fsopt->dummy_enc_policy); ret = fscrypt_parse_test_dummy_encryption(param, &fsopt->dummy_enc_policy); if (ret == -EINVAL) { warnfc(fc, "Value of option \"%s\" is unrecognized", param->key); } else if (ret == -EEXIST) { warnfc(fc, "Conflicting test_dummy_encryption options"); ret = -EINVAL; } #else warnfc(fc, "FS encryption not supported: test_dummy_encryption mount option ignored"); #endif break; default: BUG(); } return 0; out_of_range: return invalfc(fc, "%s out of range", param->key); } static void destroy_mount_options(struct ceph_mount_options *args) { dout("destroy_mount_options %p\n", args); if (!args) return; kfree(args->snapdir_name); kfree(args->mds_namespace); kfree(args->server_path); kfree(args->fscache_uniq); kfree(args->mon_addr); fscrypt_free_dummy_policy(&args->dummy_enc_policy); kfree(args); } static int strcmp_null(const char *s1, const char *s2) { if (!s1 && !s2) return 0; if (s1 && !s2) return -1; if (!s1 && s2) return 1; return strcmp(s1, s2); } static int compare_mount_options(struct ceph_mount_options *new_fsopt, struct ceph_options *new_opt, struct ceph_fs_client *fsc) { struct ceph_mount_options *fsopt1 = new_fsopt; struct ceph_mount_options *fsopt2 = fsc->mount_options; int ofs = offsetof(struct ceph_mount_options, snapdir_name); int ret; ret = memcmp(fsopt1, fsopt2, ofs); if (ret) return ret; ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name); if (ret) return ret; ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; ret = strcmp_null(fsopt1->server_path, fsopt2->server_path); if (ret) return ret; ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq); if (ret) return ret; ret = strcmp_null(fsopt1->mon_addr, fsopt2->mon_addr); if (ret) return ret; return ceph_compare_options(new_opt, fsc->client); } /** * ceph_show_options - Show mount options in /proc/mounts * @m: seq_file to write to * @root: root of that (sub)tree */ static int ceph_show_options(struct seq_file *m, struct dentry *root) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(root->d_sb); struct ceph_mount_options *fsopt = fsc->mount_options; size_t pos; int ret; /* a comma between MNT/MS and client options */ seq_putc(m, ','); pos = m->count; ret = ceph_print_client_options(m, fsc->client, false); if (ret) return ret; /* retract our comma if no client options */ if (m->count == pos) m->count--; if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT) seq_puts(m, ",dirstat"); if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES)) seq_puts(m, ",rbytes"); if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR) seq_puts(m, ",noasyncreaddir"); if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0) seq_puts(m, ",nodcache"); if (fsopt->flags & CEPH_MOUNT_OPT_INO32) seq_puts(m, ",ino32"); if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) { seq_show_option(m, "fsc", fsopt->fscache_uniq); } if (fsopt->flags & CEPH_MOUNT_OPT_NOPOOLPERM) seq_puts(m, ",nopoolperm"); if (fsopt->flags & CEPH_MOUNT_OPT_NOQUOTADF) seq_puts(m, ",noquotadf"); #ifdef CONFIG_CEPH_FS_POSIX_ACL if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); else seq_puts(m, ",noacl"); #endif if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0) seq_puts(m, ",copyfrom"); /* dump mds_namespace when old device syntax is in use */ if (fsopt->mds_namespace && !fsopt->new_dev_syntax) seq_show_option(m, "mds_namespace", fsopt->mds_namespace); if (fsopt->mon_addr) seq_printf(m, ",mon_addr=%s", fsopt->mon_addr); if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER) seq_show_option(m, "recover_session", "clean"); if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)) seq_puts(m, ",wsync"); if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE) seq_puts(m, ",nopagecache"); if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD) seq_puts(m, ",sparseread"); fscrypt_show_test_dummy_encryption(m, ',', root->d_sb); if (fsopt->wsize != CEPH_MAX_WRITE_SIZE) seq_printf(m, ",wsize=%u", fsopt->wsize); if (fsopt->rsize != CEPH_MAX_READ_SIZE) seq_printf(m, ",rsize=%u", fsopt->rsize); if (fsopt->rasize != CEPH_RASIZE_DEFAULT) seq_printf(m, ",rasize=%u", fsopt->rasize); if (fsopt->congestion_kb != default_congestion_kb()) seq_printf(m, ",write_congestion_kb=%u", fsopt->congestion_kb); if (fsopt->caps_max) seq_printf(m, ",caps_max=%d", fsopt->caps_max); if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT) seq_printf(m, ",caps_wanted_delay_min=%u", fsopt->caps_wanted_delay_min); if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT) seq_printf(m, ",caps_wanted_delay_max=%u", fsopt->caps_wanted_delay_max); if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT) seq_printf(m, ",readdir_max_entries=%u", fsopt->max_readdir); if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT) seq_printf(m, ",readdir_max_bytes=%u", fsopt->max_readdir_bytes); if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT)) seq_show_option(m, "snapdirname", fsopt->snapdir_name); return 0; } /* * handle any mon messages the standard library doesn't understand. * return error if we don't either. */ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) { struct ceph_fs_client *fsc = client->private; int type = le16_to_cpu(msg->hdr.type); switch (type) { case CEPH_MSG_MDS_MAP: ceph_mdsc_handle_mdsmap(fsc->mdsc, msg); return 0; case CEPH_MSG_FS_MAP_USER: ceph_mdsc_handle_fsmap(fsc->mdsc, msg); return 0; default: return -1; } } /* * create a new fs client * * Success or not, this function consumes @fsopt and @opt. */ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) { struct ceph_fs_client *fsc; int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); if (!fsc) { err = -ENOMEM; goto fail; } fsc->client = ceph_create_client(opt, fsc); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; ceph_set_opt(fsc->client, ABORT_ON_FULL); if (!fsopt->mds_namespace) { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true); } else { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_FSMAP, 0, false); } fsc->mount_options = fsopt; fsc->sb = NULL; fsc->mount_state = CEPH_MOUNT_MOUNTING; fsc->filp_gen = 1; fsc->have_copy_from2 = true; atomic_long_set(&fsc->writeback_count, 0); fsc->write_congested = false; err = -ENOMEM; /* * The number of concurrent works can be high but they don't need * to be processed in parallel, limit concurrency. */ fsc->inode_wq = alloc_workqueue("ceph-inode", WQ_UNBOUND, 0); if (!fsc->inode_wq) goto fail_client; fsc->cap_wq = alloc_workqueue("ceph-cap", WQ_PERCPU, 1); if (!fsc->cap_wq) goto fail_inode_wq; hash_init(fsc->async_unlink_conflict); spin_lock_init(&fsc->async_unlink_conflict_lock); spin_lock(&ceph_fsc_lock); list_add_tail(&fsc->metric_wakeup, &ceph_fsc_list); spin_unlock(&ceph_fsc_lock); return fsc; fail_inode_wq: destroy_workqueue(fsc->inode_wq); fail_client: ceph_destroy_client(fsc->client); fail: kfree(fsc); if (opt) ceph_destroy_options(opt); destroy_mount_options(fsopt); return ERR_PTR(err); } static void flush_fs_workqueues(struct ceph_fs_client *fsc) { flush_workqueue(fsc->inode_wq); flush_workqueue(fsc->cap_wq); } static void destroy_fs_client(struct ceph_fs_client *fsc) { doutc(fsc->client, "%p\n", fsc); spin_lock(&ceph_fsc_lock); list_del(&fsc->metric_wakeup); spin_unlock(&ceph_fsc_lock); ceph_mdsc_destroy(fsc); destroy_workqueue(fsc->inode_wq); destroy_workqueue(fsc->cap_wq); destroy_mount_options(fsc->mount_options); ceph_destroy_client(fsc->client); kfree(fsc); dout("%s: %p done\n", __func__, fsc); } /* * caches */ struct kmem_cache *ceph_inode_cachep; struct kmem_cache *ceph_cap_cachep; struct kmem_cache *ceph_cap_snap_cachep; struct kmem_cache *ceph_cap_flush_cachep; struct kmem_cache *ceph_dentry_cachep; struct kmem_cache *ceph_file_cachep; struct kmem_cache *ceph_dir_file_cachep; struct kmem_cache *ceph_mds_request_cachep; mempool_t *ceph_wb_pagevec_pool; static void ceph_inode_init_once(void *foo) { struct ceph_inode_info *ci = foo; inode_init_once(&ci->netfs.inode); } static int __init init_caches(void) { int error = -ENOMEM; ceph_inode_cachep = kmem_cache_create("ceph_inode_info", sizeof(struct ceph_inode_info), __alignof__(struct ceph_inode_info), SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, ceph_inode_init_once); if (!ceph_inode_cachep) return -ENOMEM; ceph_cap_cachep = KMEM_CACHE(ceph_cap, 0); if (!ceph_cap_cachep) goto bad_cap; ceph_cap_snap_cachep = KMEM_CACHE(ceph_cap_snap, 0); if (!ceph_cap_snap_cachep) goto bad_cap_snap; ceph_cap_flush_cachep = KMEM_CACHE(ceph_cap_flush, SLAB_RECLAIM_ACCOUNT); if (!ceph_cap_flush_cachep) goto bad_cap_flush; ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info, SLAB_RECLAIM_ACCOUNT); if (!ceph_dentry_cachep) goto bad_dentry; ceph_file_cachep = KMEM_CACHE(ceph_file_info, 0); if (!ceph_file_cachep) goto bad_file; ceph_dir_file_cachep = KMEM_CACHE(ceph_dir_file_info, 0); if (!ceph_dir_file_cachep) goto bad_dir_file; ceph_mds_request_cachep = KMEM_CACHE(ceph_mds_request, 0); if (!ceph_mds_request_cachep) goto bad_mds_req; ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *)); if (!ceph_wb_pagevec_pool) goto bad_pagevec_pool; return 0; bad_pagevec_pool: kmem_cache_destroy(ceph_mds_request_cachep); bad_mds_req: kmem_cache_destroy(ceph_dir_file_cachep); bad_dir_file: kmem_cache_destroy(ceph_file_cachep); bad_file: kmem_cache_destroy(ceph_dentry_cachep); bad_dentry: kmem_cache_destroy(ceph_cap_flush_cachep); bad_cap_flush: kmem_cache_destroy(ceph_cap_snap_cachep); bad_cap_snap: kmem_cache_destroy(ceph_cap_cachep); bad_cap: kmem_cache_destroy(ceph_inode_cachep); return error; } static void destroy_caches(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ceph_inode_cachep); kmem_cache_destroy(ceph_cap_cachep); kmem_cache_destroy(ceph_cap_snap_cachep); kmem_cache_destroy(ceph_cap_flush_cachep); kmem_cache_destroy(ceph_dentry_cachep); kmem_cache_destroy(ceph_file_cachep); kmem_cache_destroy(ceph_dir_file_cachep); kmem_cache_destroy(ceph_mds_request_cachep); mempool_destroy(ceph_wb_pagevec_pool); } static void __ceph_umount_begin(struct ceph_fs_client *fsc) { ceph_osdc_abort_requests(&fsc->client->osdc, -EIO); ceph_mdsc_force_umount(fsc->mdsc); fsc->filp_gen++; // invalidate open files } /* * ceph_umount_begin - initiate forced umount. Tear down the * mount, skipping steps that may hang while waiting for server(s). */ void ceph_umount_begin(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); doutc(fsc->client, "starting forced umount\n"); fsc->mount_state = CEPH_MOUNT_SHUTDOWN; __ceph_umount_begin(fsc); } static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .free_inode = ceph_free_inode, .write_inode = ceph_write_inode, .drop_inode = inode_just_drop, .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, }; /* * Bootstrap mount by opening the root directory. Note the mount * @started time from caller, and time out if this takes too long. */ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc, const char *path, unsigned long started) { struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req = NULL; int err; struct dentry *root; /* open dir */ doutc(cl, "opening '%s'\n", path); req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS); if (IS_ERR(req)) return ERR_CAST(req); req->r_path1 = kstrdup(path, GFP_NOFS); if (!req->r_path1) { root = ERR_PTR(-ENOMEM); goto out; } req->r_ino1.ino = CEPH_INO_ROOT; req->r_ino1.snap = CEPH_NOSNAP; req->r_started = started; req->r_timeout = fsc->client->options->mount_timeout; req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE); req->r_num_caps = 2; err = ceph_mdsc_do_request(mdsc, NULL, req); if (err == 0) { struct inode *inode = req->r_target_inode; req->r_target_inode = NULL; doutc(cl, "success\n"); root = d_make_root(inode); if (!root) { root = ERR_PTR(-ENOMEM); goto out; } doutc(cl, "success, root dentry is %p\n", root); } else { root = ERR_PTR(err); } out: ceph_mdsc_put_request(req); return root; } #ifdef CONFIG_FS_ENCRYPTION static int ceph_apply_test_dummy_encryption(struct super_block *sb, struct fs_context *fc, struct ceph_mount_options *fsopt) { struct ceph_fs_client *fsc = sb->s_fs_info; if (!fscrypt_is_dummy_policy_set(&fsopt->dummy_enc_policy)) return 0; /* No changing encryption context on remount. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE && !fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy, &fsc->fsc_dummy_enc_policy)) return 0; errorfc(fc, "Can't set test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure fsopt doesn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&fsc->fsc_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&fsopt->dummy_enc_policy, &fsc->fsc_dummy_enc_policy)) return 0; errorfc(fc, "Conflicting test_dummy_encryption options"); return -EINVAL; } fsc->fsc_dummy_enc_policy = fsopt->dummy_enc_policy; memset(&fsopt->dummy_enc_policy, 0, sizeof(fsopt->dummy_enc_policy)); warnfc(fc, "test_dummy_encryption mode enabled"); return 0; } #else static int ceph_apply_test_dummy_encryption(struct super_block *sb, struct fs_context *fc, struct ceph_mount_options *fsopt) { return 0; } #endif /* * mount: join the ceph cluster, and open root directory. */ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, struct fs_context *fc) { struct ceph_client *cl = fsc->client; int err; unsigned long started = jiffies; /* note the start time */ struct dentry *root; doutc(cl, "mount start %p\n", fsc); mutex_lock(&fsc->client->mount_mutex); if (!fsc->sb->s_root) { const char *path = fsc->mount_options->server_path ? fsc->mount_options->server_path + 1 : ""; err = __ceph_open_session(fsc->client); if (err < 0) goto out; /* setup fscache */ if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) { err = ceph_fscache_register_fs(fsc, fc); if (err < 0) goto out; } err = ceph_apply_test_dummy_encryption(fsc->sb, fc, fsc->mount_options); if (err) goto out; doutc(cl, "mount opening path '%s'\n", path); ceph_fs_debugfs_init(fsc); root = open_root_dentry(fsc, path, started); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; } fsc->sb->s_root = dget(root); } else { root = dget(fsc->sb->s_root); } fsc->mount_state = CEPH_MOUNT_MOUNTED; doutc(cl, "mount success\n"); mutex_unlock(&fsc->client->mount_mutex); return root; out: mutex_unlock(&fsc->client->mount_mutex); ceph_fscrypt_free_dummy_policy(fsc); return ERR_PTR(err); } static int ceph_set_super(struct super_block *s, struct fs_context *fc) { struct ceph_fs_client *fsc = s->s_fs_info; struct ceph_client *cl = fsc->client; int ret; doutc(cl, "%p\n", s); s->s_maxbytes = MAX_LFS_FILESIZE; s->s_xattr = ceph_xattr_handlers; fsc->sb = s; fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */ s->s_op = &ceph_super_ops; set_default_d_op(s, &ceph_dentry_ops); s->s_export_op = &ceph_export_ops; s->s_time_gran = 1; s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_flags |= SB_NODIRATIME | SB_NOATIME; s->s_magic = CEPH_SUPER_MAGIC; ceph_fscrypt_set_ops(s); ret = set_anon_super_fc(s, fc); if (ret != 0) fsc->sb = NULL; return ret; } /* * share superblock if same fs AND options */ static int ceph_compare_super(struct super_block *sb, struct fs_context *fc) { struct ceph_fs_client *new = fc->s_fs_info; struct ceph_mount_options *fsopt = new->mount_options; struct ceph_options *opt = new->client->options; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; doutc(cl, "%p\n", sb); if (compare_mount_options(fsopt, opt, fsc)) { doutc(cl, "monitor(s)/mount options don't match\n"); return 0; } if ((opt->flags & CEPH_OPT_FSID) && ceph_fsid_compare(&opt->fsid, &fsc->client->fsid)) { doutc(cl, "fsid doesn't match\n"); return 0; } if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) { doutc(cl, "flags differ\n"); return 0; } if (fsc->blocklisted && !ceph_test_mount_opt(fsc, CLEANRECOVER)) { doutc(cl, "client is blocklisted (and CLEANRECOVER is not set)\n"); return 0; } if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) { doutc(cl, "client has been forcibly unmounted\n"); return 0; } return 1; } /* * construct our own bdi so we can control readahead, etc. */ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) { int err; err = super_setup_bdi_name(sb, "ceph-%ld", atomic_long_inc_return(&bdi_seq)); if (err) return err; /* set ra_pages based on rasize mount option? */ sb->s_bdi->ra_pages = fsc->mount_options->rasize >> PAGE_SHIFT; /* set io_pages based on max osd read size */ sb->s_bdi->io_pages = fsc->mount_options->rsize >> PAGE_SHIFT; return 0; } static int ceph_get_tree(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct super_block *sb; struct ceph_fs_client *fsc; struct dentry *res; int (*compare_super)(struct super_block *, struct fs_context *) = ceph_compare_super; int err; dout("ceph_get_tree\n"); if (!fc->source) return invalfc(fc, "No source"); if (fsopt->new_dev_syntax && !fsopt->mon_addr) return invalfc(fc, "No monitor address"); /* create client (which we may/may not use) */ fsc = create_fs_client(pctx->opts, pctx->copts); pctx->opts = NULL; pctx->copts = NULL; if (IS_ERR(fsc)) { err = PTR_ERR(fsc); goto out_final; } err = ceph_mdsc_init(fsc); if (err < 0) goto out; if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; fc->s_fs_info = fsc; sb = sget_fc(fc, compare_super, ceph_set_super); fc->s_fs_info = NULL; if (IS_ERR(sb)) { err = PTR_ERR(sb); goto out; } if (ceph_sb_to_fs_client(sb) != fsc) { destroy_fs_client(fsc); fsc = ceph_sb_to_fs_client(sb); dout("get_sb got existing client %p\n", fsc); } else { dout("get_sb using new client %p\n", fsc); err = ceph_setup_bdi(sb, fsc); if (err < 0) goto out_splat; } res = ceph_real_mount(fsc, fc); if (IS_ERR(res)) { err = PTR_ERR(res); goto out_splat; } doutc(fsc->client, "root %p inode %p ino %llx.%llx\n", res, d_inode(res), ceph_vinop(d_inode(res))); fc->root = fsc->sb->s_root; return 0; out_splat: if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) { pr_info("No mds server is up or the cluster is laggy\n"); err = -EHOSTUNREACH; } ceph_mdsc_close_sessions(fsc->mdsc); deactivate_locked_super(sb); goto out_final; out: destroy_fs_client(fsc); out_final: dout("ceph_get_tree fail %d\n", err); return err; } static void ceph_free_fc(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx = fc->fs_private; if (pctx) { destroy_mount_options(pctx->opts); ceph_destroy_options(pctx->copts); kfree(pctx); } } static int ceph_reconfigure_fc(struct fs_context *fc) { int err; struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct ceph_mount_options *fsopt = pctx->opts; struct super_block *sb = fc->root->d_sb; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); err = ceph_apply_test_dummy_encryption(sb, fc, fsopt); if (err) return err; if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS) ceph_set_mount_opt(fsc, ASYNC_DIROPS); else ceph_clear_mount_opt(fsc, ASYNC_DIROPS); if (fsopt->flags & CEPH_MOUNT_OPT_SPARSEREAD) ceph_set_mount_opt(fsc, SPARSEREAD); else ceph_clear_mount_opt(fsc, SPARSEREAD); if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) { kfree(fsc->mount_options->mon_addr); fsc->mount_options->mon_addr = fsopt->mon_addr; fsopt->mon_addr = NULL; pr_notice_client(fsc->client, "monitor addresses recorded, but not used for reconnection"); } sync_filesystem(sb); return 0; } static const struct fs_context_operations ceph_context_ops = { .free = ceph_free_fc, .parse_param = ceph_parse_mount_param, .get_tree = ceph_get_tree, .reconfigure = ceph_reconfigure_fc, }; /* * Set up the filesystem mount context. */ static int ceph_init_fs_context(struct fs_context *fc) { struct ceph_parse_opts_ctx *pctx; struct ceph_mount_options *fsopt; pctx = kzalloc(sizeof(*pctx), GFP_KERNEL); if (!pctx) return -ENOMEM; pctx->copts = ceph_alloc_options(); if (!pctx->copts) goto nomem; pctx->opts = kzalloc(sizeof(*pctx->opts), GFP_KERNEL); if (!pctx->opts) goto nomem; fsopt = pctx->opts; fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; fsopt->wsize = CEPH_MAX_WRITE_SIZE; fsopt->rsize = CEPH_MAX_READ_SIZE; fsopt->rasize = CEPH_RASIZE_DEFAULT; fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); if (!fsopt->snapdir_name) goto nomem; fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; fsopt->congestion_kb = default_congestion_kb(); #ifdef CONFIG_CEPH_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #endif fc->fs_private = pctx; fc->ops = &ceph_context_ops; return 0; nomem: destroy_mount_options(pctx->opts); ceph_destroy_options(pctx->copts); kfree(pctx); return -ENOMEM; } /* * Return true if it successfully increases the blocker counter, * or false if the mdsc is in stopping and flushed state. */ static bool __inc_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); if (mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) { spin_unlock(&mdsc->stopping_lock); return false; } atomic_inc(&mdsc->stopping_blockers); spin_unlock(&mdsc->stopping_lock); return true; } static void __dec_stopping_blocker(struct ceph_mds_client *mdsc) { spin_lock(&mdsc->stopping_lock); if (!atomic_dec_return(&mdsc->stopping_blockers) && mdsc->stopping >= CEPH_MDSC_STOPPING_FLUSHING) complete_all(&mdsc->stopping_waiter); spin_unlock(&mdsc->stopping_lock); } /* For metadata IO requests */ bool ceph_inc_mds_stopping_blocker(struct ceph_mds_client *mdsc, struct ceph_mds_session *session) { mutex_lock(&session->s_mutex); inc_session_sequence(session); mutex_unlock(&session->s_mutex); return __inc_stopping_blocker(mdsc); } void ceph_dec_mds_stopping_blocker(struct ceph_mds_client *mdsc) { __dec_stopping_blocker(mdsc); } /* For data IO requests */ bool ceph_inc_osd_stopping_blocker(struct ceph_mds_client *mdsc) { return __inc_stopping_blocker(mdsc); } void ceph_dec_osd_stopping_blocker(struct ceph_mds_client *mdsc) { __dec_stopping_blocker(mdsc); } static void ceph_kill_sb(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(s); struct ceph_client *cl = fsc->client; struct ceph_mds_client *mdsc = fsc->mdsc; bool wait; doutc(cl, "%p\n", s); ceph_mdsc_pre_umount(mdsc); flush_fs_workqueues(fsc); /* * Though the kill_anon_super() will finally trigger the * sync_filesystem() anyway, we still need to do it here and * then bump the stage of shutdown. This will allow us to * drop any further message, which will increase the inodes' * i_count reference counters but makes no sense any more, * from MDSs. * * Without this when evicting the inodes it may fail in the * kill_anon_super(), which will trigger a warning when * destroying the fscrypt keyring and then possibly trigger * a further crash in ceph module when the iput() tries to * evict the inodes later. */ sync_filesystem(s); if (atomic64_read(&mdsc->dirty_folios) > 0) { wait_queue_head_t *wq = &mdsc->flush_end_wq; long timeleft = wait_event_killable_timeout(*wq, atomic64_read(&mdsc->dirty_folios) <= 0, fsc->client->options->mount_timeout); if (!timeleft) /* timed out */ pr_warn_client(cl, "umount timed out, %ld\n", timeleft); else if (timeleft < 0) /* killed */ pr_warn_client(cl, "umount was killed, %ld\n", timeleft); } spin_lock(&mdsc->stopping_lock); mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHING; wait = !!atomic_read(&mdsc->stopping_blockers); spin_unlock(&mdsc->stopping_lock); if (wait && atomic_read(&mdsc->stopping_blockers)) { long timeleft = wait_for_completion_killable_timeout( &mdsc->stopping_waiter, fsc->client->options->mount_timeout); if (!timeleft) /* timed out */ pr_warn_client(cl, "umount timed out, %ld\n", timeleft); else if (timeleft < 0) /* killed */ pr_warn_client(cl, "umount was killed, %ld\n", timeleft); } mdsc->stopping = CEPH_MDSC_STOPPING_FLUSHED; kill_anon_super(s); fsc->client->extra_mon_dispatch = NULL; ceph_fs_debugfs_cleanup(fsc); ceph_fscache_unregister_fs(fsc); destroy_fs_client(fsc); } static struct file_system_type ceph_fs_type = { .owner = THIS_MODULE, .name = "ceph", .init_fs_context = ceph_init_fs_context, .kill_sb = ceph_kill_sb, .fs_flags = FS_RENAME_DOES_D_MOVE | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("ceph"); int ceph_force_reconnect(struct super_block *sb) { struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); int err = 0; fsc->mount_state = CEPH_MOUNT_RECOVER; __ceph_umount_begin(fsc); /* Make sure all page caches get invalidated. * see remove_session_caps_cb() */ flush_workqueue(fsc->inode_wq); /* In case that we were blocklisted. This also reset * all mon/osd connections */ ceph_reset_client_addr(fsc->client); ceph_osdc_clear_abort_err(&fsc->client->osdc); fsc->blocklisted = false; fsc->mount_state = CEPH_MOUNT_MOUNTED; if (sb->s_root) { err = __ceph_do_getattr(d_inode(sb->s_root), NULL, CEPH_STAT_CAP_INODE, true); } return err; } static int __init init_ceph(void) { int ret = init_caches(); if (ret) goto out; ceph_flock_init(); ret = register_filesystem(&ceph_fs_type); if (ret) goto out_caches; pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL); return 0; out_caches: destroy_caches(); out: return ret; } static void __exit exit_ceph(void) { dout("exit_ceph\n"); unregister_filesystem(&ceph_fs_type); destroy_caches(); } static int param_set_metrics(const char *val, const struct kernel_param *kp) { struct ceph_fs_client *fsc; int ret; ret = param_set_bool(val, kp); if (ret) { pr_err("Failed to parse sending metrics switch value '%s'\n", val); return ret; } else if (!disable_send_metrics) { // wake up all the mds clients spin_lock(&ceph_fsc_lock); list_for_each_entry(fsc, &ceph_fsc_list, metric_wakeup) { metric_schedule_delayed(&fsc->mdsc->metric); } spin_unlock(&ceph_fsc_lock); } return 0; } static const struct kernel_param_ops param_ops_metrics = { .set = param_set_metrics, .get = param_get_bool, }; bool disable_send_metrics = false; module_param_cb(disable_send_metrics, ¶m_ops_metrics, &disable_send_metrics, 0644); MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)"); /* for both v1 and v2 syntax */ static bool mount_support = true; static const struct kernel_param_ops param_ops_mount_syntax = { .get = param_get_bool, }; module_param_cb(mount_syntax_v1, ¶m_ops_mount_syntax, &mount_support, 0444); module_param_cb(mount_syntax_v2, ¶m_ops_mount_syntax, &mount_support, 0444); bool enable_unsafe_idmap = false; module_param(enable_unsafe_idmap, bool, 0644); MODULE_PARM_DESC(enable_unsafe_idmap, "Allow to use idmapped mounts with MDS without CEPHFS_FEATURE_HAS_OWNER_UIDGID"); module_init(init_ceph); module_exit(exit_ceph); MODULE_AUTHOR("Sage Weil <sage@newdream.net>"); MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>"); MODULE_AUTHOR("Patience Warnick <patience@newdream.net>"); MODULE_DESCRIPTION("Ceph filesystem for Linux"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_DEFRAG_H #define BTRFS_DEFRAG_H #include <linux/types.h> #include <linux/compiler_types.h> struct file_ra_state; struct btrfs_inode; struct btrfs_fs_info; struct btrfs_root; struct btrfs_trans_handle; struct btrfs_ioctl_defrag_range_args; int btrfs_defrag_file(struct btrfs_inode *inode, struct file_ra_state *ra, struct btrfs_ioctl_defrag_range_args *range, u64 newer_than, unsigned long max_to_defrag); int __init btrfs_auto_defrag_init(void); void __cold btrfs_auto_defrag_exit(void); void btrfs_add_inode_defrag(struct btrfs_inode *inode, u32 extent_thresh); int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info); void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_defrag_root(struct btrfs_root *root); static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info) { return signal_pending(current); } #endif |
| 62 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * x86-optimized SHA-512 block function * * Copyright 2025 Google LLC */ #include <asm/fpu/api.h> #include <linux/static_call.h> DEFINE_STATIC_CALL(sha512_blocks_x86, sha512_blocks_generic); #define DEFINE_X86_SHA512_FN(c_fn, asm_fn) \ asmlinkage void asm_fn(struct sha512_block_state *state, \ const u8 *data, size_t nblocks); \ static void c_fn(struct sha512_block_state *state, const u8 *data, \ size_t nblocks) \ { \ if (likely(irq_fpu_usable())) { \ kernel_fpu_begin(); \ asm_fn(state, data, nblocks); \ kernel_fpu_end(); \ } else { \ sha512_blocks_generic(state, data, nblocks); \ } \ } DEFINE_X86_SHA512_FN(sha512_blocks_ssse3, sha512_transform_ssse3); DEFINE_X86_SHA512_FN(sha512_blocks_avx, sha512_transform_avx); DEFINE_X86_SHA512_FN(sha512_blocks_avx2, sha512_transform_rorx); static void sha512_blocks(struct sha512_block_state *state, const u8 *data, size_t nblocks) { static_call(sha512_blocks_x86)(state, data, nblocks); } #define sha512_mod_init_arch sha512_mod_init_arch static void sha512_mod_init_arch(void) { if (cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL) && boot_cpu_has(X86_FEATURE_AVX)) { if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) static_call_update(sha512_blocks_x86, sha512_blocks_avx2); else static_call_update(sha512_blocks_x86, sha512_blocks_avx); } else if (boot_cpu_has(X86_FEATURE_SSSE3)) { static_call_update(sha512_blocks_x86, sha512_blocks_ssse3); } } |
| 7 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * OSS compatible i/o control * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include "seq_oss_timer.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_event.h" static int snd_seq_oss_synth_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct synth_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_synth_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_midi_info_user(struct seq_oss_devinfo *dp, void __user *arg) { struct midi_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; if (snd_seq_oss_midi_make_info(dp, info.device, &info) < 0) return -EINVAL; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_seq_oss_oob_user(struct seq_oss_devinfo *dp, void __user *arg) { unsigned char ev[8]; struct snd_seq_event tmpev; if (copy_from_user(ev, arg, 8)) return -EFAULT; memset(&tmpev, 0, sizeof(tmpev)); snd_seq_oss_fill_addr(dp, &tmpev, dp->addr.client, dp->addr.port); tmpev.time.tick = 0; if (! snd_seq_oss_process_event(dp, (union evrec *)ev, &tmpev)) { snd_seq_oss_dispatch(dp, &tmpev, 0, 0); } return 0; } int snd_seq_oss_ioctl(struct seq_oss_devinfo *dp, unsigned int cmd, unsigned long carg) { int dev, val; void __user *arg = (void __user *)carg; int __user *p = arg; switch (cmd) { case SNDCTL_TMR_TIMEBASE: case SNDCTL_TMR_TEMPO: case SNDCTL_TMR_START: case SNDCTL_TMR_STOP: case SNDCTL_TMR_CONTINUE: case SNDCTL_TMR_METRONOME: case SNDCTL_TMR_SOURCE: case SNDCTL_TMR_SELECT: case SNDCTL_SEQ_CTRLRATE: return snd_seq_oss_timer_ioctl(dp->timer, cmd, arg); case SNDCTL_SEQ_PANIC: snd_seq_oss_reset(dp); return -EINVAL; case SNDCTL_SEQ_SYNC: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; while (snd_seq_oss_writeq_sync(dp->writeq)) ; if (signal_pending(current)) return -ERESTARTSYS; return 0; case SNDCTL_SEQ_RESET: snd_seq_oss_reset(dp); return 0; case SNDCTL_SEQ_TESTMIDI: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_midi_open(dp, dev, dp->file_mode); case SNDCTL_SEQ_GETINCOUNT: if (dp->readq == NULL || ! is_read_mode(dp->file_mode)) return 0; return put_user(dp->readq->qlen, p) ? -EFAULT : 0; case SNDCTL_SEQ_GETOUTCOUNT: if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return 0; return put_user(snd_seq_oss_writeq_get_free_size(dp->writeq), p) ? -EFAULT : 0; case SNDCTL_SEQ_GETTIME: return put_user(snd_seq_oss_timer_cur_tick(dp->timer), p) ? -EFAULT : 0; case SNDCTL_SEQ_RESETSAMPLES: if (get_user(dev, p)) return -EFAULT; return snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); case SNDCTL_SEQ_NRSYNTHS: return put_user(dp->max_synthdev, p) ? -EFAULT : 0; case SNDCTL_SEQ_NRMIDIS: return put_user(dp->max_mididev, p) ? -EFAULT : 0; case SNDCTL_SYNTH_MEMAVL: if (get_user(dev, p)) return -EFAULT; val = snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return put_user(val, p) ? -EFAULT : 0; case SNDCTL_FM_4OP_ENABLE: if (get_user(dev, p)) return -EFAULT; snd_seq_oss_synth_ioctl(dp, dev, cmd, carg); return 0; case SNDCTL_SYNTH_INFO: case SNDCTL_SYNTH_ID: return snd_seq_oss_synth_info_user(dp, arg); case SNDCTL_SEQ_OUTOFBAND: return snd_seq_oss_oob_user(dp, arg); case SNDCTL_MIDI_INFO: return snd_seq_oss_midi_info_user(dp, arg); case SNDCTL_SEQ_THRESHOLD: if (! is_write_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val < 1) val = 1; if (val >= dp->writeq->maxlen) val = dp->writeq->maxlen - 1; snd_seq_oss_writeq_set_output(dp->writeq, val); return 0; case SNDCTL_MIDI_PRETIME: if (dp->readq == NULL || !is_read_mode(dp->file_mode)) return 0; if (get_user(val, p)) return -EFAULT; if (val <= 0) val = -1; else val = (HZ * val) / 10; dp->readq->pre_event_timeout = val; return put_user(val, p) ? -EFAULT : 0; default: if (! is_write_mode(dp->file_mode)) return -EIO; return snd_seq_oss_synth_ioctl(dp, 0, cmd, carg); } return 0; } |
| 1 1 2 2 1 2 1 1 2 2 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "hard-interface.h" #include "main.h" #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/kref.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <uapi/linux/batadv_packet.h> #include "bat_v.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" #include "log.h" #include "mesh-interface.h" #include "originator.h" #include "send.h" #include "translation-table.h" /** * batadv_hardif_release() - release hard interface from lists and queue for * free after rcu grace period * @ref: kref pointer of the hard interface */ void batadv_hardif_release(struct kref *ref) { struct batadv_hard_iface *hard_iface; hard_iface = container_of(ref, struct batadv_hard_iface, refcount); netdev_put(hard_iface->net_dev, &hard_iface->dev_tracker); kfree_rcu(hard_iface, rcu); } /** * batadv_hardif_get_by_netdev() - Get hard interface object of a net_device * @net_dev: net_device to search for * * Return: batadv_hard_iface of net_dev (with increased refcnt), NULL on errors */ struct batadv_hard_iface * batadv_hardif_get_by_netdev(const struct net_device *net_dev) { struct batadv_hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->net_dev == net_dev && kref_get_unless_zero(&hard_iface->refcount)) goto out; } hard_iface = NULL; out: rcu_read_unlock(); return hard_iface; } /** * batadv_getlink_net() - return link net namespace (of use fallback) * @netdev: net_device to check * @fallback_net: return in case get_link_net is not available for @netdev * * Return: result of rtnl_link_ops->get_link_net or @fallback_net */ static struct net *batadv_getlink_net(const struct net_device *netdev, struct net *fallback_net) { if (!netdev->rtnl_link_ops) return fallback_net; if (!netdev->rtnl_link_ops->get_link_net) return fallback_net; return netdev->rtnl_link_ops->get_link_net(netdev); } /** * batadv_mutual_parents() - check if two devices are each others parent * @dev1: 1st net dev * @net1: 1st devices netns * @dev2: 2nd net dev * @net2: 2nd devices netns * * veth devices come in pairs and each is the parent of the other! * * Return: true if the devices are each others parent, otherwise false */ static bool batadv_mutual_parents(const struct net_device *dev1, struct net *net1, const struct net_device *dev2, struct net *net2) { int dev1_parent_iflink = dev_get_iflink(dev1); int dev2_parent_iflink = dev_get_iflink(dev2); const struct net *dev1_parent_net; const struct net *dev2_parent_net; dev1_parent_net = batadv_getlink_net(dev1, net1); dev2_parent_net = batadv_getlink_net(dev2, net2); if (!dev1_parent_iflink || !dev2_parent_iflink) return false; return (dev1_parent_iflink == dev2->ifindex) && (dev2_parent_iflink == dev1->ifindex) && net_eq(dev1_parent_net, net2) && net_eq(dev2_parent_net, net1); } /** * batadv_is_on_batman_iface() - check if a device is a batman iface descendant * @net_dev: the device to check * * If the user creates any virtual device on top of a batman-adv interface, it * is important to prevent this new interface from being used to create a new * mesh network (this behaviour would lead to a batman-over-batman * configuration). This function recursively checks all the fathers of the * device passed as argument looking for a batman-adv mesh interface. * * Return: true if the device is descendant of a batman-adv mesh interface (or * if it is a batman-adv interface itself), false otherwise */ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) { struct net *net = dev_net(net_dev); struct net_device *parent_dev; struct net *parent_net; int iflink; bool ret; /* check if this is a batman-adv mesh interface */ if (batadv_meshif_is_valid(net_dev)) return true; iflink = dev_get_iflink(net_dev); if (iflink == 0) return false; parent_net = batadv_getlink_net(net_dev, net); /* iflink to itself, most likely physical device */ if (net == parent_net && iflink == net_dev->ifindex) return false; /* recurse over the parent device */ parent_dev = __dev_get_by_index((struct net *)parent_net, iflink); if (!parent_dev) { pr_warn("Cannot find parent device. Skipping batadv-on-batadv check for %s\n", net_dev->name); return false; } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; ret = batadv_is_on_batman_iface(parent_dev); return ret; } static bool batadv_is_valid_iface(const struct net_device *net_dev) { if (net_dev->flags & IFF_LOOPBACK) return false; if (net_dev->type != ARPHRD_ETHER) return false; if (net_dev->addr_len != ETH_ALEN) return false; /* no batman over batman */ if (batadv_is_on_batman_iface(net_dev)) return false; return true; } /** * batadv_get_real_netdevice() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * * Callers must hold the rtnl semaphore. You may want batadv_get_real_netdev() * instead of this. * * Return: the 'real' net device or the original net device and NULL in case * of an error. */ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; struct net *real_net; struct net *net; int iflink; ASSERT_RTNL(); if (!netdev) return NULL; iflink = dev_get_iflink(netdev); if (iflink == 0) { dev_hold(netdev); return netdev; } hard_iface = batadv_hardif_get_by_netdev(netdev); if (!hard_iface || !hard_iface->mesh_iface) goto out; net = dev_net(hard_iface->mesh_iface); real_net = batadv_getlink_net(netdev, net); /* iflink to itself, most likely physical device */ if (net == real_net && netdev->ifindex == iflink) { real_netdev = netdev; dev_hold(real_netdev); goto out; } real_netdev = dev_get_by_index(real_net, iflink); out: batadv_hardif_put(hard_iface); return real_netdev; } /** * batadv_get_real_netdev() - check if the given net_device struct is a virtual * interface on top of another 'real' interface * @net_device: the device to check * * Return: the 'real' net device or the original net device and NULL in case * of an error. */ struct net_device *batadv_get_real_netdev(struct net_device *net_device) { struct net_device *real_netdev; rtnl_lock(); real_netdev = batadv_get_real_netdevice(net_device); rtnl_unlock(); return real_netdev; } /** * batadv_is_wext_netdev() - check if the given net_device struct is a * wext wifi interface * @net_device: the device to check * * Return: true if the net device is a wext wireless device, false * otherwise. */ static bool batadv_is_wext_netdev(struct net_device *net_device) { if (!net_device) return false; #ifdef CONFIG_WIRELESS_EXT /* pre-cfg80211 drivers have to implement WEXT, so it is possible to * check for wireless_handlers != NULL */ if (net_device->wireless_handlers) return true; #endif return false; } /** * batadv_is_cfg80211_netdev() - check if the given net_device struct is a * cfg80211 wifi interface * @net_device: the device to check * * Return: true if the net device is a cfg80211 wireless device, false * otherwise. */ static bool batadv_is_cfg80211_netdev(struct net_device *net_device) { if (!net_device) return false; #if IS_ENABLED(CONFIG_CFG80211) /* cfg80211 drivers have to set ieee80211_ptr */ if (net_device->ieee80211_ptr) return true; #endif return false; } /** * batadv_wifi_flags_evaluate() - calculate wifi flags for net_device * @net_device: the device to check * * Return: batadv_hard_iface_wifi_flags flags of the device */ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) { u32 wifi_flags = 0; struct net_device *real_netdev; if (batadv_is_wext_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_WEXT_DIRECT; if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; real_netdev = batadv_get_real_netdevice(net_device); if (!real_netdev) return wifi_flags; if (real_netdev == net_device) goto out; if (batadv_is_wext_netdev(real_netdev)) wifi_flags |= BATADV_HARDIF_WIFI_WEXT_INDIRECT; if (batadv_is_cfg80211_netdev(real_netdev)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_INDIRECT; out: dev_put(real_netdev); return wifi_flags; } /** * batadv_is_cfg80211_hardif() - check if the given hardif is a cfg80211 wifi * interface * @hard_iface: the device to check * * Return: true if the net device is a cfg80211 wireless device, false * otherwise. */ bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface) { u32 allowed_flags = 0; allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_INDIRECT; return !!(hard_iface->wifi_flags & allowed_flags); } /** * batadv_is_wifi_hardif() - check if the given hardif is a wifi interface * @hard_iface: the device to check * * Return: true if the net device is a 802.11 wireless device, false otherwise. */ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface) { if (!hard_iface) return false; return hard_iface->wifi_flags != 0; } /** * batadv_hardif_no_broadcast() - check whether (re)broadcast is necessary * @if_outgoing: the outgoing interface checked and considered for (re)broadcast * @orig_addr: the originator of this packet * @orig_neigh: originator address of the forwarder we just got the packet from * (NULL if we originated) * * Checks whether a packet needs to be (re)broadcasted on the given interface. * * Return: * BATADV_HARDIF_BCAST_NORECIPIENT: No neighbor on interface * BATADV_HARDIF_BCAST_DUPFWD: Just one neighbor, but it is the forwarder * BATADV_HARDIF_BCAST_DUPORIG: Just one neighbor, but it is the originator * BATADV_HARDIF_BCAST_OK: Several neighbors, must broadcast */ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, u8 *orig_addr, u8 *orig_neigh) { struct batadv_hardif_neigh_node *hardif_neigh; struct hlist_node *first; int ret = BATADV_HARDIF_BCAST_OK; rcu_read_lock(); /* 0 neighbors -> no (re)broadcast */ first = rcu_dereference(hlist_first_rcu(&if_outgoing->neigh_list)); if (!first) { ret = BATADV_HARDIF_BCAST_NORECIPIENT; goto out; } /* >1 neighbors -> (re)broadcast */ if (rcu_dereference(hlist_next_rcu(first))) goto out; hardif_neigh = hlist_entry(first, struct batadv_hardif_neigh_node, list); /* 1 neighbor, is the originator -> no rebroadcast */ if (orig_addr && batadv_compare_eth(hardif_neigh->orig, orig_addr)) { ret = BATADV_HARDIF_BCAST_DUPORIG; /* 1 neighbor, is the one we received from -> no rebroadcast */ } else if (orig_neigh && batadv_compare_eth(hardif_neigh->orig, orig_neigh)) { ret = BATADV_HARDIF_BCAST_DUPFWD; } out: rcu_read_unlock(); return ret; } static struct batadv_hard_iface * batadv_hardif_get_active(struct net_device *mesh_iface) { struct batadv_hard_iface *hard_iface; struct list_head *iter; rcu_read_lock(); netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) { if (hard_iface->if_status == BATADV_IF_ACTIVE && kref_get_unless_zero(&hard_iface->refcount)) goto out; } hard_iface = NULL; out: rcu_read_unlock(); return hard_iface; } static void batadv_primary_if_update_addr(struct batadv_priv *bat_priv, struct batadv_hard_iface *oldif) { struct batadv_hard_iface *primary_if; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; batadv_dat_init_own_addr(bat_priv, primary_if); batadv_bla_update_orig_address(bat_priv, primary_if, oldif); out: batadv_hardif_put(primary_if); } static void batadv_primary_if_select(struct batadv_priv *bat_priv, struct batadv_hard_iface *new_hard_iface) { struct batadv_hard_iface *curr_hard_iface; ASSERT_RTNL(); if (new_hard_iface) kref_get(&new_hard_iface->refcount); curr_hard_iface = rcu_replace_pointer(bat_priv->primary_if, new_hard_iface, 1); if (!new_hard_iface) goto out; bat_priv->algo_ops->iface.primary_set(new_hard_iface); batadv_primary_if_update_addr(bat_priv, curr_hard_iface); out: batadv_hardif_put(curr_hard_iface); } static bool batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface) { if (hard_iface->net_dev->flags & IFF_UP) return true; return false; } static void batadv_check_known_mac_addr(const struct batadv_hard_iface *hard_iface) { struct net_device *mesh_iface = hard_iface->mesh_iface; const struct batadv_hard_iface *tmp_hard_iface; struct list_head *iter; if (!mesh_iface) return; netdev_for_each_lower_private(mesh_iface, tmp_hard_iface, iter) { if (tmp_hard_iface == hard_iface) continue; if (tmp_hard_iface->if_status == BATADV_IF_NOT_IN_USE) continue; if (!batadv_compare_eth(tmp_hard_iface->net_dev->dev_addr, hard_iface->net_dev->dev_addr)) continue; pr_warn("The newly added mac address (%pM) already exists on: %s\n", hard_iface->net_dev->dev_addr, tmp_hard_iface->net_dev->name); pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n"); } } /** * batadv_hardif_recalc_extra_skbroom() - Recalculate skbuff extra head/tailroom * @mesh_iface: netdev struct of the mesh interface */ static void batadv_hardif_recalc_extra_skbroom(struct net_device *mesh_iface) { const struct batadv_hard_iface *hard_iface; unsigned short lower_header_len = ETH_HLEN; unsigned short lower_headroom = 0; unsigned short lower_tailroom = 0; unsigned short needed_headroom; struct list_head *iter; rcu_read_lock(); netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) { if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) continue; lower_header_len = max_t(unsigned short, lower_header_len, hard_iface->net_dev->hard_header_len); lower_headroom = max_t(unsigned short, lower_headroom, hard_iface->net_dev->needed_headroom); lower_tailroom = max_t(unsigned short, lower_tailroom, hard_iface->net_dev->needed_tailroom); } rcu_read_unlock(); needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); /* fragmentation headers don't strip the unicast/... header */ needed_headroom += sizeof(struct batadv_frag_packet); mesh_iface->needed_headroom = needed_headroom; mesh_iface->needed_tailroom = lower_tailroom; } /** * batadv_hardif_min_mtu() - Calculate maximum MTU for mesh interface * @mesh_iface: netdev struct of the mesh interface * * Return: MTU for the mesh-interface (limited by the minimal MTU of all active * slave interfaces) */ int batadv_hardif_min_mtu(struct net_device *mesh_iface) { struct batadv_priv *bat_priv = netdev_priv(mesh_iface); const struct batadv_hard_iface *hard_iface; struct list_head *iter; int min_mtu = INT_MAX; rcu_read_lock(); netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) { if (hard_iface->if_status != BATADV_IF_ACTIVE && hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; min_mtu = min_t(int, hard_iface->net_dev->mtu, min_mtu); } rcu_read_unlock(); if (atomic_read(&bat_priv->fragmentation) == 0) goto out; /* with fragmentation enabled the maximum size of internally generated * packets such as translation table exchanges or tvlv containers, etc * has to be calculated */ min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; out: /* report to the other components the maximum amount of bytes that * batman-adv can send over the wire (without considering the payload * overhead). For example, this value is used by TT to compute the * maximum local table size */ atomic_set(&bat_priv->packet_size_max, min_mtu); /* the real mesh-interface MTU is computed by removing the payload * overhead from the maximum amount of bytes that was just computed. */ return min_t(int, min_mtu - batadv_max_header_len(), BATADV_MAX_MTU); } /** * batadv_update_min_mtu() - Adjusts the MTU if a new interface with a smaller * MTU appeared * @mesh_iface: netdev struct of the mesh interface */ void batadv_update_min_mtu(struct net_device *mesh_iface) { struct batadv_priv *bat_priv = netdev_priv(mesh_iface); int limit_mtu; int mtu; mtu = batadv_hardif_min_mtu(mesh_iface); if (bat_priv->mtu_set_by_user) limit_mtu = bat_priv->mtu_set_by_user; else limit_mtu = ETH_DATA_LEN; mtu = min(mtu, limit_mtu); dev_set_mtu(mesh_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. */ batadv_tt_local_resize_to_mtu(mesh_iface); } static void batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; bat_priv = netdev_priv(hard_iface->mesh_iface); bat_priv->algo_ops->iface.update_mac(hard_iface); hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED; /* the first active interface becomes our primary interface or * the next active interface after the old primary interface was removed */ primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) batadv_primary_if_select(bat_priv, hard_iface); batadv_info(hard_iface->mesh_iface, "Interface activated: %s\n", hard_iface->net_dev->name); batadv_update_min_mtu(hard_iface->mesh_iface); if (bat_priv->algo_ops->iface.activate) bat_priv->algo_ops->iface.activate(hard_iface); out: batadv_hardif_put(primary_if); } static void batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) { if (hard_iface->if_status != BATADV_IF_ACTIVE && hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) return; hard_iface->if_status = BATADV_IF_INACTIVE; batadv_info(hard_iface->mesh_iface, "Interface deactivated: %s\n", hard_iface->net_dev->name); batadv_update_min_mtu(hard_iface->mesh_iface); } /** * batadv_hardif_enable_interface() - Enslave hard interface to mesh interface * @hard_iface: hard interface to add to mesh interface * @mesh_iface: netdev struct of the mesh interface * * Return: 0 on success or negative error number in case of failure */ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net_device *mesh_iface) { struct batadv_priv *bat_priv; __be16 ethertype = htons(ETH_P_BATMAN); int max_header_len = batadv_max_header_len(); unsigned int required_mtu; unsigned int hardif_mtu; int ret; hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu); required_mtu = READ_ONCE(mesh_iface->mtu) + max_header_len; if (hardif_mtu < ETH_MIN_MTU + max_header_len) return -EINVAL; if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) goto out; kref_get(&hard_iface->refcount); netdev_hold(mesh_iface, &hard_iface->meshif_dev_tracker, GFP_ATOMIC); hard_iface->mesh_iface = mesh_iface; bat_priv = netdev_priv(hard_iface->mesh_iface); ret = netdev_master_upper_dev_link(hard_iface->net_dev, mesh_iface, hard_iface, NULL, NULL); if (ret) goto err_dev; ret = bat_priv->algo_ops->iface.enable(hard_iface); if (ret < 0) goto err_upper; hard_iface->if_status = BATADV_IF_INACTIVE; kref_get(&hard_iface->refcount); hard_iface->batman_adv_ptype.type = ethertype; hard_iface->batman_adv_ptype.func = batadv_batman_skb_recv; hard_iface->batman_adv_ptype.dev = hard_iface->net_dev; dev_add_pack(&hard_iface->batman_adv_ptype); batadv_info(hard_iface->mesh_iface, "Adding interface: %s\n", hard_iface->net_dev->name); if (atomic_read(&bat_priv->fragmentation) && hardif_mtu < required_mtu) batadv_info(hard_iface->mesh_iface, "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %i would solve the problem.\n", hard_iface->net_dev->name, hardif_mtu, required_mtu); if (!atomic_read(&bat_priv->fragmentation) && hardif_mtu < required_mtu) batadv_info(hard_iface->mesh_iface, "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %i.\n", hard_iface->net_dev->name, hardif_mtu, required_mtu); batadv_check_known_mac_addr(hard_iface); if (batadv_hardif_is_iface_up(hard_iface)) batadv_hardif_activate_interface(hard_iface); else batadv_err(hard_iface->mesh_iface, "Not using interface %s (retrying later): interface not active\n", hard_iface->net_dev->name); batadv_hardif_recalc_extra_skbroom(mesh_iface); if (bat_priv->algo_ops->iface.enabled) bat_priv->algo_ops->iface.enabled(hard_iface); out: return 0; err_upper: netdev_upper_dev_unlink(hard_iface->net_dev, mesh_iface); err_dev: hard_iface->mesh_iface = NULL; netdev_put(mesh_iface, &hard_iface->meshif_dev_tracker); batadv_hardif_put(hard_iface); return ret; } /** * batadv_hardif_cnt() - get number of interfaces enslaved to mesh interface * @mesh_iface: mesh interface to check * * This function is only using RCU for locking - the result can therefore be * off when another function is modifying the list at the same time. The * caller can use the rtnl_lock to make sure that the count is accurate. * * Return: number of connected/enslaved hard interfaces */ static size_t batadv_hardif_cnt(struct net_device *mesh_iface) { struct batadv_hard_iface *hard_iface; struct list_head *iter; size_t count = 0; rcu_read_lock(); netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) count++; rcu_read_unlock(); return count; } /** * batadv_hardif_disable_interface() - Remove hard interface from mesh interface * @hard_iface: hard interface to be removed */ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); struct batadv_hard_iface *primary_if = NULL; batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; batadv_info(hard_iface->mesh_iface, "Removing interface: %s\n", hard_iface->net_dev->name); dev_remove_pack(&hard_iface->batman_adv_ptype); batadv_hardif_put(hard_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { struct batadv_hard_iface *new_if; new_if = batadv_hardif_get_active(hard_iface->mesh_iface); batadv_primary_if_select(bat_priv, new_if); batadv_hardif_put(new_if); } bat_priv->algo_ops->iface.disable(hard_iface); hard_iface->if_status = BATADV_IF_NOT_IN_USE; /* delete all references to this hard_iface */ batadv_purge_orig_ref(bat_priv); batadv_purge_outstanding_packets(bat_priv, hard_iface); netdev_put(hard_iface->mesh_iface, &hard_iface->meshif_dev_tracker); netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->mesh_iface); batadv_hardif_recalc_extra_skbroom(hard_iface->mesh_iface); /* nobody uses this interface anymore */ if (batadv_hardif_cnt(hard_iface->mesh_iface) <= 1) batadv_gw_check_client_stop(bat_priv); hard_iface->mesh_iface = NULL; batadv_hardif_put(hard_iface); out: batadv_hardif_put(primary_if); } static struct batadv_hard_iface * batadv_hardif_add_interface(struct net_device *net_dev) { struct batadv_hard_iface *hard_iface; ASSERT_RTNL(); if (!batadv_is_valid_iface(net_dev)) return NULL; hard_iface = kzalloc(sizeof(*hard_iface), GFP_ATOMIC); if (!hard_iface) return NULL; netdev_hold(net_dev, &hard_iface->dev_tracker, GFP_ATOMIC); hard_iface->net_dev = net_dev; hard_iface->mesh_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); spin_lock_init(&hard_iface->neigh_list_lock); kref_init(&hard_iface->refcount); hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; hard_iface->wifi_flags = batadv_wifi_flags_evaluate(net_dev); if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; atomic_set(&hard_iface->hop_penalty, 0); batadv_v_hardif_init(hard_iface); kref_get(&hard_iface->refcount); list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); batadv_hardif_generation++; return hard_iface; } static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) { ASSERT_RTNL(); /* first deactivate interface */ if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) batadv_hardif_disable_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) return; hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; batadv_hardif_put(hard_iface); } /** * batadv_hard_if_event_meshif() - Handle events for mesh interfaces * @event: NETDEV_* event to handle * @net_dev: net_device which generated an event * * Return: NOTIFY_* result */ static int batadv_hard_if_event_meshif(unsigned long event, struct net_device *net_dev) { struct batadv_priv *bat_priv; switch (event) { case NETDEV_REGISTER: bat_priv = netdev_priv(net_dev); batadv_meshif_create_vlan(bat_priv, BATADV_NO_FLAGS); break; } return NOTIFY_DONE; } static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; if (batadv_meshif_is_valid(net_dev)) return batadv_hard_if_event_meshif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER || event == NETDEV_POST_TYPE_CHANGE)) hard_iface = batadv_hardif_add_interface(net_dev); if (!hard_iface) goto out; switch (event) { case NETDEV_UP: batadv_hardif_activate_interface(hard_iface); break; case NETDEV_GOING_DOWN: case NETDEV_DOWN: batadv_hardif_deactivate_interface(hard_iface); break; case NETDEV_UNREGISTER: case NETDEV_PRE_TYPE_CHANGE: list_del_rcu(&hard_iface->list); batadv_hardif_generation++; batadv_hardif_remove_interface(hard_iface); break; case NETDEV_CHANGEMTU: if (hard_iface->mesh_iface) batadv_update_min_mtu(hard_iface->mesh_iface); break; case NETDEV_CHANGEADDR: if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) goto hardif_put; batadv_check_known_mac_addr(hard_iface); bat_priv = netdev_priv(hard_iface->mesh_iface); bat_priv->algo_ops->iface.update_mac(hard_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto hardif_put; if (hard_iface == primary_if) batadv_primary_if_update_addr(bat_priv, NULL); break; case NETDEV_CHANGEUPPER: hard_iface->wifi_flags = batadv_wifi_flags_evaluate(net_dev); if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; break; default: break; } hardif_put: batadv_hardif_put(hard_iface); out: batadv_hardif_put(primary_if); return NOTIFY_DONE; } struct notifier_block batadv_hard_if_notifier = { .notifier_call = batadv_hard_if_event, }; |
| 31 31 31 3 3 3 6 35 18 16 2 6 6 18 35 29 34 29 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 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 #include <linux/proc_fs.h> #include <linux/nsproxy.h> #include <linux/ptrace.h> #include <linux/namei.h> #include <linux/file.h> #include <linux/utsname.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include "internal.h" static const struct proc_ns_operations *const ns_entries[] = { #ifdef CONFIG_NET_NS &netns_operations, #endif #ifdef CONFIG_UTS_NS &utsns_operations, #endif #ifdef CONFIG_IPC_NS &ipcns_operations, #endif #ifdef CONFIG_PID_NS &pidns_operations, &pidns_for_children_operations, #endif #ifdef CONFIG_USER_NS &userns_operations, #endif &mntns_operations, #ifdef CONFIG_CGROUPS &cgroupns_operations, #endif #ifdef CONFIG_TIME_NS &timens_operations, &timens_for_children_operations, #endif }; static const char *proc_ns_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); task = get_proc_task(inode); if (!task) return ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out; error = ns_get_path(&ns_path, task, ns_ops); if (error) goto out; error = nd_jump_link(&ns_path); out: put_task_struct(task); return ERR_PTR(error); } static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; char name[50]; int res = -EACCES; task = get_proc_task(inode); if (!task) return res; if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name, strlen(name)); } put_task_struct(task); return res; } static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, .get_link = proc_ns_get_link, .setattr = proc_setattr, }; static struct dentry *proc_ns_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct proc_ns_operations *ns_ops = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); inode->i_op = &proc_ns_link_inode_operations; ei->ns_ops = ns_ops; pid_update_inode(task, inode); return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); } static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) { struct task_struct *task = get_proc_task(file_inode(file)); const struct proc_ns_operations *const *entry, *const *last; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries)) goto out; entry = ns_entries + (ctx->pos - 2); last = &ns_entries[ARRAY_SIZE(ns_entries) - 1]; while (entry <= last) { const struct proc_ns_operations *ops = *entry; if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name), proc_ns_instantiate, task, ops)) break; ctx->pos++; entry++; } out: put_task_struct(task); return 0; } const struct file_operations proc_ns_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_ns_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct task_struct *task = get_proc_task(dir); const struct proc_ns_operations *const *entry, *const *last; unsigned int len = dentry->d_name.len; struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; last = &ns_entries[ARRAY_SIZE(ns_entries)]; for (entry = ns_entries; entry < last; entry++) { if (strlen((*entry)->name) != len) continue; if (!memcmp(dentry->d_name.name, (*entry)->name, len)) break; } if (entry == last) goto out; res = proc_ns_instantiate(dentry, task, *entry); out: put_task_struct(task); out_no_task: return res; } const struct inode_operations proc_ns_dir_inode_operations = { .lookup = proc_ns_dir_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; |
| 209 325 579 593 429 582 586 584 585 519 562 583 568 568 568 569 567 288 289 188 174 7 7 7 7 7 7 7 225 125 114 6 288 288 6 288 288 6 6 6 288 288 289 289 287 112 289 287 225 132 286 286 286 285 116 6 117 117 288 286 263 56 6 290 290 506 548 532 490 535 443 492 565 567 567 565 567 567 567 481 513 88 88 106 106 106 106 105 106 6 6 106 106 106 566 561 559 511 486 550 6 384 551 51 52 469 469 468 27 275 293 27 275 2 274 27 275 274 275 468 464 106 6 106 5 4 1 4 3 65 64 312 4 556 537 334 561 286 558 276 123 1 286 555 559 314 38 313 29 560 559 561 283 558 541 337 562 562 466 543 338 120 270 558 478 551 458 559 559 296 465 467 468 467 468 12 275 33 169 451 450 466 559 2 560 14 14 8 6 6 6 6 6 6 6 6 6 16 13 3 16 149 1 149 10 4 7 6 5 337 336 226 3 226 19 20 20 4 16 20 19 19 19 21 21 21 21 21 21 24 24 23 6 24 324 209 324 320 320 6 6 6 1 6 1 6 6 6 6 6 1 6 6 1 222 211 14 1 1 6 14 13 14 11 5 13 13 13 13 2 11 11 11 13 2 11 13 224 213 6 14 21 21 21 21 21 21 2 2 2 29 29 21 3 13 2 13 13 8 21 23 3 1 6 2 3 6 20 2 2 3 3 3 38 38 37 36 2 2 38 52 52 52 52 318 315 218 318 275 306 318 317 43 316 38 315 94 92 3 3 9 9 6 3 9 3 6 9 9 9 8 263 196 257 257 257 144 1 258 17 217 2 215 7 213 186 87 87 87 1 84 32 67 2 73 82 29 11 73 42 42 42 41 42 30 11 391 390 6 391 390 380 24 23 24 24 24 391 308 305 290 61 15 57 58 2 31 37 10 1 8 8 9 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007,2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/mm.h> #include <linux/error-injection.h> #include "messages.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "print-tree.h" #include "locking.h" #include "volumes.h" #include "qgroup.h" #include "tree-mod-log.h" #include "tree-checker.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "relocation.h" #include "file-item.h" static struct kmem_cache *btrfs_path_cachep; static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level); static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, bool extend); static int push_node_left(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src, bool empty); static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); /* * The leaf data grows from end-to-front in the node. this returns the address * of the start of the last item, which is the stop of the leaf data stack. */ static unsigned int leaf_data_end(const struct extent_buffer *leaf) { u32 nr = btrfs_header_nritems(leaf); if (nr == 0) return BTRFS_LEAF_DATA_SIZE(leaf->fs_info); return btrfs_item_offset(leaf, nr - 1); } /* * Move data in a @leaf (using memmove, safe for overlapping ranges). * * @leaf: leaf that we're doing a memmove on * @dst_offset: item data offset we're moving to * @src_offset: item data offset were' moving from * @len: length of the data we're moving * * Wrapper around memmove_extent_buffer() that takes into account the header on * the leaf. The btrfs_item offset's start directly after the header, so we * have to adjust any offsets to account for the header in the leaf. This * handles that math to simplify the callers. */ static inline void memmove_leaf_data(const struct extent_buffer *leaf, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { memmove_extent_buffer(leaf, btrfs_item_nr_offset(leaf, 0) + dst_offset, btrfs_item_nr_offset(leaf, 0) + src_offset, len); } /* * Copy item data from @src into @dst at the given @offset. * * @dst: destination leaf that we're copying into * @src: source leaf that we're copying from * @dst_offset: item data offset we're copying to * @src_offset: item data offset were' copying from * @len: length of the data we're copying * * Wrapper around copy_extent_buffer() that takes into account the header on * the leaf. The btrfs_item offset's start directly after the header, so we * have to adjust any offsets to account for the header in the leaf. This * handles that math to simplify the callers. */ static inline void copy_leaf_data(const struct extent_buffer *dst, const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { copy_extent_buffer(dst, src, btrfs_item_nr_offset(dst, 0) + dst_offset, btrfs_item_nr_offset(src, 0) + src_offset, len); } /* * Move items in a @leaf (using memmove). * * @dst: destination leaf for the items * @dst_item: the item nr we're copying into * @src_item: the item nr we're copying from * @nr_items: the number of items to copy * * Wrapper around memmove_extent_buffer() that does the math to get the * appropriate offsets into the leaf from the item numbers. */ static inline void memmove_leaf_items(const struct extent_buffer *leaf, int dst_item, int src_item, int nr_items) { memmove_extent_buffer(leaf, btrfs_item_nr_offset(leaf, dst_item), btrfs_item_nr_offset(leaf, src_item), nr_items * sizeof(struct btrfs_item)); } /* * Copy items from @src into @dst at the given @offset. * * @dst: destination leaf for the items * @src: source leaf for the items * @dst_item: the item nr we're copying into * @src_item: the item nr we're copying from * @nr_items: the number of items to copy * * Wrapper around copy_extent_buffer() that does the math to get the * appropriate offsets into the leaf from the item numbers. */ static inline void copy_leaf_items(const struct extent_buffer *dst, const struct extent_buffer *src, int dst_item, int src_item, int nr_items) { copy_extent_buffer(dst, src, btrfs_item_nr_offset(dst, dst_item), btrfs_item_nr_offset(src, src_item), nr_items * sizeof(struct btrfs_item)); } struct btrfs_path *btrfs_alloc_path(void) { might_sleep(); return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS); } /* this also releases the path */ void btrfs_free_path(struct btrfs_path *p) { if (!p) return; btrfs_release_path(p); kmem_cache_free(btrfs_path_cachep, p); } /* * path release drops references on the extent buffers in the path * and it drops any locks held by this path * * It is safe to call this on paths that no locks or extent buffers held. */ noinline void btrfs_release_path(struct btrfs_path *p) { int i; for (i = 0; i < BTRFS_MAX_LEVEL; i++) { p->slots[i] = 0; if (!p->nodes[i]) continue; if (p->locks[i]) { btrfs_tree_unlock_rw(p->nodes[i], p->locks[i]); p->locks[i] = 0; } free_extent_buffer(p->nodes[i]); p->nodes[i] = NULL; } } /* * safely gets a reference on the root node of a tree. A lock * is not taken, so a concurrent writer may put a different node * at the root of the tree. See btrfs_lock_root_node for the * looping required. * * The extent buffer returned by this has a reference taken, so * it won't disappear. It may stop being the root of the tree * at any time because there are no locks held. */ struct extent_buffer *btrfs_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { rcu_read_lock(); eb = rcu_dereference(root->node); /* * RCU really hurts here, we could free up the root node because * it was COWed but we may not get the new root node yet so do * the inc_not_zero dance and if it doesn't work then * synchronize_rcu and try again. */ if (refcount_inc_not_zero(&eb->refs)) { rcu_read_unlock(); break; } rcu_read_unlock(); synchronize_rcu(); } return eb; } /* * Cowonly root (not-shareable trees, everything not subvolume or reloc roots), * just get put onto a simple dirty list. Transaction walks this list to make * sure they get properly updated on disk. */ static void add_root_to_dirty_list(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; if (test_bit(BTRFS_ROOT_DIRTY, &root->state) || !test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state)) return; spin_lock(&fs_info->trans_lock); if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) { /* Want the extent tree to be the last on the list */ if (btrfs_root_id(root) == BTRFS_EXTENT_TREE_OBJECTID) list_move_tail(&root->dirty_list, &fs_info->dirty_cowonly_roots); else list_move(&root->dirty_list, &fs_info->dirty_cowonly_roots); } spin_unlock(&fs_info->trans_lock); } /* * used by snapshot creation to make a copy of a root for a tree with * a given objectid. The buffer with the new root node is returned in * cow_ret, and this func returns zero on success or a negative error code. */ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *cow; int ret = 0; int level; struct btrfs_disk_key disk_key; u64 reloc_src_root = 0; WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != fs_info->running_transaction->transid); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != btrfs_get_root_last_trans(root)); level = btrfs_header_level(buf); if (level == 0) btrfs_item_key(buf, &disk_key, 0); else btrfs_node_key(buf, &disk_key, 0); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) reloc_src_root = btrfs_header_owner(buf); cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid, &disk_key, level, buf->start, 0, reloc_src_root, BTRFS_NESTING_NEW_ROOT); if (IS_ERR(cow)) return PTR_ERR(cow); copy_extent_buffer_full(cow, buf); btrfs_set_header_bytenr(cow, cow->start); btrfs_set_header_generation(cow, trans->transid); btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV); btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN | BTRFS_HEADER_FLAG_RELOC); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC); else btrfs_set_header_owner(cow, new_root_objectid); write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid); if (unlikely(btrfs_header_generation(buf) > trans->transid)) { btrfs_tree_unlock(cow); free_extent_buffer(cow); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) { ret = btrfs_inc_ref(trans, root, cow, 1); if (unlikely(ret)) btrfs_abort_transaction(trans, ret); } else { ret = btrfs_inc_ref(trans, root, cow, 0); if (unlikely(ret)) btrfs_abort_transaction(trans, ret); } if (ret) { btrfs_tree_unlock(cow); free_extent_buffer(cow); return ret; } btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; } /* * check if the tree block can be shared by multiple trees */ bool btrfs_block_can_be_shared(const struct btrfs_trans_handle *trans, const struct btrfs_root *root, const struct extent_buffer *buf) { const u64 buf_gen = btrfs_header_generation(buf); /* * Tree blocks not in shareable trees and tree roots are never shared. * If a block was allocated after the last snapshot and the block was * not allocated by tree relocation, we know the block is not shared. */ if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return false; if (buf == root->node) return false; if (buf_gen > btrfs_root_last_snapshot(&root->root_item) && !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) return false; if (buf != root->commit_root) return true; /* * An extent buffer that used to be the commit root may still be shared * because the tree height may have increased and it became a child of a * higher level root. This can happen when snapshotting a subvolume * created in the current transaction. */ if (buf_gen == trans->transid) return true; return false; } static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *cow, int *last_ref) { struct btrfs_fs_info *fs_info = root->fs_info; u64 refs; u64 owner; u64 flags; int ret; /* * Backrefs update rules: * * Always use full backrefs for extent pointers in tree block * allocated by tree relocation. * * If a shared tree block is no longer referenced by its owner * tree (btrfs_header_owner(buf) == root->root_key.objectid), * use full backrefs for extent pointers in tree block. * * If a tree block is been relocating * (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID), * use full backrefs for extent pointers in tree block. * The reason for this is some operations (such as drop tree) * are only allowed for blocks use full backrefs. */ if (btrfs_block_can_be_shared(trans, root, buf)) { ret = btrfs_lookup_extent_info(trans, fs_info, buf->start, btrfs_header_level(buf), 1, &refs, &flags, NULL); if (ret) return ret; if (unlikely(refs == 0)) { btrfs_crit(fs_info, "found 0 references for tree block at bytenr %llu level %d root %llu", buf->start, btrfs_header_level(buf), btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } } else { refs = 1; if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID || btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) flags = BTRFS_BLOCK_FLAG_FULL_BACKREF; else flags = 0; } owner = btrfs_header_owner(buf); if (unlikely(owner == BTRFS_TREE_RELOC_OBJECTID && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))) { btrfs_crit(fs_info, "found tree block at bytenr %llu level %d root %llu refs %llu flags %llx without full backref flag set", buf->start, btrfs_header_level(buf), btrfs_root_id(root), refs, flags); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } if (refs > 1) { if ((owner == btrfs_root_id(root) || btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { ret = btrfs_inc_ref(trans, root, buf, 1); if (ret) return ret; if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { ret = btrfs_dec_ref(trans, root, buf, 0); if (ret) return ret; ret = btrfs_inc_ref(trans, root, cow, 1); if (ret) return ret; } ret = btrfs_set_disk_extent_flags(trans, buf, BTRFS_BLOCK_FLAG_FULL_BACKREF); if (ret) return ret; } else { if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) return ret; } } else { if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) { if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); if (ret) return ret; ret = btrfs_dec_ref(trans, root, buf, 1); if (ret) return ret; } btrfs_clear_buffer_dirty(trans, buf); *last_ref = 1; } return 0; } /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked * dirty and returned locked. If you modify the block it needs to be marked * dirty again. * * search_start -- an allocation hint for the new block * * empty_size -- a hint that you plan on doing more cow. This is the size in * bytes the allocator should try to find free next to the block it returns. * This is just a hint and may be ignored by the allocator. */ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, u64 search_start, u64 empty_size, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *cow; int level, ret; int last_ref = 0; int unlock_orig = 0; u64 parent_start = 0; u64 reloc_src_root = 0; if (*cow_ret == buf) unlock_orig = 1; btrfs_assert_tree_write_locked(buf); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != fs_info->running_transaction->transid); WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && trans->transid != btrfs_get_root_last_trans(root)); level = btrfs_header_level(buf); if (level == 0) btrfs_item_key(buf, &disk_key, 0); else btrfs_node_key(buf, &disk_key, 0); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) { if (parent) parent_start = parent->start; reloc_src_root = btrfs_header_owner(buf); } cow = btrfs_alloc_tree_block(trans, root, parent_start, btrfs_root_id(root), &disk_key, level, search_start, empty_size, reloc_src_root, nest); if (IS_ERR(cow)) return PTR_ERR(cow); /* cow is set to blocking by btrfs_init_new_buffer */ copy_extent_buffer_full(cow, buf); btrfs_set_header_bytenr(cow, cow->start); btrfs_set_header_generation(cow, trans->transid); btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV); btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN | BTRFS_HEADER_FLAG_RELOC); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC); else btrfs_set_header_owner(cow, btrfs_root_id(root)); write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid); ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } if (buf == root->node) { WARN_ON(parent && parent != buf); if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID || btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) parent_start = buf->start; ret = btrfs_tree_mod_log_insert_root(root->node, cow, true); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } refcount_inc(&cow->refs); rcu_assign_pointer(root->node, cow); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf, parent_start, last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } else { WARN_ON(trans->transid != btrfs_header_generation(parent)); ret = btrfs_tree_mod_log_insert_key(parent, parent_slot, BTRFS_MOD_LOG_KEY_REPLACE); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } btrfs_set_node_blockptr(parent, parent_slot, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); btrfs_mark_buffer_dirty(trans, parent); if (last_ref) { ret = btrfs_tree_mod_log_free_eb(buf); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf, parent_start, last_ref); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto error_unlock_cow; } } trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; error_unlock_cow: btrfs_tree_unlock(cow); free_extent_buffer(cow); return ret; } static inline bool should_cow_block(const struct btrfs_trans_handle *trans, const struct btrfs_root *root, const struct extent_buffer *buf) { if (btrfs_is_testing(root->fs_info)) return false; /* * We do not need to cow a block if * 1) this block is not created or changed in this transaction; * 2) this block does not belong to TREE_RELOC tree; * 3) the root is not forced COW. * * What is forced COW: * when we create snapshot during committing the transaction, * after we've finished copying src root, we must COW the shared * block to ensure the metadata consistency. */ if (btrfs_header_generation(buf) != trans->transid) return true; if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) return true; /* Ensure we can see the FORCE_COW bit. */ smp_mb__before_atomic(); if (test_bit(BTRFS_ROOT_FORCE_COW, &root->state)) return true; if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) return false; if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) return true; return false; } /* * COWs a single block, see btrfs_force_cow_block() for the real work. * This version of it has extra checks so that a block isn't COWed more than * once per transaction, as long as it hasn't been written yet */ int btrfs_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, enum btrfs_lock_nesting nest) { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); btrfs_crit(fs_info, "attempt to COW block %llu on root %llu that is being deleted", buf->start, btrfs_root_id(root)); return -EUCLEAN; } /* * COWing must happen through a running transaction, which always * matches the current fs generation (it's a transaction with a state * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs * into error state to prevent the commit of any transaction. */ if (unlikely(trans->transaction != fs_info->running_transaction || trans->transid != fs_info->generation)) { btrfs_abort_transaction(trans, -EUCLEAN); btrfs_crit(fs_info, "unexpected transaction when attempting to COW block %llu on root %llu, transaction %llu running transaction %llu fs generation %llu", buf->start, btrfs_root_id(root), trans->transid, fs_info->running_transaction->transid, fs_info->generation); return -EUCLEAN; } if (!should_cow_block(trans, root, buf)) { *cow_ret = buf; return 0; } search_start = round_down(buf->start, SZ_1G); /* * Before CoWing this block for later modification, check if it's * the subtree root and do the delayed subtree trace if needed. * * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); /* * same as comp_keys only with two btrfs_key's */ int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2) { if (k1->objectid > k2->objectid) return 1; if (k1->objectid < k2->objectid) return -1; if (k1->type > k2->type) return 1; if (k1->type < k2->type) return -1; if (k1->offset > k2->offset) return 1; if (k1->offset < k2->offset) return -1; return 0; } /* * Search for a key in the given extent_buffer. * * The lower boundary for the search is specified by the slot number @first_slot. * Use a value of 0 to search over the whole extent buffer. Works for both * leaves and nodes. * * The slot in the extent buffer is returned via @slot. If the key exists in the * extent buffer, then @slot will point to the slot where the key is, otherwise * it points to the slot where you would insert the key. * * Slot may point to the total number of items (i.e. one position beyond the last * key) if the key is bigger than the last key in the extent buffer. */ int btrfs_bin_search(const struct extent_buffer *eb, int first_slot, const struct btrfs_key *key, int *slot) { unsigned long p; int item_size; /* * Use unsigned types for the low and high slots, so that we get a more * efficient division in the search loop below. */ u32 low = first_slot; u32 high = btrfs_header_nritems(eb); int ret; const int key_size = sizeof(struct btrfs_disk_key); if (unlikely(low > high)) { btrfs_err(eb->fs_info, "%s: low (%u) > high (%u) eb %llu owner %llu level %d", __func__, low, high, eb->start, btrfs_header_owner(eb), btrfs_header_level(eb)); return -EINVAL; } if (btrfs_header_level(eb) == 0) { p = offsetof(struct btrfs_leaf, items); item_size = sizeof(struct btrfs_item); } else { p = offsetof(struct btrfs_node, ptrs); item_size = sizeof(struct btrfs_key_ptr); } while (low < high) { const int unit_size = eb->folio_size; unsigned long oil; unsigned long offset; struct btrfs_disk_key *tmp; struct btrfs_disk_key unaligned; int mid; mid = (low + high) / 2; offset = p + mid * item_size; oil = get_eb_offset_in_folio(eb, offset); if (oil + key_size <= unit_size) { const unsigned long idx = get_eb_folio_index(eb, offset); char *kaddr = folio_address(eb->folios[idx]); oil = get_eb_offset_in_folio(eb, offset); tmp = (struct btrfs_disk_key *)(kaddr + oil); } else { read_extent_buffer(eb, &unaligned, offset, key_size); tmp = &unaligned; } ret = btrfs_comp_keys(tmp, key); if (ret < 0) low = mid + 1; else if (ret > 0) high = mid; else { *slot = mid; return 0; } } *slot = low; return 1; } static void root_add_used_bytes(struct btrfs_root *root) { spin_lock(&root->accounting_lock); btrfs_set_root_used(&root->root_item, btrfs_root_used(&root->root_item) + root->fs_info->nodesize); spin_unlock(&root->accounting_lock); } static void root_sub_used_bytes(struct btrfs_root *root) { spin_lock(&root->accounting_lock); btrfs_set_root_used(&root->root_item, btrfs_root_used(&root->root_item) - root->fs_info->nodesize); spin_unlock(&root->accounting_lock); } /* given a node and slot number, this reads the blocks it points to. The * extent buffer is returned with a reference taken (but unlocked). */ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent, int slot) { int level = btrfs_header_level(parent); struct btrfs_tree_parent_check check = { 0 }; struct extent_buffer *eb; if (slot < 0 || slot >= btrfs_header_nritems(parent)) return ERR_PTR(-ENOENT); ASSERT(level); check.level = level - 1; check.transid = btrfs_node_ptr_generation(parent, slot); check.owner_root = btrfs_header_owner(parent); check.has_first_key = true; btrfs_node_key_to_cpu(parent, &check.first_key, slot); eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot), &check); if (IS_ERR(eb)) return eb; if (unlikely(!extent_buffer_uptodate(eb))) { free_extent_buffer(eb); return ERR_PTR(-EIO); } return eb; } /* * node level balancing, used to make sure nodes are in proper order for * item deletion. We balance from the top down, so we have to make sure * that a deletion won't leave an node completely empty later on. */ static noinline int balance_level(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *right = NULL; struct extent_buffer *mid; struct extent_buffer *left = NULL; struct extent_buffer *parent = NULL; int ret = 0; int wret; int pslot; int orig_slot = path->slots[level]; u64 orig_ptr; ASSERT(level > 0); mid = path->nodes[level]; WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK); WARN_ON(btrfs_header_generation(mid) != trans->transid); orig_ptr = btrfs_node_blockptr(mid, orig_slot); if (level < BTRFS_MAX_LEVEL - 1) { parent = path->nodes[level + 1]; pslot = path->slots[level + 1]; } /* * deal with the case where there is only one pointer in the root * by promoting the node below to a root */ if (!parent) { struct extent_buffer *child; if (btrfs_header_nritems(mid) != 1) return 0; /* promote the child to a root */ child = btrfs_read_node_slot(mid, 0); if (IS_ERR(child)) { ret = PTR_ERR(child); goto out; } btrfs_tree_lock(child); ret = btrfs_cow_block(trans, root, child, mid, 0, &child, BTRFS_NESTING_COW); if (ret) { btrfs_tree_unlock(child); free_extent_buffer(child); goto out; } ret = btrfs_tree_mod_log_insert_root(root->node, child, true); if (unlikely(ret < 0)) { btrfs_tree_unlock(child); free_extent_buffer(child); btrfs_abort_transaction(trans, ret); goto out; } rcu_assign_pointer(root->node, child); add_root_to_dirty_list(root); btrfs_tree_unlock(child); path->locks[level] = 0; path->nodes[level] = NULL; btrfs_clear_buffer_dirty(trans, mid); btrfs_tree_unlock(mid); /* once for the path */ free_extent_buffer(mid); root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } return 0; } if (btrfs_header_nritems(mid) > BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 4) return 0; if (pslot) { left = btrfs_read_node_slot(parent, pslot - 1); if (IS_ERR(left)) { ret = PTR_ERR(left); left = NULL; goto out; } btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); wret = btrfs_cow_block(trans, root, left, parent, pslot - 1, &left, BTRFS_NESTING_LEFT_COW); if (wret) { ret = wret; goto out; } } if (pslot + 1 < btrfs_header_nritems(parent)) { right = btrfs_read_node_slot(parent, pslot + 1); if (IS_ERR(right)) { ret = PTR_ERR(right); right = NULL; goto out; } btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); wret = btrfs_cow_block(trans, root, right, parent, pslot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (wret) { ret = wret; goto out; } } /* first, try to make some room in the middle buffer */ if (left) { orig_slot += btrfs_header_nritems(left); wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } /* * then try to empty the right most buffer into the middle */ if (right) { wret = push_node_left(trans, mid, right, 1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (btrfs_header_nritems(right) == 0) { btrfs_clear_buffer_dirty(trans, right); btrfs_tree_unlock(right); ret = btrfs_del_ptr(trans, root, path, level + 1, pslot + 1); if (ret < 0) { free_extent_buffer_stale(right); right = NULL; goto out; } root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), right, 0, 1); free_extent_buffer_stale(right); right = NULL; if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } } else { struct btrfs_disk_key right_key; btrfs_node_key(right, &right_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_set_node_key(parent, &right_key, pslot + 1); btrfs_mark_buffer_dirty(trans, parent); } } if (btrfs_header_nritems(mid) == 1) { /* * we're not allowed to leave a node with one item in the * tree during a delete. A deletion from lower in the tree * could try to delete the only pointer in this node. * So, pull some keys from the left. * There has to be a left pointer at this point because * otherwise we would have pulled some pointers from the * right */ if (unlikely(!left)) { btrfs_crit(fs_info, "missing left child when middle child only has 1 item, parent bytenr %llu level %d mid bytenr %llu root %llu", parent->start, btrfs_header_level(parent), mid->start, btrfs_root_id(root)); ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); goto out; } wret = balance_node_right(trans, mid, left); if (wret < 0) { ret = wret; goto out; } if (wret == 1) { wret = push_node_left(trans, left, mid, 1); if (wret < 0) ret = wret; } BUG_ON(wret == 1); } if (btrfs_header_nritems(mid) == 0) { btrfs_clear_buffer_dirty(trans, mid); btrfs_tree_unlock(mid); ret = btrfs_del_ptr(trans, root, path, level + 1, pslot); if (ret < 0) { free_extent_buffer_stale(mid); mid = NULL; goto out; } root_sub_used_bytes(root); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } } else { /* update the parent key to reflect our changes */ struct btrfs_disk_key mid_key; btrfs_node_key(mid, &mid_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_set_node_key(parent, &mid_key, pslot); btrfs_mark_buffer_dirty(trans, parent); } /* update the path */ if (left) { if (btrfs_header_nritems(left) > orig_slot) { refcount_inc(&left->refs); /* left was locked after cow */ path->nodes[level] = left; path->slots[level + 1] -= 1; path->slots[level] = orig_slot; if (mid) { btrfs_tree_unlock(mid); free_extent_buffer(mid); } } else { orig_slot -= btrfs_header_nritems(left); path->slots[level] = orig_slot; } } /* double check we haven't messed things up */ if (orig_ptr != btrfs_node_blockptr(path->nodes[level], path->slots[level])) BUG(); out: if (right) { btrfs_tree_unlock(right); free_extent_buffer(right); } if (left) { if (path->nodes[level] != left) btrfs_tree_unlock(left); free_extent_buffer(left); } return ret; } /* Node balancing for insertion. Here we only split or push nodes around * when they are completely full. This is also done top down, so we * have to be pessimistic. */ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *right = NULL; struct extent_buffer *mid; struct extent_buffer *left = NULL; struct extent_buffer *parent = NULL; int ret = 0; int wret; int pslot; int orig_slot = path->slots[level]; if (level == 0) return 1; mid = path->nodes[level]; WARN_ON(btrfs_header_generation(mid) != trans->transid); if (level < BTRFS_MAX_LEVEL - 1) { parent = path->nodes[level + 1]; pslot = path->slots[level + 1]; } if (!parent) return 1; /* first, try to make some room in the middle buffer */ if (pslot) { u32 left_nr; left = btrfs_read_node_slot(parent, pslot - 1); if (IS_ERR(left)) return PTR_ERR(left); btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); left_nr = btrfs_header_nritems(left); if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { wret = 1; } else { ret = btrfs_cow_block(trans, root, left, parent, pslot - 1, &left, BTRFS_NESTING_LEFT_COW); if (ret) wret = 1; else { wret = push_node_left(trans, left, mid, 0); } } if (wret < 0) ret = wret; if (wret == 0) { struct btrfs_disk_key disk_key; orig_slot += left_nr; btrfs_node_key(mid, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); if (unlikely(ret < 0)) { btrfs_tree_unlock(left); free_extent_buffer(left); btrfs_abort_transaction(trans, ret); return ret; } btrfs_set_node_key(parent, &disk_key, pslot); btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(left) > orig_slot) { path->nodes[level] = left; path->slots[level + 1] -= 1; path->slots[level] = orig_slot; btrfs_tree_unlock(mid); free_extent_buffer(mid); } else { orig_slot -= btrfs_header_nritems(left); path->slots[level] = orig_slot; btrfs_tree_unlock(left); free_extent_buffer(left); } return 0; } btrfs_tree_unlock(left); free_extent_buffer(left); } /* * then try to empty the right most buffer into the middle */ if (pslot + 1 < btrfs_header_nritems(parent)) { u32 right_nr; right = btrfs_read_node_slot(parent, pslot + 1); if (IS_ERR(right)) return PTR_ERR(right); btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); right_nr = btrfs_header_nritems(right); if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { wret = 1; } else { ret = btrfs_cow_block(trans, root, right, parent, pslot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (ret) wret = 1; else { wret = balance_node_right(trans, right, mid); } } if (wret < 0) ret = wret; if (wret == 0) { struct btrfs_disk_key disk_key; btrfs_node_key(right, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); if (unlikely(ret < 0)) { btrfs_tree_unlock(right); free_extent_buffer(right); btrfs_abort_transaction(trans, ret); return ret; } btrfs_set_node_key(parent, &disk_key, pslot + 1); btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(mid) <= orig_slot) { path->nodes[level] = right; path->slots[level + 1] += 1; path->slots[level] = orig_slot - btrfs_header_nritems(mid); btrfs_tree_unlock(mid); free_extent_buffer(mid); } else { btrfs_tree_unlock(right); free_extent_buffer(right); } return 0; } btrfs_tree_unlock(right); free_extent_buffer(right); } return 1; } /* * readahead one full node of leaves, finding things that are close * to the block in 'slot', and triggering ra on them. */ static void reada_for_search(struct btrfs_fs_info *fs_info, const struct btrfs_path *path, int level, int slot, u64 objectid) { struct extent_buffer *node; struct btrfs_disk_key disk_key; u32 nritems; u64 search; u64 target; u64 nread = 0; u64 nread_max; u32 nr; u32 blocksize; u32 nscan = 0; if (level != 1 && path->reada != READA_FORWARD_ALWAYS) return; if (!path->nodes[level]) return; node = path->nodes[level]; /* * Since the time between visiting leaves is much shorter than the time * between visiting nodes, limit read ahead of nodes to 1, to avoid too * much IO at once (possibly random). */ if (path->reada == READA_FORWARD_ALWAYS) { if (level > 1) nread_max = node->fs_info->nodesize; else nread_max = SZ_128K; } else { nread_max = SZ_64K; } search = btrfs_node_blockptr(node, slot); blocksize = fs_info->nodesize; if (path->reada != READA_FORWARD_ALWAYS) { struct extent_buffer *eb; eb = find_extent_buffer(fs_info, search); if (eb) { free_extent_buffer(eb); return; } } target = search; nritems = btrfs_header_nritems(node); nr = slot; while (1) { if (path->reada == READA_BACK) { if (nr == 0) break; nr--; } else if (path->reada == READA_FORWARD || path->reada == READA_FORWARD_ALWAYS) { nr++; if (nr >= nritems) break; } if (path->reada == READA_BACK && objectid) { btrfs_node_key(node, &disk_key, nr); if (btrfs_disk_key_objectid(&disk_key) != objectid) break; } search = btrfs_node_blockptr(node, nr); if (path->reada == READA_FORWARD_ALWAYS || (search <= target && target - search <= 65536) || (search > target && search - target <= 65536)) { btrfs_readahead_node_child(node, nr); nread += blocksize; } nscan++; if (nread > nread_max || nscan > 32) break; } } static noinline void reada_for_balance(const struct btrfs_path *path, int level) { struct extent_buffer *parent; int slot; int nritems; parent = path->nodes[level + 1]; if (!parent) return; nritems = btrfs_header_nritems(parent); slot = path->slots[level + 1]; if (slot > 0) btrfs_readahead_node_child(parent, slot - 1); if (slot + 1 < nritems) btrfs_readahead_node_child(parent, slot + 1); } /* * when we walk down the tree, it is usually safe to unlock the higher layers * in the tree. The exceptions are when our path goes through slot 0, because * operations on the tree might require changing key pointers higher up in the * tree. * * callers might also have set path->keep_locks, which tells this code to keep * the lock if the path points to the last slot in the block. This is part of * walking through the tree, and selecting the next slot in the higher block. * * lowest_unlock sets the lowest level in the tree we're allowed to unlock. so * if lowest_unlock is 1, level 0 won't be unlocked */ static noinline void unlock_up(struct btrfs_path *path, int level, int lowest_unlock, int min_write_lock_level, int *write_lock_level) { int i; int skip_level = level; bool check_skip = true; for (i = level; i < BTRFS_MAX_LEVEL; i++) { if (!path->nodes[i]) break; if (!path->locks[i]) break; if (check_skip) { if (path->slots[i] == 0) { skip_level = i + 1; continue; } if (path->keep_locks) { u32 nritems; nritems = btrfs_header_nritems(path->nodes[i]); if (nritems < 1 || path->slots[i] >= nritems - 1) { skip_level = i + 1; continue; } } } if (i >= lowest_unlock && i > skip_level) { check_skip = false; btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]); path->locks[i] = 0; if (write_lock_level && i > min_write_lock_level && i <= *write_lock_level) { *write_lock_level = i - 1; } } } } /* * Helper function for btrfs_search_slot() and other functions that do a search * on a btree. The goal is to find a tree block in the cache (the radix tree at * fs_info->buffer_radix), but if we can't find it, or it's not up to date, read * its pages from disk. * * Returns -EAGAIN, with the path unlocked, if the caller needs to repeat the * whole btree search, starting again from the current root node. */ static int read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, struct extent_buffer **eb_ret, int slot, const struct btrfs_key *key) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_tree_parent_check check = { 0 }; u64 blocknr; struct extent_buffer *tmp = NULL; int ret = 0; int ret2; int parent_level; bool read_tmp = false; bool tmp_locked = false; bool path_released = false; blocknr = btrfs_node_blockptr(*eb_ret, slot); parent_level = btrfs_header_level(*eb_ret); btrfs_node_key_to_cpu(*eb_ret, &check.first_key, slot); check.has_first_key = true; check.level = parent_level - 1; check.transid = btrfs_node_ptr_generation(*eb_ret, slot); check.owner_root = btrfs_root_id(root); /* * If we need to read an extent buffer from disk and we are holding locks * on upper level nodes, we unlock all the upper nodes before reading the * extent buffer, and then return -EAGAIN to the caller as it needs to * restart the search. We don't release the lock on the current level * because we need to walk this node to figure out which blocks to read. */ tmp = find_extent_buffer(fs_info, blocknr); if (tmp) { if (p->reada == READA_FORWARD_ALWAYS) reada_for_search(fs_info, p, parent_level, slot, key->objectid); /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, check.transid, true) > 0) { /* * Do extra check for first_key, eb can be stale due to * being cached, read from scrub, or have multiple * parents (shared tree blocks). */ if (unlikely(btrfs_verify_level_key(tmp, &check))) { ret = -EUCLEAN; goto out; } *eb_ret = tmp; tmp = NULL; ret = 0; goto out; } if (p->nowait) { ret = -EAGAIN; goto out; } if (!p->skip_locking) { btrfs_unlock_up_safe(p, parent_level + 1); btrfs_maybe_reset_lockdep_class(root, tmp); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); ret = -EAGAIN; path_released = true; } /* Now we're allowed to do a blocking uptodate check. */ ret2 = btrfs_read_extent_buffer(tmp, &check); if (ret2) { ret = ret2; goto out; } if (ret == 0) { ASSERT(!tmp_locked); *eb_ret = tmp; tmp = NULL; } goto out; } else if (p->nowait) { ret = -EAGAIN; goto out; } if (!p->skip_locking) { btrfs_unlock_up_safe(p, parent_level + 1); ret = -EAGAIN; } if (p->reada != READA_NONE) reada_for_search(fs_info, p, parent_level, slot, key->objectid); tmp = btrfs_find_create_tree_block(fs_info, blocknr, check.owner_root, check.level); if (IS_ERR(tmp)) { ret = PTR_ERR(tmp); tmp = NULL; goto out; } read_tmp = true; if (!p->skip_locking) { ASSERT(ret == -EAGAIN); btrfs_maybe_reset_lockdep_class(root, tmp); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); path_released = true; } /* Now we're allowed to do a blocking uptodate check. */ ret2 = btrfs_read_extent_buffer(tmp, &check); if (ret2) { ret = ret2; goto out; } /* * If the read above didn't mark this buffer up to date, * it will never end up being up to date. Set ret to EIO now * and give up so that our caller doesn't loop forever * on our EAGAINs. */ if (unlikely(!extent_buffer_uptodate(tmp))) { ret = -EIO; goto out; } if (ret == 0) { ASSERT(!tmp_locked); *eb_ret = tmp; tmp = NULL; } out: if (tmp) { if (tmp_locked) btrfs_tree_read_unlock(tmp); if (read_tmp && ret && ret != -EAGAIN) free_extent_buffer_stale(tmp); else free_extent_buffer(tmp); } if (ret && !path_released) btrfs_release_path(p); return ret; } /* * helper function for btrfs_search_slot. This does all of the checks * for node-level blocks and does any balancing required based on * the ins_len. * * If no extra work was required, zero is returned. If we had to * drop the path, -EAGAIN is returned and btrfs_search_slot must * start over */ static int setup_nodes_for_search(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *p, struct extent_buffer *b, int level, int ins_len, int *write_lock_level) { struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) { if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); return -EAGAIN; } reada_for_balance(p, level); ret = split_node(trans, root, p, level); b = p->nodes[level]; } else if (ins_len < 0 && btrfs_header_nritems(b) < BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 2) { if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); return -EAGAIN; } reada_for_balance(p, level); ret = balance_level(trans, root, p, level); if (ret) return ret; b = p->nodes[level]; if (!b) { btrfs_release_path(p); return -EAGAIN; } BUG_ON(btrfs_header_nritems(b) == 1); } return ret; } int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 iobjectid, u64 ioff, u8 key_type, struct btrfs_key *found_key) { int ret; struct btrfs_key key; struct extent_buffer *eb; ASSERT(path); ASSERT(found_key); key.type = key_type; key.objectid = iobjectid; key.offset = ioff; ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0); if (ret < 0) return ret; eb = path->nodes[0]; if (ret && path->slots[0] >= btrfs_header_nritems(eb)) { ret = btrfs_next_leaf(fs_root, path); if (ret) return ret; eb = path->nodes[0]; } btrfs_item_key_to_cpu(eb, found_key, path->slots[0]); if (found_key->type != key.type || found_key->objectid != key.objectid) return 1; return 0; } static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root, struct btrfs_path *p, int write_lock_level) { struct extent_buffer *b; int root_lock = 0; int level = 0; if (p->search_commit_root) { b = root->commit_root; refcount_inc(&b->refs); level = btrfs_header_level(b); /* * Ensure that all callers have set skip_locking when * p->search_commit_root = 1. */ ASSERT(p->skip_locking == 1); goto out; } if (p->skip_locking) { b = btrfs_root_node(root); level = btrfs_header_level(b); goto out; } /* We try very hard to do read locks on the root */ root_lock = BTRFS_READ_LOCK; /* * If the level is set to maximum, we can skip trying to get the read * lock. */ if (write_lock_level < BTRFS_MAX_LEVEL) { /* * We don't know the level of the root node until we actually * have it read locked */ if (p->nowait) { b = btrfs_try_read_lock_root_node(root); if (IS_ERR(b)) return b; } else { b = btrfs_read_lock_root_node(root); } level = btrfs_header_level(b); if (level > write_lock_level) goto out; /* Whoops, must trade for write lock */ btrfs_tree_read_unlock(b); free_extent_buffer(b); } b = btrfs_lock_root_node(root); root_lock = BTRFS_WRITE_LOCK; /* The level might have changed, check again */ level = btrfs_header_level(b); out: /* * The root may have failed to write out at some point, and thus is no * longer valid, return an error in this case. */ if (unlikely(!extent_buffer_uptodate(b))) { if (root_lock) btrfs_tree_unlock_rw(b, root_lock); free_extent_buffer(b); return ERR_PTR(-EIO); } p->nodes[level] = b; if (!p->skip_locking) p->locks[level] = root_lock; /* * Callers are responsible for dropping b's references. */ return b; } /* * Replace the extent buffer at the lowest level of the path with a cloned * version. The purpose is to be able to use it safely, after releasing the * commit root semaphore, even if relocation is happening in parallel, the * transaction used for relocation is committed and the extent buffer is * reallocated in the next transaction. * * This is used in a context where the caller does not prevent transaction * commits from happening, either by holding a transaction handle or holding * some lock, while it's doing searches through a commit root. * At the moment it's only used for send operations. */ static int finish_need_commit_sem_search(struct btrfs_path *path) { const int i = path->lowest_level; const int slot = path->slots[i]; struct extent_buffer *lowest = path->nodes[i]; struct extent_buffer *clone; ASSERT(path->need_commit_sem); if (!lowest) return 0; lockdep_assert_held_read(&lowest->fs_info->commit_root_sem); clone = btrfs_clone_extent_buffer(lowest); if (!clone) return -ENOMEM; btrfs_release_path(path); path->nodes[i] = clone; path->slots[i] = slot; return 0; } static inline int search_for_key_slot(const struct extent_buffer *eb, int search_low_slot, const struct btrfs_key *key, int prev_cmp, int *slot) { /* * If a previous call to btrfs_bin_search() on a parent node returned an * exact match (prev_cmp == 0), we can safely assume the target key will * always be at slot 0 on lower levels, since each key pointer * (struct btrfs_key_ptr) refers to the lowest key accessible from the * subtree it points to. Thus we can skip searching lower levels. */ if (prev_cmp == 0) { *slot = 0; return 0; } return btrfs_bin_search(eb, search_low_slot, key, slot); } static int search_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *path, int ins_len, int prev_cmp) { struct extent_buffer *leaf = path->nodes[0]; int leaf_free_space = -1; int search_low_slot = 0; int ret; bool do_bin_search = true; /* * If we are doing an insertion, the leaf has enough free space and the * destination slot for the key is not slot 0, then we can unlock our * write lock on the parent, and any other upper nodes, before doing the * binary search on the leaf (with search_for_key_slot()), allowing other * tasks to lock the parent and any other upper nodes. */ if (ins_len > 0) { /* * Cache the leaf free space, since we will need it later and it * will not change until then. */ leaf_free_space = btrfs_leaf_free_space(leaf); /* * !path->locks[1] means we have a single node tree, the leaf is * the root of the tree. */ if (path->locks[1] && leaf_free_space >= ins_len) { struct btrfs_disk_key first_key; ASSERT(btrfs_header_nritems(leaf) > 0); btrfs_item_key(leaf, &first_key, 0); /* * Doing the extra comparison with the first key is cheap, * taking into account that the first key is very likely * already in a cache line because it immediately follows * the extent buffer's header and we have recently accessed * the header's level field. */ ret = btrfs_comp_keys(&first_key, key); if (ret < 0) { /* * The first key is smaller than the key we want * to insert, so we are safe to unlock all upper * nodes and we have to do the binary search. * * We do use btrfs_unlock_up_safe() and not * unlock_up() because the later does not unlock * nodes with a slot of 0 - we can safely unlock * any node even if its slot is 0 since in this * case the key does not end up at slot 0 of the * leaf and there's no need to split the leaf. */ btrfs_unlock_up_safe(path, 1); search_low_slot = 1; } else { /* * The first key is >= then the key we want to * insert, so we can skip the binary search as * the target key will be at slot 0. * * We can not unlock upper nodes when the key is * less than the first key, because we will need * to update the key at slot 0 of the parent node * and possibly of other upper nodes too. * If the key matches the first key, then we can * unlock all the upper nodes, using * btrfs_unlock_up_safe() instead of unlock_up() * as stated above. */ if (ret == 0) btrfs_unlock_up_safe(path, 1); /* * ret is already 0 or 1, matching the result of * a btrfs_bin_search() call, so there is no need * to adjust it. */ do_bin_search = false; path->slots[0] = 0; } } } if (do_bin_search) { ret = search_for_key_slot(leaf, search_low_slot, key, prev_cmp, &path->slots[0]); if (ret < 0) return ret; } if (ins_len > 0) { /* * Item key already exists. In this case, if we are allowed to * insert the item (for example, in dir_item case, item key * collision is allowed), it will be merged with the original * item. Only the item size grows, no new btrfs item will be * added. If search_for_extension is not set, ins_len already * accounts the size btrfs_item, deduct it here so leaf space * check will be correct. */ if (ret == 0 && !path->search_for_extension) { ASSERT(ins_len >= sizeof(struct btrfs_item)); ins_len -= sizeof(struct btrfs_item); } ASSERT(leaf_free_space >= 0); if (leaf_free_space < ins_len) { int ret2; ret2 = split_leaf(trans, root, key, path, ins_len, (ret == 0)); ASSERT(ret2 <= 0); if (WARN_ON(ret2 > 0)) ret2 = -EUCLEAN; if (ret2) ret = ret2; } } return ret; } /* * Look for a key in a tree and perform necessary modifications to preserve * tree invariants. * * @trans: Handle of transaction, used when modifying the tree * @p: Holds all btree nodes along the search path * @root: The root node of the tree * @key: The key we are looking for * @ins_len: Indicates purpose of search: * >0 for inserts it's size of item inserted (*) * <0 for deletions * 0 for plain searches, not modifying the tree * * (*) If size of item inserted doesn't include * sizeof(struct btrfs_item), then p->search_for_extension must * be set. * @cow: boolean should CoW operations be performed. Must always be 1 * when modifying the tree. * * If @ins_len > 0, nodes and leaves will be split as we walk down the tree. * If @ins_len < 0, nodes will be merged as we walk down the tree (if possible) * * If @key is found, 0 is returned and you can find the item in the leaf level * of the path (level 0) * * If @key isn't found, 1 is returned and the leaf level of the path (level 0) * points to the slot where it should be inserted * * If an error is encountered while searching the tree a negative error number * is returned */ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { struct btrfs_fs_info *fs_info; struct extent_buffer *b; int slot; int ret; int level; int lowest_unlock = 1; /* everything at write_lock_level or lower must be write locked */ int write_lock_level = 0; u8 lowest_level = 0; int min_write_lock_level; int prev_cmp; if (!root) return -EINVAL; fs_info = root->fs_info; might_sleep(); lowest_level = p->lowest_level; WARN_ON(lowest_level && ins_len > 0); WARN_ON(p->nodes[0] != NULL); BUG_ON(!cow && ins_len); /* * For now only allow nowait for read only operations. There's no * strict reason why we can't, we just only need it for reads so it's * only implemented for reads. */ ASSERT(!p->nowait || !cow); if (ins_len < 0) { lowest_unlock = 2; /* when we are removing items, we might have to go up to level * two as we update tree pointers Make sure we keep write * for those levels as well */ write_lock_level = 2; } else if (ins_len > 0) { /* * for inserting items, make sure we have a write lock on * level 1 so we can update keys */ write_lock_level = 1; } if (!cow) write_lock_level = -1; if (cow && (p->keep_locks || p->lowest_level)) write_lock_level = BTRFS_MAX_LEVEL; min_write_lock_level = write_lock_level; if (p->need_commit_sem) { ASSERT(p->search_commit_root); if (p->nowait) { if (!down_read_trylock(&fs_info->commit_root_sem)) return -EAGAIN; } else { down_read(&fs_info->commit_root_sem); } } again: prev_cmp = -1; b = btrfs_search_slot_get_root(root, p, write_lock_level); if (IS_ERR(b)) { ret = PTR_ERR(b); goto done; } while (b) { int dec = 0; int ret2; level = btrfs_header_level(b); if (cow) { bool last_level = (level == (BTRFS_MAX_LEVEL - 1)); /* * if we don't really need to cow this block * then we don't want to set the path blocking, * so we test it here */ if (!should_cow_block(trans, root, b)) goto cow_done; /* * must have write locks on this node and the * parent */ if (level > write_lock_level || (level + 1 > write_lock_level && level + 1 < BTRFS_MAX_LEVEL && p->nodes[level + 1])) { write_lock_level = level + 1; btrfs_release_path(p); goto again; } if (last_level) ret2 = btrfs_cow_block(trans, root, b, NULL, 0, &b, BTRFS_NESTING_COW); else ret2 = btrfs_cow_block(trans, root, b, p->nodes[level + 1], p->slots[level + 1], &b, BTRFS_NESTING_COW); if (ret2) { ret = ret2; goto done; } } cow_done: p->nodes[level] = b; /* * we have a lock on b and as long as we aren't changing * the tree, there is no way to for the items in b to change. * It is safe to drop the lock on our parent before we * go through the expensive btree search on b. * * If we're inserting or deleting (ins_len != 0), then we might * be changing slot zero, which may require changing the parent. * So, we can't drop the lock until after we know which slot * we're operating on. */ if (!ins_len && !p->keep_locks) { int u = level + 1; if (u < BTRFS_MAX_LEVEL && p->locks[u]) { btrfs_tree_unlock_rw(p->nodes[u], p->locks[u]); p->locks[u] = 0; } } if (level == 0) { if (ins_len > 0) ASSERT(write_lock_level >= 1); ret = search_leaf(trans, root, key, p, ins_len, prev_cmp); if (!p->search_for_split) unlock_up(p, level, lowest_unlock, min_write_lock_level, NULL); goto done; } ret = search_for_key_slot(b, 0, key, prev_cmp, &slot); if (ret < 0) goto done; prev_cmp = ret; if (ret && slot > 0) { dec = 1; slot--; } p->slots[level] = slot; ret2 = setup_nodes_for_search(trans, root, p, b, level, ins_len, &write_lock_level); if (ret2 == -EAGAIN) goto again; if (ret2) { ret = ret2; goto done; } b = p->nodes[level]; slot = p->slots[level]; /* * Slot 0 is special, if we change the key we have to update * the parent pointer which means we must have a write lock on * the parent */ if (slot == 0 && ins_len && write_lock_level < level + 1) { write_lock_level = level + 1; btrfs_release_path(p); goto again; } unlock_up(p, level, lowest_unlock, min_write_lock_level, &write_lock_level); if (level == lowest_level) { if (dec) p->slots[level]++; goto done; } ret2 = read_block_for_search(root, p, &b, slot, key); if (ret2 == -EAGAIN && !p->nowait) goto again; if (ret2) { ret = ret2; goto done; } if (!p->skip_locking) { level = btrfs_header_level(b); btrfs_maybe_reset_lockdep_class(root, b); if (level <= write_lock_level) { btrfs_tree_lock(b); p->locks[level] = BTRFS_WRITE_LOCK; } else { if (p->nowait) { if (!btrfs_try_tree_read_lock(b)) { free_extent_buffer(b); ret = -EAGAIN; goto done; } } else { btrfs_tree_read_lock(b); } p->locks[level] = BTRFS_READ_LOCK; } p->nodes[level] = b; } } ret = 1; done: if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); if (p->need_commit_sem) { int ret2; ret2 = finish_need_commit_sem_search(p); up_read(&fs_info->commit_root_sem); if (ret2) ret = ret2; } return ret; } ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO); /* * Like btrfs_search_slot, this looks for a key in the given tree. It uses the * current state of the tree together with the operations recorded in the tree * modification log to search for the key in a previous version of this tree, as * denoted by the time_seq parameter. * * Naturally, there is no support for insert, delete or cow operations. * * The resulting path and return value will be set up as if we called * btrfs_search_slot at that point in time with ins_len and cow both set to 0. */ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, u64 time_seq) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *b; int slot; int ret; int level; int lowest_unlock = 1; u8 lowest_level = 0; lowest_level = p->lowest_level; WARN_ON(p->nodes[0] != NULL); ASSERT(!p->nowait); if (p->search_commit_root) { BUG_ON(time_seq); return btrfs_search_slot(NULL, root, key, p, 0, 0); } again: b = btrfs_get_old_root(root, time_seq); if (unlikely(!b)) { ret = -EIO; goto done; } level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; while (b) { int dec = 0; int ret2; level = btrfs_header_level(b); p->nodes[level] = b; /* * we have a lock on b and as long as we aren't changing * the tree, there is no way to for the items in b to change. * It is safe to drop the lock on our parent before we * go through the expensive btree search on b. */ btrfs_unlock_up_safe(p, level + 1); ret = btrfs_bin_search(b, 0, key, &slot); if (ret < 0) goto done; if (level == 0) { p->slots[level] = slot; unlock_up(p, level, lowest_unlock, 0, NULL); goto done; } if (ret && slot > 0) { dec = 1; slot--; } p->slots[level] = slot; unlock_up(p, level, lowest_unlock, 0, NULL); if (level == lowest_level) { if (dec) p->slots[level]++; goto done; } ret2 = read_block_for_search(root, p, &b, slot, key); if (ret2 == -EAGAIN && !p->nowait) goto again; if (ret2) { ret = ret2; goto done; } level = btrfs_header_level(b); btrfs_tree_read_lock(b); b = btrfs_tree_mod_log_rewind(fs_info, b, time_seq); if (!b) { ret = -ENOMEM; goto done; } p->locks[level] = BTRFS_READ_LOCK; p->nodes[level] = b; } ret = 1; done: if (ret < 0) btrfs_release_path(p); return ret; } /* * Search the tree again to find a leaf with smaller keys. * Returns 0 if it found something. * Returns 1 if there are no smaller keys. * Returns < 0 on error. * * This may release the path, and so you may lose any locks held at the * time you call it. */ static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); orig_key = key; if (key.offset > 0) { key.offset--; } else if (key.type > 0) { key.type--; key.offset = (u64)-1; } else if (key.objectid > 0) { key.objectid--; key.type = (u8)-1; key.offset = (u64)-1; } else { return 1; } btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret <= 0) return ret; /* * Previous key not found. Even if we were at slot 0 of the leaf we had * before releasing the path and calling btrfs_search_slot(), we now may * be in a slot pointing to the same original key - this can happen if * after we released the path, one of more items were moved from a * sibling leaf into the front of the leaf we had due to an insertion * (see push_leaf_right()). * If we hit this case and our slot is > 0 and just decrement the slot * so that the caller does not process the same key again, which may or * may not break the caller, depending on its logic. */ if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); ret = btrfs_comp_keys(&found_key, &orig_key); if (ret == 0) { if (path->slots[0] > 0) { path->slots[0]--; return 0; } /* * At slot 0, same key as before, it means orig_key is * the lowest, leftmost, key in the tree. We're done. */ return 1; } } btrfs_item_key(path->nodes[0], &found_key, 0); ret = btrfs_comp_keys(&found_key, &key); /* * We might have had an item with the previous key in the tree right * before we released our path. And after we released our path, that * item might have been pushed to the first slot (0) of the leaf we * were holding due to a tree balance. Alternatively, an item with the * previous key can exist as the only element of a leaf (big fat item). * Therefore account for these 2 cases, so that our callers (like * btrfs_previous_item) don't miss an existing item with a key matching * the previous key we computed above. */ if (ret <= 0) return 0; return 1; } /* * helper to use instead of search slot if no exact match is needed but * instead the next or previous item should be returned. * When find_higher is true, the next higher item is returned, the next lower * otherwise. * When return_any and find_higher are both true, and no higher item is found, * return the next lower instead. * When return_any is true and find_higher is false, and no lower item is found, * return the next higher instead. * It returns 0 if any item is found, 1 if none is found (tree empty), and * < 0 on error */ int btrfs_search_slot_for_read(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int find_higher, int return_any) { int ret; struct extent_buffer *leaf; again: ret = btrfs_search_slot(NULL, root, key, p, 0, 0); if (ret <= 0) return ret; /* * a return value of 1 means the path is at the position where the * item should be inserted. Normally this is the next bigger item, * but in case the previous item is the last in a leaf, path points * to the first free slot in the previous leaf, i.e. at an invalid * item. */ leaf = p->nodes[0]; if (find_higher) { if (p->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, p); if (ret <= 0) return ret; if (!return_any) return 1; /* * no higher item found, return the next * lower instead */ return_any = 0; find_higher = 0; btrfs_release_path(p); goto again; } } else { if (p->slots[0] == 0) { ret = btrfs_prev_leaf(root, p); if (ret < 0) return ret; if (!ret) { leaf = p->nodes[0]; if (p->slots[0] == btrfs_header_nritems(leaf)) p->slots[0]--; return 0; } if (!return_any) return 1; /* * no lower item found, return the next * higher instead */ return_any = 0; find_higher = 1; btrfs_release_path(p); goto again; } else { --p->slots[0]; } } return 0; } /* * Execute search and call btrfs_previous_item to traverse backwards if the item * was not found. * * Return 0 if found, 1 if not found and < 0 if error. */ int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path) { int ret; ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret > 0) ret = btrfs_previous_item(root, path, key->objectid, key->type); if (ret == 0) btrfs_item_key_to_cpu(path->nodes[0], key, path->slots[0]); return ret; } /* * Search for a valid slot for the given path. * * @root: The root node of the tree. * @key: Will contain a valid item if found. * @path: The starting point to validate the slot. * * Return: 0 if the item is valid * 1 if not found * <0 if error. */ int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path) { if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { int ret; ret = btrfs_next_leaf(root, path); if (ret) return ret; } btrfs_item_key_to_cpu(path->nodes[0], key, path->slots[0]); return 0; } /* * adjust the pointers going up the tree, starting at level * making sure the right key of each node is points to 'key'. * This is used after shifting pointers to the left, so it stops * fixing up pointers when a given leaf/node is not in slot 0 of the * higher levels * */ static void fixup_low_keys(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_disk_key *key, int level) { int i; struct extent_buffer *t; int ret; for (i = level; i < BTRFS_MAX_LEVEL; i++) { int tslot = path->slots[i]; if (!path->nodes[i]) break; t = path->nodes[i]; ret = btrfs_tree_mod_log_insert_key(t, tslot, BTRFS_MOD_LOG_KEY_REPLACE); BUG_ON(ret < 0); btrfs_set_node_key(t, key, tslot); btrfs_mark_buffer_dirty(trans, path->nodes[i]); if (tslot != 0) break; } } /* * update item key. * * This function isn't completely safe. It's the caller's responsibility * that the new key won't break the order */ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_key *new_key) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *eb; int slot; eb = path->nodes[0]; slot = path->slots[0]; if (slot > 0) { btrfs_item_key(eb, &disk_key, slot - 1); if (unlikely(btrfs_comp_keys(&disk_key, new_key) >= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); BUG(); } } if (slot < btrfs_header_nritems(eb) - 1) { btrfs_item_key(eb, &disk_key, slot + 1); if (unlikely(btrfs_comp_keys(&disk_key, new_key) <= 0)) { btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), btrfs_disk_key_type(&disk_key), btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); BUG(); } } btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(eb, &disk_key, slot); btrfs_mark_buffer_dirty(trans, eb); if (slot == 0) fixup_low_keys(trans, path, &disk_key, 1); } /* * Check key order of two sibling extent buffers. * * Return true if something is wrong. * Return false if everything is fine. * * Tree-checker only works inside one tree block, thus the following * corruption can not be detected by tree-checker: * * Leaf @left | Leaf @right * -------------------------------------------------------------- * | 1 | 2 | 3 | 4 | 5 | f6 | | 7 | 8 | * * Key f6 in leaf @left itself is valid, but not valid when the next * key in leaf @right is 7. * This can only be checked at tree block merge time. * And since tree checker has ensured all key order in each tree block * is correct, we only need to bother the last key of @left and the first * key of @right. */ static bool check_sibling_keys(const struct extent_buffer *left, const struct extent_buffer *right) { struct btrfs_key left_last; struct btrfs_key right_first; int level = btrfs_header_level(left); int nr_left = btrfs_header_nritems(left); int nr_right = btrfs_header_nritems(right); /* No key to check in one of the tree blocks */ if (!nr_left || !nr_right) return false; if (level) { btrfs_node_key_to_cpu(left, &left_last, nr_left - 1); btrfs_node_key_to_cpu(right, &right_first, 0); } else { btrfs_item_key_to_cpu(left, &left_last, nr_left - 1); btrfs_item_key_to_cpu(right, &right_first, 0); } if (unlikely(btrfs_comp_cpu_keys(&left_last, &right_first) >= 0)) { btrfs_crit(left->fs_info, "left extent buffer:"); btrfs_print_tree(left, false); btrfs_crit(left->fs_info, "right extent buffer:"); btrfs_print_tree(right, false); btrfs_crit(left->fs_info, "bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)", left_last.objectid, left_last.type, left_last.offset, right_first.objectid, right_first.type, right_first.offset); return true; } return false; } /* * try to push data from one node into the next node left in the * tree. * * returns 0 if some ptrs were pushed left, < 0 if there was some horrible * error, and > 0 if there was no room in the left hand block. */ static int push_node_left(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src, bool empty) { struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int src_nritems; int dst_nritems; int ret = 0; src_nritems = btrfs_header_nritems(src); dst_nritems = btrfs_header_nritems(dst); push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems; WARN_ON(btrfs_header_generation(src) != trans->transid); WARN_ON(btrfs_header_generation(dst) != trans->transid); if (!empty && src_nritems <= 8) return 1; if (push_items <= 0) return 1; if (empty) { push_items = min(src_nritems, push_items); if (push_items < src_nritems) { /* leave at least 8 pointers in the node if * we aren't going to empty it */ if (src_nritems - push_items < 8) { if (push_items <= 8) return 1; push_items -= 8; } } } else push_items = min(src_nritems - 8, push_items); /* dst is the left eb, src is the middle eb */ if (unlikely(check_sibling_keys(dst, src))) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } ret = btrfs_tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst, dst_nritems), btrfs_node_key_ptr_offset(src, 0), push_items * sizeof(struct btrfs_key_ptr)); if (push_items < src_nritems) { /* * btrfs_tree_mod_log_eb_copy handles logging the move, so we * don't need to do an explicit tree mod log operation for it. */ memmove_extent_buffer(src, btrfs_node_key_ptr_offset(src, 0), btrfs_node_key_ptr_offset(src, push_items), (src_nritems - push_items) * sizeof(struct btrfs_key_ptr)); } btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); btrfs_mark_buffer_dirty(trans, src); btrfs_mark_buffer_dirty(trans, dst); return ret; } /* * try to push data from one node into the next node right in the * tree. * * returns 0 if some ptrs were pushed, < 0 if there was some horrible * error, and > 0 if there was no room in the right hand block. * * this will only push up to 1/2 the contents of the left node over */ static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst, struct extent_buffer *src) { struct btrfs_fs_info *fs_info = trans->fs_info; int push_items = 0; int max_push; int src_nritems; int dst_nritems; int ret = 0; WARN_ON(btrfs_header_generation(src) != trans->transid); WARN_ON(btrfs_header_generation(dst) != trans->transid); src_nritems = btrfs_header_nritems(src); dst_nritems = btrfs_header_nritems(dst); push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems; if (push_items <= 0) return 1; if (src_nritems < 4) return 1; max_push = src_nritems / 2 + 1; /* don't try to empty the node */ if (max_push >= src_nritems) return 1; if (max_push < push_items) push_items = max_push; /* dst is the right eb, src is the middle eb */ if (unlikely(check_sibling_keys(src, dst))) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); return ret; } /* * btrfs_tree_mod_log_eb_copy handles logging the move, so we don't * need to do an explicit tree mod log operation for it. */ memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(dst, push_items), btrfs_node_key_ptr_offset(dst, 0), (dst_nritems) * sizeof(struct btrfs_key_ptr)); ret = btrfs_tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items, push_items); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst, 0), btrfs_node_key_ptr_offset(src, src_nritems - push_items), push_items * sizeof(struct btrfs_key_ptr)); btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); btrfs_mark_buffer_dirty(trans, src); btrfs_mark_buffer_dirty(trans, dst); return ret; } /* * helper function to insert a new root level in the tree. * A new node is allocated, and a single item is inserted to * point to the existing root * * returns zero on success or < 0 on failure. */ static noinline int insert_new_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { u64 lower_gen; struct extent_buffer *lower; struct extent_buffer *c; struct extent_buffer *old; struct btrfs_disk_key lower_key; int ret; BUG_ON(path->nodes[level]); BUG_ON(path->nodes[level-1] != root->node); lower = path->nodes[level-1]; if (level == 1) btrfs_item_key(lower, &lower_key, 0); else btrfs_node_key(lower, &lower_key, 0); c = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &lower_key, level, root->node->start, 0, 0, BTRFS_NESTING_NEW_ROOT); if (IS_ERR(c)) return PTR_ERR(c); root_add_used_bytes(root); btrfs_set_header_nritems(c, 1); btrfs_set_node_key(c, &lower_key, 0); btrfs_set_node_blockptr(c, 0, lower->start); lower_gen = btrfs_header_generation(lower); WARN_ON(lower_gen != trans->transid); btrfs_set_node_ptr_generation(c, 0, lower_gen); btrfs_mark_buffer_dirty(trans, c); old = root->node; ret = btrfs_tree_mod_log_insert_root(root->node, c, false); if (ret < 0) { int ret2; btrfs_clear_buffer_dirty(trans, c); ret2 = btrfs_free_tree_block(trans, btrfs_root_id(root), c, 0, 1); if (unlikely(ret2 < 0)) btrfs_abort_transaction(trans, ret2); btrfs_tree_unlock(c); free_extent_buffer(c); return ret; } rcu_assign_pointer(root->node, c); /* the super has an extra ref to root->node */ free_extent_buffer(old); add_root_to_dirty_list(root); refcount_inc(&c->refs); path->nodes[level] = c; path->locks[level] = BTRFS_WRITE_LOCK; path->slots[level] = 0; return 0; } /* * worker function to insert a single pointer in a node. * the node should have enough room for the pointer already * * slot and level indicate where you want the key to go, and * blocknr is the block the key points to. */ static int insert_ptr(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_disk_key *key, u64 bytenr, int slot, int level) { struct extent_buffer *lower; int nritems; int ret; BUG_ON(!path->nodes[level]); btrfs_assert_tree_write_locked(path->nodes[level]); lower = path->nodes[level]; nritems = btrfs_header_nritems(lower); BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(trans->fs_info)); if (slot != nritems) { if (level) { ret = btrfs_tree_mod_log_insert_move(lower, slot + 1, slot, nritems - slot); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } } memmove_extent_buffer(lower, btrfs_node_key_ptr_offset(lower, slot + 1), btrfs_node_key_ptr_offset(lower, slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } if (level) { ret = btrfs_tree_mod_log_insert_key(lower, slot, BTRFS_MOD_LOG_KEY_ADD); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } } btrfs_set_node_key(lower, key, slot); btrfs_set_node_blockptr(lower, slot, bytenr); WARN_ON(trans->transid == 0); btrfs_set_node_ptr_generation(lower, slot, trans->transid); btrfs_set_header_nritems(lower, nritems + 1); btrfs_mark_buffer_dirty(trans, lower); return 0; } /* * split the node at the specified level in path in two. * The path is corrected to point to the appropriate node after the split * * Before splitting this tries to make some room in the node by pushing * left and right, if either one works, it returns right away. * * returns 0 on success and < 0 on failure */ static noinline int split_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *c; struct extent_buffer *split; struct btrfs_disk_key disk_key; int mid; int ret; u32 c_nritems; c = path->nodes[level]; WARN_ON(btrfs_header_generation(c) != trans->transid); if (c == root->node) { /* * trying to split the root, lets make a new one * * tree mod log: We don't log_removal old root in * insert_new_root, because that root buffer will be kept as a * normal node. We are going to log removal of half of the * elements below with btrfs_tree_mod_log_eb_copy(). We're * holding a tree lock on the buffer, which is why we cannot * race with other tree_mod_log users. */ ret = insert_new_root(trans, root, path, level + 1); if (ret) return ret; } else { ret = push_nodes_for_insert(trans, root, path, level); c = path->nodes[level]; if (!ret && btrfs_header_nritems(c) < BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) return 0; if (ret < 0) return ret; } c_nritems = btrfs_header_nritems(c); mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); split = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &disk_key, level, c->start, 0, 0, BTRFS_NESTING_SPLIT); if (IS_ERR(split)) return PTR_ERR(split); root_add_used_bytes(root); ASSERT(btrfs_header_level(c) == level); ret = btrfs_tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid); if (unlikely(ret)) { btrfs_tree_unlock(split); free_extent_buffer(split); btrfs_abort_transaction(trans, ret); return ret; } copy_extent_buffer(split, c, btrfs_node_key_ptr_offset(split, 0), btrfs_node_key_ptr_offset(c, mid), (c_nritems - mid) * sizeof(struct btrfs_key_ptr)); btrfs_set_header_nritems(split, c_nritems - mid); btrfs_set_header_nritems(c, mid); btrfs_mark_buffer_dirty(trans, c); btrfs_mark_buffer_dirty(trans, split); ret = insert_ptr(trans, path, &disk_key, split->start, path->slots[level + 1] + 1, level + 1); if (ret < 0) { btrfs_tree_unlock(split); free_extent_buffer(split); return ret; } if (path->slots[level] >= mid) { path->slots[level] -= mid; btrfs_tree_unlock(c); free_extent_buffer(c); path->nodes[level] = split; path->slots[level + 1] += 1; } else { btrfs_tree_unlock(split); free_extent_buffer(split); } return 0; } /* * how many bytes are required to store the items in a leaf. start * and nr indicate which items in the leaf to check. This totals up the * space used both by the item structs and the item data */ static int leaf_space_used(const struct extent_buffer *l, int start, int nr) { int data_len; int nritems = btrfs_header_nritems(l); int end = min(nritems, start + nr) - 1; if (!nr) return 0; data_len = btrfs_item_offset(l, start) + btrfs_item_size(l, start); data_len = data_len - btrfs_item_offset(l, end); data_len += sizeof(struct btrfs_item) * nr; WARN_ON(data_len < 0); return data_len; } /* * The space between the end of the leaf items and * the start of the leaf data. IOW, how much room * the leaf has left for both items and data */ int btrfs_leaf_free_space(const struct extent_buffer *leaf) { struct btrfs_fs_info *fs_info = leaf->fs_info; int nritems = btrfs_header_nritems(leaf); int ret; ret = BTRFS_LEAF_DATA_SIZE(fs_info) - leaf_space_used(leaf, 0, nritems); if (unlikely(ret < 0)) { btrfs_crit(fs_info, "leaf free space ret %d, leaf data size %lu, used %d nritems %d", ret, (unsigned long) BTRFS_LEAF_DATA_SIZE(fs_info), leaf_space_used(leaf, 0, nritems), nritems); } return ret; } /* * min slot controls the lowest index we're willing to push to the * right. We'll push up to and including min_slot, but no lower */ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_path *path, int data_size, bool empty, struct extent_buffer *right, int free_space, u32 left_nritems, u32 min_slot) { struct btrfs_fs_info *fs_info = right->fs_info; struct extent_buffer *left = path->nodes[0]; struct extent_buffer *upper = path->nodes[1]; struct btrfs_disk_key disk_key; int slot; u32 i; int push_space = 0; int push_items = 0; u32 nr; u32 right_nritems; u32 data_end; u32 this_item_size; if (empty) nr = 0; else nr = max_t(u32, 1, min_slot); if (path->slots[0] >= left_nritems) push_space += data_size; slot = path->slots[1]; i = left_nritems - 1; while (i >= nr) { if (!empty && push_items > 0) { if (path->slots[0] > i) break; if (path->slots[0] == i) { int space = btrfs_leaf_free_space(left); if (space + push_space * 2 > free_space) break; } } if (path->slots[0] == i) push_space += data_size; this_item_size = btrfs_item_size(left, i); if (this_item_size + sizeof(struct btrfs_item) + push_space > free_space) break; push_items++; push_space += this_item_size + sizeof(struct btrfs_item); if (i == 0) break; i--; } if (push_items == 0) goto out_unlock; WARN_ON(!empty && push_items == left_nritems); /* push left to right */ right_nritems = btrfs_header_nritems(right); push_space = btrfs_item_data_end(left, left_nritems - push_items); push_space -= leaf_data_end(left); /* make room in the right data area */ data_end = leaf_data_end(right); memmove_leaf_data(right, data_end - push_space, data_end, BTRFS_LEAF_DATA_SIZE(fs_info) - data_end); /* copy from the left data area */ copy_leaf_data(right, left, BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, leaf_data_end(left), push_space); memmove_leaf_items(right, push_items, 0, right_nritems); /* copy the items from left to right */ copy_leaf_items(right, left, 0, left_nritems - push_items, push_items); /* update the item pointers */ right_nritems += push_items; btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(fs_info); for (i = 0; i < right_nritems; i++) { push_space -= btrfs_item_size(right, i); btrfs_set_item_offset(right, i, push_space); } left_nritems -= push_items; btrfs_set_header_nritems(left, left_nritems); if (left_nritems) btrfs_mark_buffer_dirty(trans, left); else btrfs_clear_buffer_dirty(trans, left); btrfs_mark_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); btrfs_set_node_key(upper, &disk_key, slot + 1); btrfs_mark_buffer_dirty(trans, upper); /* then fixup the leaf pointer in the path */ if (path->slots[0] >= left_nritems) { path->slots[0] -= left_nritems; if (btrfs_header_nritems(path->nodes[0]) == 0) btrfs_clear_buffer_dirty(trans, path->nodes[0]); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[1] += 1; } else { btrfs_tree_unlock(right); free_extent_buffer(right); } return 0; out_unlock: btrfs_tree_unlock(right); free_extent_buffer(right); return 1; } /* * push some data in the path leaf to the right, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * returns 1 if the push failed because the other node didn't have enough * room, 0 if everything worked out and < 0 if there were major errors. * * this will push starting from min_slot to the end of the leaf. It won't * push any slot lower than min_slot */ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int min_data_size, int data_size, bool empty, u32 min_slot) { struct extent_buffer *left = path->nodes[0]; struct extent_buffer *right; struct extent_buffer *upper; int slot; int free_space; u32 left_nritems; int ret; if (!path->nodes[1]) return 1; slot = path->slots[1]; upper = path->nodes[1]; if (slot >= btrfs_header_nritems(upper) - 1) return 1; btrfs_assert_tree_write_locked(path->nodes[1]); right = btrfs_read_node_slot(upper, slot + 1); if (IS_ERR(right)) return PTR_ERR(right); btrfs_tree_lock_nested(right, BTRFS_NESTING_RIGHT); free_space = btrfs_leaf_free_space(right); if (free_space < data_size) goto out_unlock; ret = btrfs_cow_block(trans, root, right, upper, slot + 1, &right, BTRFS_NESTING_RIGHT_COW); if (ret) goto out_unlock; left_nritems = btrfs_header_nritems(left); if (left_nritems == 0) goto out_unlock; if (unlikely(check_sibling_keys(left, right))) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } if (path->slots[0] == left_nritems && !empty) { /* Key greater than all keys in the leaf, right neighbor has * enough room for it and we're not emptying our leaf to delete * it, therefore use right neighbor to insert the new item and * no need to touch/dirty our left leaf. */ btrfs_tree_unlock(left); free_extent_buffer(left); path->nodes[0] = right; path->slots[0] = 0; path->slots[1]++; return 0; } return __push_leaf_right(trans, path, min_data_size, empty, right, free_space, left_nritems, min_slot); out_unlock: btrfs_tree_unlock(right); free_extent_buffer(right); return 1; } /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * max_slot can put a limit on how far into the leaf we'll push items. The * item at 'max_slot' won't be touched. Use (u32)-1 to make us do all the * items */ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_path *path, int data_size, bool empty, struct extent_buffer *left, int free_space, u32 right_nritems, u32 max_slot) { struct btrfs_fs_info *fs_info = left->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *right = path->nodes[0]; int i; int push_space = 0; int push_items = 0; u32 old_left_nritems; u32 nr; int ret = 0; u32 this_item_size; u32 old_left_item_size; if (empty) nr = min(right_nritems, max_slot); else nr = min(right_nritems - 1, max_slot); for (i = 0; i < nr; i++) { if (!empty && push_items > 0) { if (path->slots[0] < i) break; if (path->slots[0] == i) { int space = btrfs_leaf_free_space(right); if (space + push_space * 2 > free_space) break; } } if (path->slots[0] == i) push_space += data_size; this_item_size = btrfs_item_size(right, i); if (this_item_size + sizeof(struct btrfs_item) + push_space > free_space) break; push_items++; push_space += this_item_size + sizeof(struct btrfs_item); } if (push_items == 0) { ret = 1; goto out; } WARN_ON(!empty && push_items == btrfs_header_nritems(right)); /* push data from right to left */ copy_leaf_items(left, right, btrfs_header_nritems(left), 0, push_items); push_space = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_offset(right, push_items - 1); copy_leaf_data(left, right, leaf_data_end(left) - push_space, btrfs_item_offset(right, push_items - 1), push_space); old_left_nritems = btrfs_header_nritems(left); BUG_ON(old_left_nritems <= 0); old_left_item_size = btrfs_item_offset(left, old_left_nritems - 1); for (i = old_left_nritems; i < old_left_nritems + push_items; i++) { u32 ioff; ioff = btrfs_item_offset(left, i); btrfs_set_item_offset(left, i, ioff - (BTRFS_LEAF_DATA_SIZE(fs_info) - old_left_item_size)); } btrfs_set_header_nritems(left, old_left_nritems + push_items); /* fixup right node */ if (push_items > right_nritems) WARN(1, KERN_CRIT "push items %d nr %u\n", push_items, right_nritems); if (push_items < right_nritems) { push_space = btrfs_item_offset(right, push_items - 1) - leaf_data_end(right); memmove_leaf_data(right, BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, leaf_data_end(right), push_space); memmove_leaf_items(right, 0, push_items, btrfs_header_nritems(right) - push_items); } right_nritems -= push_items; btrfs_set_header_nritems(right, right_nritems); push_space = BTRFS_LEAF_DATA_SIZE(fs_info); for (i = 0; i < right_nritems; i++) { push_space = push_space - btrfs_item_size(right, i); btrfs_set_item_offset(right, i, push_space); } btrfs_mark_buffer_dirty(trans, left); if (right_nritems) btrfs_mark_buffer_dirty(trans, right); else btrfs_clear_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, 1); /* then fixup the leaf pointer in the path */ if (path->slots[0] < push_items) { path->slots[0] += old_left_nritems; btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = left; path->slots[1] -= 1; } else { btrfs_tree_unlock(left); free_extent_buffer(left); path->slots[0] -= push_items; } BUG_ON(path->slots[0] < 0); return ret; out: btrfs_tree_unlock(left); free_extent_buffer(left); return ret; } /* * push some data in the path leaf to the left, trying to free up at * least data_size bytes. returns zero if the push worked, nonzero otherwise * * max_slot can put a limit on how far into the leaf we'll push items. The * item at 'max_slot' won't be touched. Use (u32)-1 to make us push all the * items */ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int min_data_size, int data_size, int empty, u32 max_slot) { struct extent_buffer *right = path->nodes[0]; struct extent_buffer *left; int slot; int free_space; u32 right_nritems; int ret = 0; slot = path->slots[1]; if (slot == 0) return 1; if (!path->nodes[1]) return 1; right_nritems = btrfs_header_nritems(right); if (right_nritems == 0) return 1; btrfs_assert_tree_write_locked(path->nodes[1]); left = btrfs_read_node_slot(path->nodes[1], slot - 1); if (IS_ERR(left)) return PTR_ERR(left); btrfs_tree_lock_nested(left, BTRFS_NESTING_LEFT); free_space = btrfs_leaf_free_space(left); if (free_space < data_size) { ret = 1; goto out; } ret = btrfs_cow_block(trans, root, left, path->nodes[1], slot - 1, &left, BTRFS_NESTING_LEFT_COW); if (ret) { /* we hit -ENOSPC, but it isn't fatal here */ if (ret == -ENOSPC) ret = 1; goto out; } if (unlikely(check_sibling_keys(left, right))) { ret = -EUCLEAN; btrfs_abort_transaction(trans, ret); goto out; } return __push_leaf_left(trans, path, min_data_size, empty, left, free_space, right_nritems, max_slot); out: btrfs_tree_unlock(left); free_extent_buffer(left); return ret; } /* * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. */ static noinline int copy_for_split(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct extent_buffer *l, struct extent_buffer *right, int slot, int mid, int nritems) { struct btrfs_fs_info *fs_info = trans->fs_info; int data_copy_size; int rt_data_off; int i; int ret; struct btrfs_disk_key disk_key; nritems = nritems - mid; btrfs_set_header_nritems(right, nritems); data_copy_size = btrfs_item_data_end(l, mid) - leaf_data_end(l); copy_leaf_items(right, l, 0, mid, nritems); copy_leaf_data(right, l, BTRFS_LEAF_DATA_SIZE(fs_info) - data_copy_size, leaf_data_end(l), data_copy_size); rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_data_end(l, mid); for (i = 0; i < nritems; i++) { u32 ioff; ioff = btrfs_item_offset(right, i); btrfs_set_item_offset(right, i, ioff + rt_data_off); } btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); if (ret < 0) return ret; btrfs_mark_buffer_dirty(trans, right); btrfs_mark_buffer_dirty(trans, l); BUG_ON(path->slots[0] != slot); if (mid <= slot) { btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] -= mid; path->slots[1] += 1; } else { btrfs_tree_unlock(right); free_extent_buffer(right); } BUG_ON(path->slots[0] < 0); return 0; } /* * double splits happen when we need to insert a big item in the middle * of a leaf. A double split can leave us with 3 mostly empty leaves: * leaf: [ slots 0 - N] [ our target ] [ N + 1 - total in leaf ] * A B C * * We avoid this by trying to push the items on either side of our target * into the adjacent leaves. If all goes well we can avoid the double split * completely. */ static noinline int push_for_double_split(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int data_size) { int ret; int progress = 0; int slot; u32 nritems; int space_needed = data_size; slot = path->slots[0]; if (slot < btrfs_header_nritems(path->nodes[0])) space_needed -= btrfs_leaf_free_space(path->nodes[0]); /* * try to push all the items after our slot into the * right leaf */ ret = push_leaf_right(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; if (ret == 0) progress++; nritems = btrfs_header_nritems(path->nodes[0]); /* * our goal is to get our slot at the start or end of a leaf. If * we've done so we're done */ if (path->slots[0] == 0 || path->slots[0] == nritems) return 0; if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; /* try to push all the items before our slot into the next leaf */ slot = path->slots[0]; space_needed = data_size; if (slot > 0) space_needed -= btrfs_leaf_free_space(path->nodes[0]); ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot); if (ret < 0) return ret; if (ret == 0) progress++; if (progress) return 0; return 1; } /* * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. * * returns 0 if all went well and < 0 on failure. */ static noinline int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *ins_key, struct btrfs_path *path, int data_size, bool extend) { struct btrfs_disk_key disk_key; struct extent_buffer *l; u32 nritems; int mid; int slot; struct extent_buffer *right; struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; int wret; int split; int num_doubles = 0; int tried_avoid_double = 0; l = path->nodes[0]; slot = path->slots[0]; if (extend && data_size + btrfs_item_size(l, slot) + sizeof(struct btrfs_item) > BTRFS_LEAF_DATA_SIZE(fs_info)) return -EOVERFLOW; /* first try to make some room by pushing left and right */ if (data_size && path->nodes[1]) { int space_needed = data_size; if (slot < btrfs_header_nritems(l)) space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_right(trans, root, path, space_needed, space_needed, 0, 0); if (wret < 0) return wret; if (wret) { space_needed = data_size; if (slot > 0) space_needed -= btrfs_leaf_free_space(l); wret = push_leaf_left(trans, root, path, space_needed, space_needed, 0, (u32)-1); if (wret < 0) return wret; } l = path->nodes[0]; /* did the pushes work? */ if (btrfs_leaf_free_space(l) >= data_size) return 0; } if (!path->nodes[1]) { ret = insert_new_root(trans, root, path, 1); if (ret) return ret; } again: split = 1; l = path->nodes[0]; slot = path->slots[0]; nritems = btrfs_header_nritems(l); mid = (nritems + 1) / 2; if (mid <= slot) { if (nritems == 1 || leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (slot >= nritems) { split = 0; } else { mid = slot; if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (data_size && !tried_avoid_double) goto push_for_double; split = 2; } } } } else { if (leaf_space_used(l, 0, mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (!extend && data_size && slot == 0) { split = 0; } else if ((extend || !data_size) && slot == 0) { mid = 1; } else { mid = slot; if (mid != nritems && leaf_space_used(l, mid, nritems - mid) + data_size > BTRFS_LEAF_DATA_SIZE(fs_info)) { if (data_size && !tried_avoid_double) goto push_for_double; split = 2; } } } } if (split == 0) btrfs_cpu_key_to_disk(&disk_key, ins_key); else btrfs_item_key(l, &disk_key, mid); /* * We have to about BTRFS_NESTING_NEW_ROOT here if we've done a double * split, because we're only allowed to have MAX_LOCKDEP_SUBCLASSES * subclasses, which is 8 at the time of this patch, and we've maxed it * out. In the future we could add a * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just * use BTRFS_NESTING_NEW_ROOT. */ right = btrfs_alloc_tree_block(trans, root, 0, btrfs_root_id(root), &disk_key, 0, l->start, 0, 0, num_doubles ? BTRFS_NESTING_NEW_ROOT : BTRFS_NESTING_SPLIT); if (IS_ERR(right)) return PTR_ERR(right); root_add_used_bytes(root); if (split == 0) { if (mid <= slot) { btrfs_set_header_nritems(right, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] = 0; path->slots[1] += 1; } else { btrfs_set_header_nritems(right, 0); ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1], 1); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; path->slots[0] = 0; if (path->slots[1] == 0) fixup_low_keys(trans, path, &disk_key, 1); } /* * We create a new leaf 'right' for the required ins_len and * we'll do btrfs_mark_buffer_dirty() on this leaf after copying * the content of ins_len to 'right'. */ return ret; } ret = copy_for_split(trans, path, l, right, slot, mid, nritems); if (ret < 0) { btrfs_tree_unlock(right); free_extent_buffer(right); return ret; } if (split == 2) { BUG_ON(num_doubles != 0); num_doubles++; goto again; } return 0; push_for_double: push_for_double_split(trans, root, path, data_size); tried_avoid_double = 1; if (btrfs_leaf_free_space(path->nodes[0]) >= data_size) return 0; goto again; } static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int ins_len) { struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_file_extent_item *fi; u64 extent_len = 0; u32 item_size; int ret; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY && key.type != BTRFS_RAID_STRIPE_KEY && key.type != BTRFS_EXTENT_CSUM_KEY); if (btrfs_leaf_free_space(leaf) >= ins_len) return 0; item_size = btrfs_item_size(leaf, path->slots[0]); if (key.type == BTRFS_EXTENT_DATA_KEY) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); extent_len = btrfs_file_extent_num_bytes(leaf, fi); } btrfs_release_path(path); path->keep_locks = 1; path->search_for_split = 1; ret = btrfs_search_slot(trans, root, &key, path, 0, 1); path->search_for_split = 0; if (ret > 0) ret = -EAGAIN; if (ret < 0) goto err; ret = -EAGAIN; leaf = path->nodes[0]; /* if our item isn't there, return now */ if (item_size != btrfs_item_size(leaf, path->slots[0])) goto err; /* the leaf has changed, it now has room. return now */ if (btrfs_leaf_free_space(path->nodes[0]) >= ins_len) goto err; if (key.type == BTRFS_EXTENT_DATA_KEY) { fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); if (extent_len != btrfs_file_extent_num_bytes(leaf, fi)) goto err; } ret = split_leaf(trans, root, &key, path, ins_len, 1); if (ret) goto err; path->keep_locks = 0; btrfs_unlock_up_safe(path, 1); return 0; err: path->keep_locks = 0; return ret; } static noinline int split_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { struct extent_buffer *leaf; int orig_slot, slot; char *buf; u32 nritems; u32 item_size; u32 orig_offset; struct btrfs_disk_key disk_key; leaf = path->nodes[0]; /* * Shouldn't happen because the caller must have previously called * setup_leaf_for_split() to make room for the new item in the leaf. */ if (WARN_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item))) return -ENOSPC; orig_slot = path->slots[0]; orig_offset = btrfs_item_offset(leaf, path->slots[0]); item_size = btrfs_item_size(leaf, path->slots[0]); buf = kmalloc(item_size, GFP_NOFS); if (!buf) return -ENOMEM; read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, path->slots[0]), item_size); slot = path->slots[0] + 1; nritems = btrfs_header_nritems(leaf); if (slot != nritems) { /* shift the items */ memmove_leaf_items(leaf, slot + 1, slot, nritems - slot); } btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(leaf, &disk_key, slot); btrfs_set_item_offset(leaf, slot, orig_offset); btrfs_set_item_size(leaf, slot, item_size - split_offset); btrfs_set_item_offset(leaf, orig_slot, orig_offset + item_size - split_offset); btrfs_set_item_size(leaf, orig_slot, split_offset); btrfs_set_header_nritems(leaf, nritems + 1); /* write the data for the start of the original item */ write_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, path->slots[0]), split_offset); /* write the data for the new item */ write_extent_buffer(leaf, buf + split_offset, btrfs_item_ptr_offset(leaf, slot), item_size - split_offset); btrfs_mark_buffer_dirty(trans, leaf); BUG_ON(btrfs_leaf_free_space(leaf) < 0); kfree(buf); return 0; } /* * This function splits a single item into two items, * giving 'new_key' to the new item and splitting the * old one at split_offset (from the start of the item). * * The path may be released by this operation. After * the split, the path is pointing to the old item. The * new item is going to be in the same node as the old one. * * Note, the item being split must be smaller enough to live alone on * a tree block with room for one extra struct btrfs_item * * This allows us to split the item in place, keeping a lock on the * leaf the entire time. */ int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { int ret; ret = setup_leaf_for_split(trans, root, path, sizeof(struct btrfs_item)); if (ret) return ret; ret = split_item(trans, path, new_key, split_offset); return ret; } /* * make the item pointed to by the path smaller. new_size indicates * how small to make it, and from_end tells us if we just chop bytes * off the end of the item or if we shift the item to chop bytes off * the front. */ void btrfs_truncate_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 new_size, int from_end) { int slot; struct extent_buffer *leaf; u32 nritems; unsigned int data_end; unsigned int old_data_start; unsigned int old_size; unsigned int size_diff; int i; leaf = path->nodes[0]; slot = path->slots[0]; old_size = btrfs_item_size(leaf, slot); if (old_size == new_size) return; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); old_data_start = btrfs_item_offset(leaf, slot); size_diff = old_size - new_size; BUG_ON(slot < 0); BUG_ON(slot >= nritems); /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_item_offset(leaf, i); btrfs_set_item_offset(leaf, i, ioff + size_diff); } /* shift the data */ if (from_end) { memmove_leaf_data(leaf, data_end + size_diff, data_end, old_data_start + new_size - data_end); } else { struct btrfs_disk_key disk_key; u64 offset; btrfs_item_key(leaf, &disk_key, slot); if (btrfs_disk_key_type(&disk_key) == BTRFS_EXTENT_DATA_KEY) { unsigned long ptr; struct btrfs_file_extent_item *fi; fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); fi = (struct btrfs_file_extent_item *)( (unsigned long)fi - size_diff); if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { ptr = btrfs_item_ptr_offset(leaf, slot); memmove_extent_buffer(leaf, ptr, (unsigned long)fi, BTRFS_FILE_EXTENT_INLINE_DATA_START); } } memmove_leaf_data(leaf, data_end + size_diff, data_end, old_data_start - data_end); offset = btrfs_disk_key_offset(&disk_key); btrfs_set_disk_key_offset(&disk_key, offset + size_diff); btrfs_set_item_key(leaf, &disk_key, slot); if (slot == 0) fixup_low_keys(trans, path, &disk_key, 1); } btrfs_set_item_size(leaf, slot, new_size); btrfs_mark_buffer_dirty(trans, leaf); if (unlikely(btrfs_leaf_free_space(leaf) < 0)) { btrfs_print_leaf(leaf); BUG(); } } /* * make the item pointed to by the path bigger, data_size is the added size. */ void btrfs_extend_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 data_size) { int slot; struct extent_buffer *leaf; u32 nritems; unsigned int data_end; unsigned int old_data; unsigned int old_size; int i; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); if (btrfs_leaf_free_space(leaf) < data_size) { btrfs_print_leaf(leaf); BUG(); } slot = path->slots[0]; old_data = btrfs_item_data_end(leaf, slot); BUG_ON(slot < 0); if (unlikely(slot >= nritems)) { btrfs_print_leaf(leaf); btrfs_crit(leaf->fs_info, "slot %d too large, nritems %d", slot, nritems); BUG(); } /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_item_offset(leaf, i); btrfs_set_item_offset(leaf, i, ioff - data_size); } /* shift the data */ memmove_leaf_data(leaf, data_end - data_size, data_end, old_data - data_end); data_end = old_data; old_size = btrfs_item_size(leaf, slot); btrfs_set_item_size(leaf, slot, old_size + data_size); btrfs_mark_buffer_dirty(trans, leaf); if (unlikely(btrfs_leaf_free_space(leaf) < 0)) { btrfs_print_leaf(leaf); BUG(); } } /* * Make space in the node before inserting one or more items. * * @trans: transaction handle * @root: root we are inserting items to * @path: points to the leaf/slot where we are going to insert new items * @batch: information about the batch of items to insert * * Main purpose is to save stack depth by doing the bulk of the work in a * function that doesn't call btrfs_search_slot */ static void setup_items_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch) { struct btrfs_fs_info *fs_info = root->fs_info; int i; u32 nritems; unsigned int data_end; struct btrfs_disk_key disk_key; struct extent_buffer *leaf; int slot; u32 total_size; /* * Before anything else, update keys in the parent and other ancestors * if needed, then release the write locks on them, so that other tasks * can use them while we modify the leaf. */ if (path->slots[0] == 0) { btrfs_cpu_key_to_disk(&disk_key, &batch->keys[0]); fixup_low_keys(trans, path, &disk_key, 1); } btrfs_unlock_up_safe(path, 1); leaf = path->nodes[0]; slot = path->slots[0]; nritems = btrfs_header_nritems(leaf); data_end = leaf_data_end(leaf); total_size = batch->total_data_size + (batch->nr * sizeof(struct btrfs_item)); if (unlikely(btrfs_leaf_free_space(leaf) < total_size)) { btrfs_print_leaf(leaf); btrfs_crit(fs_info, "not enough freespace need %u have %d", total_size, btrfs_leaf_free_space(leaf)); BUG(); } if (slot != nritems) { unsigned int old_data = btrfs_item_data_end(leaf, slot); if (unlikely(old_data < data_end)) { btrfs_print_leaf(leaf); btrfs_crit(fs_info, "item at slot %d with data offset %u beyond data end of leaf %u", slot, old_data, data_end); BUG(); } /* * item0..itemN ... dataN.offset..dataN.size .. data0.size */ /* first correct the data pointers */ for (i = slot; i < nritems; i++) { u32 ioff; ioff = btrfs_item_offset(leaf, i); btrfs_set_item_offset(leaf, i, ioff - batch->total_data_size); } /* shift the items */ memmove_leaf_items(leaf, slot + batch->nr, slot, nritems - slot); /* shift the data */ memmove_leaf_data(leaf, data_end - batch->total_data_size, data_end, old_data - data_end); data_end = old_data; } /* setup the item for the new data */ for (i = 0; i < batch->nr; i++) { btrfs_cpu_key_to_disk(&disk_key, &batch->keys[i]); btrfs_set_item_key(leaf, &disk_key, slot + i); data_end -= batch->data_sizes[i]; btrfs_set_item_offset(leaf, slot + i, data_end); btrfs_set_item_size(leaf, slot + i, batch->data_sizes[i]); } btrfs_set_header_nritems(leaf, nritems + batch->nr); btrfs_mark_buffer_dirty(trans, leaf); if (unlikely(btrfs_leaf_free_space(leaf) < 0)) { btrfs_print_leaf(leaf); BUG(); } } /* * Insert a new item into a leaf. * * @trans: Transaction handle. * @root: The root of the btree. * @path: A path pointing to the target leaf and slot. * @key: The key of the new item. * @data_size: The size of the data associated with the new key. */ void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size) { struct btrfs_item_batch batch; batch.keys = key; batch.data_sizes = &data_size; batch.total_data_size = data_size; batch.nr = 1; setup_items_for_insert(trans, root, path, &batch); } /* * Given a key and some data, insert items into the tree. * This does all the path init required, making room in the tree if needed. * * Returns: 0 on success * -EEXIST if the first key already exists * < 0 on other errors */ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch) { int ret = 0; int slot; u32 total_size; total_size = batch->total_data_size + (batch->nr * sizeof(struct btrfs_item)); ret = btrfs_search_slot(trans, root, &batch->keys[0], path, total_size, 1); if (ret == 0) return -EEXIST; if (ret < 0) return ret; slot = path->slots[0]; BUG_ON(slot < 0); setup_items_for_insert(trans, root, path, batch); return 0; } /* * Given a key and some data, insert an item into the tree. * This does all the path init required, making room in the tree if needed. */ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *cpu_key, void *data, u32 data_size) { int ret = 0; BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *leaf; unsigned long ptr; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_insert_empty_item(trans, root, path, cpu_key, data_size); if (!ret) { leaf = path->nodes[0]; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, data, ptr, data_size); btrfs_mark_buffer_dirty(trans, leaf); } return ret; } /* * This function duplicates an item, giving 'new_key' to the new item. * It guarantees both items live in the same tree leaf and the new item is * contiguous with the original item. * * This allows us to split a file extent in place, keeping a lock on the leaf * the entire time. */ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key) { struct extent_buffer *leaf; int ret; u32 item_size; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); ret = setup_leaf_for_split(trans, root, path, item_size + sizeof(struct btrfs_item)); if (ret) return ret; path->slots[0]++; btrfs_setup_item_for_insert(trans, root, path, new_key, item_size); leaf = path->nodes[0]; memcpy_extent_buffer(leaf, btrfs_item_ptr_offset(leaf, path->slots[0]), btrfs_item_ptr_offset(leaf, path->slots[0] - 1), item_size); return 0; } /* * delete the pointer from a given node. * * the tree should have been previously balanced so the deletion does not * empty a node. * * This is exported for use inside btrfs-progs, don't un-export it. */ int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot) { struct extent_buffer *parent = path->nodes[level]; u32 nritems; int ret; nritems = btrfs_header_nritems(parent); if (slot != nritems - 1) { if (level) { ret = btrfs_tree_mod_log_insert_move(parent, slot, slot + 1, nritems - slot - 1); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } } memmove_extent_buffer(parent, btrfs_node_key_ptr_offset(parent, slot), btrfs_node_key_ptr_offset(parent, slot + 1), sizeof(struct btrfs_key_ptr) * (nritems - slot - 1)); } else if (level) { ret = btrfs_tree_mod_log_insert_key(parent, slot, BTRFS_MOD_LOG_KEY_REMOVE); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); return ret; } } nritems--; btrfs_set_header_nritems(parent, nritems); if (nritems == 0 && parent == root->node) { BUG_ON(btrfs_header_level(root->node) != 1); /* just turn the root into a leaf and break */ btrfs_set_header_level(root->node, 0); } else if (slot == 0) { struct btrfs_disk_key disk_key; btrfs_node_key(parent, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, level + 1); } btrfs_mark_buffer_dirty(trans, parent); return 0; } /* * a helper function to delete the leaf pointed to by path->slots[1] and * path->nodes[1]. * * This deletes the pointer in path->nodes[1] and frees the leaf * block extent. zero is returned if it all worked out, < 0 otherwise. * * The path must have already been setup for deleting the leaf, including * all the proper balancing. path->nodes[1] must be locked. */ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *leaf) { int ret; WARN_ON(btrfs_header_generation(leaf) != trans->transid); ret = btrfs_del_ptr(trans, root, path, 1, path->slots[1]); if (ret < 0) return ret; /* * btrfs_free_extent is expensive, we want to make sure we * aren't holding any locks when we call it */ btrfs_unlock_up_safe(path, 0); root_sub_used_bytes(root); refcount_inc(&leaf->refs); ret = btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); if (ret < 0) btrfs_abort_transaction(trans, ret); return ret; } /* * delete the item at the leaf level in path. If that empties * the leaf, remove it from the tree */ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int slot, int nr) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; int ret = 0; int wret; u32 nritems; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (slot + nr != nritems) { const u32 last_off = btrfs_item_offset(leaf, slot + nr - 1); const int data_end = leaf_data_end(leaf); u32 dsize = 0; int i; for (i = 0; i < nr; i++) dsize += btrfs_item_size(leaf, slot + i); memmove_leaf_data(leaf, data_end + dsize, data_end, last_off - data_end); for (i = slot + nr; i < nritems; i++) { u32 ioff; ioff = btrfs_item_offset(leaf, i); btrfs_set_item_offset(leaf, i, ioff + dsize); } memmove_leaf_items(leaf, slot, slot + nr, nritems - slot - nr); } btrfs_set_header_nritems(leaf, nritems - nr); nritems -= nr; /* delete the leaf if we've emptied it */ if (nritems == 0) { if (leaf == root->node) { btrfs_set_header_level(leaf, 0); } else { btrfs_clear_buffer_dirty(trans, leaf); ret = btrfs_del_leaf(trans, root, path, leaf); if (ret < 0) return ret; } } else { int used = leaf_space_used(leaf, 0, nritems); if (slot == 0) { struct btrfs_disk_key disk_key; btrfs_item_key(leaf, &disk_key, 0); fixup_low_keys(trans, path, &disk_key, 1); } /* * Try to delete the leaf if it is mostly empty. We do this by * trying to move all its items into its left and right neighbours. * If we can't move all the items, then we don't delete it - it's * not ideal, but future insertions might fill the leaf with more * items, or items from other leaves might be moved later into our * leaf due to deletions on those leaves. */ if (used < BTRFS_LEAF_DATA_SIZE(fs_info) / 3) { u32 min_push_space; /* push_leaf_left fixes the path. * make sure the path still points to our leaf * for possible call to btrfs_del_ptr below */ slot = path->slots[1]; refcount_inc(&leaf->refs); /* * We want to be able to at least push one item to the * left neighbour leaf, and that's the first item. */ min_push_space = sizeof(struct btrfs_item) + btrfs_item_size(leaf, 0); wret = push_leaf_left(trans, root, path, 0, min_push_space, 1, (u32)-1); if (wret < 0 && wret != -ENOSPC) ret = wret; if (path->nodes[0] == leaf && btrfs_header_nritems(leaf)) { /* * If we were not able to push all items from our * leaf to its left neighbour, then attempt to * either push all the remaining items to the * right neighbour or none. There's no advantage * in pushing only some items, instead of all, as * it's pointless to end up with a leaf having * too few items while the neighbours can be full * or nearly full. */ nritems = btrfs_header_nritems(leaf); min_push_space = leaf_space_used(leaf, 0, nritems); wret = push_leaf_right(trans, root, path, 0, min_push_space, 1, 0); if (wret < 0 && wret != -ENOSPC) ret = wret; } if (btrfs_header_nritems(leaf) == 0) { path->slots[1] = slot; ret = btrfs_del_leaf(trans, root, path, leaf); if (ret < 0) return ret; free_extent_buffer(leaf); ret = 0; } else { /* if we're still in the path, make sure * we're dirty. Otherwise, one of the * push_leaf functions must have already * dirtied this buffer */ if (path->nodes[0] == leaf) btrfs_mark_buffer_dirty(trans, leaf); free_extent_buffer(leaf); } } else { btrfs_mark_buffer_dirty(trans, leaf); } } return ret; } /* * A helper function to walk down the tree starting at min_key, and looking * for leaves that have a minimum transaction id. * This is used by the btree defrag code, and tree logging * * This does not cow, but it does stuff the starting key it finds back * into min_key, so you can call btrfs_search_slot with cow=1 on the * key and get a writable path. * * min_trans indicates the oldest transaction that you are interested * in walking through. Any nodes or leaves older than min_trans are * skipped over (without reading them). * * returns zero if something useful was found, < 0 on error and 1 if there * was nothing in the tree that matched the search criteria. */ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key, struct btrfs_path *path, u64 min_trans) { struct extent_buffer *cur; int slot; int sret; u32 nritems; int level; int ret = 1; int keep_locks = path->keep_locks; ASSERT(!path->nowait); ASSERT(path->lowest_level == 0); path->keep_locks = 1; again: cur = btrfs_read_lock_root_node(root); level = btrfs_header_level(cur); WARN_ON(path->nodes[level]); path->nodes[level] = cur; path->locks[level] = BTRFS_READ_LOCK; if (btrfs_header_generation(cur) < min_trans) { ret = 1; goto out; } while (1) { nritems = btrfs_header_nritems(cur); level = btrfs_header_level(cur); sret = btrfs_bin_search(cur, 0, min_key, &slot); if (sret < 0) { ret = sret; goto out; } /* At level 0 we're done, setup the path and exit. */ if (level == 0) { if (slot >= nritems) goto find_next_key; ret = 0; path->slots[level] = slot; /* Save our key for returning back. */ btrfs_item_key_to_cpu(cur, min_key, slot); goto out; } if (sret && slot > 0) slot--; /* * check this node pointer against the min_trans parameters. * If it is too old, skip to the next one. */ while (slot < nritems) { u64 gen; gen = btrfs_node_ptr_generation(cur, slot); if (gen < min_trans) { slot++; continue; } break; } find_next_key: /* * we didn't find a candidate key in this node, walk forward * and find another one */ path->slots[level] = slot; if (slot >= nritems) { sret = btrfs_find_next_key(root, path, min_key, level, min_trans); if (sret == 0) { btrfs_release_path(path); goto again; } else { goto out; } } cur = btrfs_read_node_slot(cur, slot); if (IS_ERR(cur)) { ret = PTR_ERR(cur); goto out; } btrfs_tree_read_lock(cur); path->locks[level - 1] = BTRFS_READ_LOCK; path->nodes[level - 1] = cur; unlock_up(path, level, 1, 0, NULL); } out: path->keep_locks = keep_locks; if (ret == 0) btrfs_unlock_up_safe(path, 1); return ret; } /* * this is similar to btrfs_next_leaf, but does not try to preserve * and fixup the path. It looks for and returns the next key in the * tree based on the current path and the min_trans parameters. * * 0 is returned if another key is found, < 0 if there are any errors * and 1 is returned if there are no higher keys in the tree * * path->keep_locks should be set to 1 on the search made before * calling this function. */ int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *key, int level, u64 min_trans) { int slot; struct extent_buffer *c; WARN_ON(!path->keep_locks && !path->skip_locking); while (level < BTRFS_MAX_LEVEL) { if (!path->nodes[level]) return 1; slot = path->slots[level] + 1; c = path->nodes[level]; next: if (slot >= btrfs_header_nritems(c)) { int ret; int orig_lowest; struct btrfs_key cur_key; if (level + 1 >= BTRFS_MAX_LEVEL || !path->nodes[level + 1]) return 1; if (path->locks[level + 1] || path->skip_locking) { level++; continue; } slot = btrfs_header_nritems(c) - 1; if (level == 0) btrfs_item_key_to_cpu(c, &cur_key, slot); else btrfs_node_key_to_cpu(c, &cur_key, slot); orig_lowest = path->lowest_level; btrfs_release_path(path); path->lowest_level = level; ret = btrfs_search_slot(NULL, root, &cur_key, path, 0, 0); path->lowest_level = orig_lowest; if (ret < 0) return ret; c = path->nodes[level]; slot = path->slots[level]; if (ret == 0) slot++; goto next; } if (level == 0) btrfs_item_key_to_cpu(c, key, slot); else { u64 gen = btrfs_node_ptr_generation(c, slot); if (gen < min_trans) { slot++; goto next; } btrfs_node_key_to_cpu(c, key, slot); } return 0; } return 1; } int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq) { int slot; int level; struct extent_buffer *c; struct extent_buffer *next; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; bool need_commit_sem = false; u32 nritems; int ret; int i; /* * The nowait semantics are used only for write paths, where we don't * use the tree mod log and sequence numbers. */ if (time_seq) ASSERT(!path->nowait); nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) return 1; btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1); again: level = 1; next = NULL; btrfs_release_path(path); path->keep_locks = 1; if (time_seq) { ret = btrfs_search_old_slot(root, &key, path, time_seq); } else { if (path->need_commit_sem) { path->need_commit_sem = 0; need_commit_sem = true; if (path->nowait) { if (!down_read_trylock(&fs_info->commit_root_sem)) { ret = -EAGAIN; goto done; } } else { down_read(&fs_info->commit_root_sem); } } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); } path->keep_locks = 0; if (ret < 0) goto done; nritems = btrfs_header_nritems(path->nodes[0]); /* * by releasing the path above we dropped all our locks. A balance * could have added more items next to the key that used to be * at the very end of the block. So, check again here and * advance the path if there are now more items available. */ if (nritems > 0 && path->slots[0] < nritems - 1) { if (ret == 0) path->slots[0]++; ret = 0; goto done; } /* * So the above check misses one case: * - after releasing the path above, someone has removed the item that * used to be at the very end of the block, and balance between leafs * gets another one with bigger key.offset to replace it. * * This one should be returned as well, or we can get leaf corruption * later(esp. in __btrfs_drop_extents()). * * And a bit more explanation about this check, * with ret > 0, the key isn't found, the path points to the slot * where it should be inserted, so the path->slots[0] item must be the * bigger one. */ if (nritems > 0 && ret > 0 && path->slots[0] == nritems - 1) { ret = 0; goto done; } while (level < BTRFS_MAX_LEVEL) { if (!path->nodes[level]) { ret = 1; goto done; } slot = path->slots[level] + 1; c = path->nodes[level]; if (slot >= btrfs_header_nritems(c)) { level++; if (level == BTRFS_MAX_LEVEL) { ret = 1; goto done; } continue; } /* * Our current level is where we're going to start from, and to * make sure lockdep doesn't complain we need to drop our locks * and nodes from 0 to our current level. */ for (i = 0; i < level; i++) { if (path->locks[level]) { btrfs_tree_read_unlock(path->nodes[i]); path->locks[i] = 0; } free_extent_buffer(path->nodes[i]); path->nodes[i] = NULL; } next = c; ret = read_block_for_search(root, path, &next, slot, &key); if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { btrfs_release_path(path); goto done; } if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); if (!ret && path->nowait) { ret = -EAGAIN; goto done; } if (!ret && time_seq) { /* * If we don't get the lock, we may be racing * with push_leaf_left, holding that lock while * itself waiting for the leaf we've currently * locked. To solve this situation, we give up * on our lock and cycle. */ free_extent_buffer(next); btrfs_release_path(path); cond_resched(); goto again; } if (!ret) btrfs_tree_read_lock(next); } break; } path->slots[level] = slot; while (1) { level--; path->nodes[level] = next; path->slots[level] = 0; if (!path->skip_locking) path->locks[level] = BTRFS_READ_LOCK; if (!level) break; ret = read_block_for_search(root, path, &next, 0, &key); if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { btrfs_release_path(path); goto done; } if (!path->skip_locking) { if (path->nowait) { if (!btrfs_try_tree_read_lock(next)) { ret = -EAGAIN; goto done; } } else { btrfs_tree_read_lock(next); } } } ret = 0; done: unlock_up(path, 0, 1, 0, NULL); if (need_commit_sem) { int ret2; path->need_commit_sem = 1; ret2 = finish_need_commit_sem_search(path); up_read(&fs_info->commit_root_sem); if (ret2) ret = ret2; } return ret; } int btrfs_next_old_item(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq) { path->slots[0]++; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) return btrfs_next_old_leaf(root, path, time_seq); return 0; } /* * this uses btrfs_prev_leaf to walk backwards in the tree, and keeps * searching until it gets past min_objectid or finds an item of 'type' * * returns 0 if something is found, 1 if nothing was found and < 0 on error */ int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, int type) { struct btrfs_key found_key; struct extent_buffer *leaf; u32 nritems; int ret; while (1) { if (path->slots[0] == 0) { ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; } else { path->slots[0]--; } leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (nritems == 0) return 1; if (path->slots[0] == nritems) path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid < min_objectid) break; if (found_key.type == type) return 0; if (found_key.objectid == min_objectid && found_key.type < type) break; } return 1; } /* * search in extent tree to find a previous Metadata/Data extent item with * min objecitd. * * returns 0 if something is found, 1 if nothing was found and < 0 on error */ int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid) { struct btrfs_key found_key; struct extent_buffer *leaf; u32 nritems; int ret; while (1) { if (path->slots[0] == 0) { ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; } else { path->slots[0]--; } leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); if (nritems == 0) return 1; if (path->slots[0] == nritems) path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid < min_objectid) break; if (found_key.type == BTRFS_EXTENT_ITEM_KEY || found_key.type == BTRFS_METADATA_ITEM_KEY) return 0; if (found_key.objectid == min_objectid && found_key.type < BTRFS_EXTENT_ITEM_KEY) break; } return 1; } int __init btrfs_ctree_init(void) { btrfs_path_cachep = KMEM_CACHE(btrfs_path, 0); if (!btrfs_path_cachep) return -ENOMEM; return 0; } void __cold btrfs_ctree_exit(void) { kmem_cache_destroy(btrfs_path_cachep); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_usage srcuu; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_register_unique_prio( struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register_unique_prio( struct blocking_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ |
| 2 2 2 1 1 1 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vhost transport for vsock * * Copyright (C) 2013-2015 Red Hat, Inc. * Author: Asias He <asias@redhat.com> * Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/miscdevice.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <net/sock.h> #include <linux/virtio_vsock.h> #include <linux/vhost.h> #include <linux/hashtable.h> #include <net/af_vsock.h> #include "vhost.h" #define VHOST_VSOCK_DEFAULT_HOST_CID 2 /* Max number of bytes transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others. */ #define VHOST_VSOCK_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others with * small pkts. */ #define VHOST_VSOCK_PKT_WEIGHT 256 enum { VHOST_VSOCK_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_VSOCK_F_SEQPACKET) }; enum { VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) }; /* Used to track all the vhost_vsock instances on the system. */ static DEFINE_MUTEX(vhost_vsock_mutex); static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8); struct vhost_vsock { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; /* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */ struct hlist_node hash; struct vhost_work send_pkt_work; struct sk_buff_head send_pkt_queue; /* host->guest pending packets */ atomic_t queued_replies; u32 guest_cid; bool seqpacket_allow; }; static u32 vhost_transport_get_local_cid(void) { return VHOST_VSOCK_DEFAULT_HOST_CID; } /* Callers that dereference the return value must hold vhost_vsock_mutex or the * RCU read lock. */ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) { struct vhost_vsock *vsock; hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) { u32 other_cid = vsock->guest_cid; /* Skip instances that have no CID yet */ if (other_cid == 0) continue; if (other_cid == guest_cid) return vsock; } return NULL; } static void vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct vhost_virtqueue *vq) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int pkts = 0, total_len = 0; bool added = false; bool restart_tx = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; /* Avoid further vmexits, we're already processing the virtqueue */ vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; size_t iov_len, payload_len; struct iov_iter iov_iter; u32 flags_to_restore = 0; struct sk_buff *skb; unsigned out, in; size_t nbytes; u32 offset; int head; skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); if (!skb) { vhost_enable_notify(&vsock->dev, vq); break; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } if (head == vq->num) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); /* We cannot finish yet if more buffers snuck in while * re-enabling notify. */ if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } if (out) { kfree_skb(skb); vq_err(vq, "Expected 0 output buffers, got %u\n", out); break; } iov_len = iov_length(&vq->iov[out], in); if (iov_len < sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Buffer len [%zu] too small\n", iov_len); break; } iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len); offset = VIRTIO_VSOCK_SKB_CB(skb)->offset; payload_len = skb->len - offset; hdr = virtio_vsock_hdr(skb); /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ if (payload_len > iov_len - sizeof(*hdr)) { payload_len = iov_len - sizeof(*hdr); /* As we are copying pieces of large packet's buffer to * small rx buffers, headers of packets in rx queue are * created dynamically and are initialized with header * of current packet(except length). But in case of * SOCK_SEQPACKET, we also must clear message delimeter * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise, * there will be sequence of packets with these * bits set. After initialized header will be copied to * rx buffer, these required bits will be restored. */ if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR; } } } /* Set the correct length in the header */ hdr->len = cpu_to_le32(payload_len); nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt hdr\n"); break; } if (skb_copy_datagram_iter(skb, offset, &iov_iter, payload_len)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt buf\n"); break; } /* Deliver to monitoring devices all packets that we * will transmit. */ virtio_transport_deliver_tap_pkt(skb); vhost_add_used(vq, head, sizeof(*hdr) + payload_len); added = true; VIRTIO_VSOCK_SKB_CB(skb)->offset += payload_len; total_len += payload_len; /* If we didn't send all the payload we can requeue the packet * to send it with the next available buffer. */ if (VIRTIO_VSOCK_SKB_CB(skb)->offset < skb->len) { hdr->flags |= cpu_to_le32(flags_to_restore); /* We are queueing the same skb to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. */ virtio_vsock_skb_clear_tap_delivered(skb); virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); } else { if (virtio_vsock_skb_reply(skb)) { int val; val = atomic_dec_return(&vsock->queued_replies); /* Do we have resources to resume tx * processing? */ if (val + 1 == tx_vq->num) restart_tx = true; } virtio_transport_consume_skb_sent(skb, true); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); if (restart_tx) vhost_poll_queue(&tx_vq->poll); } static void vhost_transport_send_pkt_work(struct vhost_work *work) { struct vhost_virtqueue *vq; struct vhost_vsock *vsock; vsock = container_of(work, struct vhost_vsock, send_pkt_work); vq = &vsock->vqs[VSOCK_VQ_RX]; vhost_transport_do_send_pkt(vsock, vq); } static int vhost_transport_send_pkt(struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vhost_vsock *vsock; int len = skb->len; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid)); if (!vsock) { rcu_read_unlock(); kfree_skb(skb); return -ENODEV; } if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); rcu_read_unlock(); return len; } static int vhost_transport_cancel_pkt(struct vsock_sock *vsk) { struct vhost_vsock *vsock; int cnt = 0; int ret = -ENODEV; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid); if (!vsock) goto out; cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int new_cnt; new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num) vhost_poll_queue(&tx_vq->poll); } ret = 0; out: rcu_read_unlock(); return ret; } static struct sk_buff * vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, unsigned int out, unsigned int in) { struct virtio_vsock_hdr *hdr; struct iov_iter iov_iter; struct sk_buff *skb; size_t payload_len; size_t nbytes; size_t len; if (in != 0) { vq_err(vq, "Expected 0 input buffers, got %u\n", in); return NULL; } len = iov_length(vq->iov, out); if (len < VIRTIO_VSOCK_SKB_HEADROOM || len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM) return NULL; /* len contains both payload and hdr */ skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); if (!skb) return NULL; iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len); hdr = virtio_vsock_hdr(skb); nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n", sizeof(*hdr), nbytes); kfree_skb(skb); return NULL; } payload_len = le32_to_cpu(hdr->len); /* No payload */ if (!payload_len) return skb; /* The pkt is too big or the length in the header is invalid */ if (payload_len + sizeof(*hdr) > len) { kfree_skb(skb); return NULL; } virtio_vsock_skb_put(skb, payload_len); if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) { vq_err(vq, "Failed to copy %zu byte payload\n", payload_len); kfree_skb(skb); return NULL; } return skb; } /* Is there space left for replies to rx packets? */ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq = &vsock->vqs[VSOCK_VQ_TX]; int val; smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ val = atomic_read(&vsock->queued_replies); return val < vq->num; } static bool vhost_transport_msgzerocopy_allow(void) { return true; } static bool vhost_transport_seqpacket_allow(u32 remote_cid); static struct virtio_transport vhost_transport = { .transport = { .module = THIS_MODULE, .get_local_cid = vhost_transport_get_local_cid, .init = virtio_transport_do_socket_init, .destruct = virtio_transport_destruct, .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, .cancel_pkt = vhost_transport_cancel_pkt, .dgram_enqueue = virtio_transport_dgram_enqueue, .dgram_dequeue = virtio_transport_dgram_dequeue, .dgram_bind = virtio_transport_dgram_bind, .dgram_allow = virtio_transport_dgram_allow, .stream_enqueue = virtio_transport_stream_enqueue, .stream_dequeue = virtio_transport_stream_dequeue, .stream_has_data = virtio_transport_stream_has_data, .stream_has_space = virtio_transport_stream_has_space, .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, .seqpacket_allow = vhost_transport_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, .msgzerocopy_allow = vhost_transport_msgzerocopy_allow, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, .notify_send_init = virtio_transport_notify_send_init, .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .unsent_bytes = virtio_transport_unsent_bytes, .read_skb = virtio_transport_read_skb, }, .send_pkt = vhost_transport_send_pkt, }; static bool vhost_transport_seqpacket_allow(u32 remote_cid) { struct vhost_vsock *vsock; bool seqpacket_allow = false; rcu_read_lock(); vsock = vhost_vsock_get(remote_cid); if (vsock) seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; } static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); int head, pkts = 0, total_len = 0; unsigned int out, in; struct sk_buff *skb; bool added = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue * callbacks disabled. */ goto no_more_replies; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) break; if (head == vq->num) { if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } skb = vhost_vsock_alloc_skb(vq, out, in); if (!skb) { vq_err(vq, "Faulted on pkt\n"); continue; } total_len += sizeof(*hdr) + skb->len; /* Deliver to monitoring devices all received packets */ virtio_transport_deliver_tap_pkt(skb); hdr = virtio_vsock_hdr(skb); /* Only accept correctly addressed packets */ if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid && le64_to_cpu(hdr->dst_cid) == vhost_transport_get_local_cid()) virtio_transport_recv_pkt(&vhost_transport, skb); else kfree_skb(skb); vhost_add_used(vq, head, 0); added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); no_more_replies: if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); } static void vhost_vsock_handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); vhost_transport_do_send_pkt(vsock, vq); } static int vhost_vsock_start(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq; size_t i; int ret; mutex_lock(&vsock->dev.mutex); ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); if (!vhost_vq_access_ok(vq)) { ret = -EFAULT; goto err_vq; } if (!vhost_vq_get_backend(vq)) { vhost_vq_set_backend(vq, vsock); ret = vhost_vq_init_access(vq); if (ret) goto err_vq; } mutex_unlock(&vq->mutex); } /* Some packets may have been queued before the device was started, * let's kick the send worker to send them. */ vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); mutex_unlock(&vsock->dev.mutex); return 0; err_vq: vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner) { size_t i; int ret = 0; mutex_lock(&vsock->dev.mutex); if (check_owner) { ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; } for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { struct vhost_virtqueue *vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static void vhost_vsock_free(struct vhost_vsock *vsock) { kvfree(vsock); } static int vhost_vsock_dev_open(struct inode *inode, struct file *file) { struct vhost_virtqueue **vqs; struct vhost_vsock *vsock; int ret; /* This struct is large and allocation could fail, fall back to vmalloc * if there is no other way. */ vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!vsock) return -ENOMEM; vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL); if (!vqs) { ret = -ENOMEM; goto out; } vsock->guest_cid = 0; /* no CID assigned yet */ vsock->seqpacket_allow = false; atomic_set(&vsock->queued_replies, 0); vqs[VSOCK_VQ_TX] = &vsock->vqs[VSOCK_VQ_TX]; vqs[VSOCK_VQ_RX] = &vsock->vqs[VSOCK_VQ_RX]; vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT, VHOST_VSOCK_WEIGHT, true, NULL); file->private_data = vsock; skb_queue_head_init(&vsock->send_pkt_queue); vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work); return 0; out: vhost_vsock_free(vsock); return ret; } static void vhost_vsock_flush(struct vhost_vsock *vsock) { vhost_dev_flush(&vsock->dev); } static void vhost_vsock_reset_orphans(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); /* vmci_transport.c doesn't take sk_lock here either. At least we're * under vsock_table_lock so the sock cannot disappear while we're * executing. */ /* If the peer is still valid, no need to reset connection */ if (vhost_vsock_get(vsk->remote_addr.svm_cid)) return; /* If the close timeout is pending, let it expire. This avoids races * with the timeout callback. */ if (vsk->close_work_scheduled) return; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; sk_error_report(sk); } static int vhost_vsock_dev_release(struct inode *inode, struct file *file) { struct vhost_vsock *vsock = file->private_data; mutex_lock(&vhost_vsock_mutex); if (vsock->guest_cid) hash_del_rcu(&vsock->hash); mutex_unlock(&vhost_vsock_mutex); /* Wait for other CPUs to finish using vsock */ synchronize_rcu(); /* Iterating over all connections for all CIDs to find orphans is * inefficient. Room for improvement here. */ vsock_for_each_connected_socket(&vhost_transport.transport, vhost_vsock_reset_orphans); /* Don't check the owner, because we are in the release path, so we * need to stop the vsock device in any case. * vhost_vsock_stop() can not fail in this case, so we don't need to * check the return code. */ vhost_vsock_stop(vsock, false); vhost_vsock_flush(vsock); vhost_dev_stop(&vsock->dev); virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); vhost_dev_cleanup(&vsock->dev); kfree(vsock->dev.vqs); vhost_vsock_free(vsock); return 0; } static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) { struct vhost_vsock *other; /* Refuse reserved CIDs */ if (guest_cid <= VMADDR_CID_HOST || guest_cid == U32_MAX) return -EINVAL; /* 64-bit CIDs are not yet supported */ if (guest_cid > U32_MAX) return -EINVAL; /* Refuse if CID is assigned to the guest->host transport (i.e. nested * VM), to make the loopback work. */ if (vsock_find_cid(guest_cid)) return -EADDRINUSE; /* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); if (other && other != vsock) { mutex_unlock(&vhost_vsock_mutex); return -EADDRINUSE; } if (vsock->guest_cid) hash_del_rcu(&vsock->hash); vsock->guest_cid = guest_cid; hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid); mutex_unlock(&vhost_vsock_mutex); return 0; } static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) { struct vhost_virtqueue *vq; int i; if (features & ~VHOST_VSOCK_FEATURES) return -EOPNOTSUPP; mutex_lock(&vsock->dev.mutex); if ((features & (1 << VHOST_F_LOG_ALL)) && !vhost_log_access_ok(&vsock->dev)) { goto err; } if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&vsock->dev)) goto err; } vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vq->acked_features = features; mutex_unlock(&vq->mutex); } mutex_unlock(&vsock->dev.mutex); return 0; err: mutex_unlock(&vsock->dev.mutex); return -EFAULT; } static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { struct vhost_vsock *vsock = f->private_data; void __user *argp = (void __user *)arg; u64 guest_cid; u64 features; int start; int r; switch (ioctl) { case VHOST_VSOCK_SET_GUEST_CID: if (copy_from_user(&guest_cid, argp, sizeof(guest_cid))) return -EFAULT; return vhost_vsock_set_cid(vsock, guest_cid); case VHOST_VSOCK_SET_RUNNING: if (copy_from_user(&start, argp, sizeof(start))) return -EFAULT; if (start) return vhost_vsock_start(vsock); else return vhost_vsock_stop(vsock, true); case VHOST_GET_FEATURES: features = VHOST_VSOCK_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; return vhost_vsock_set_features(vsock, features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_VSOCK_BACKEND_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_BACKEND_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; if (features & ~VHOST_VSOCK_BACKEND_FEATURES) return -EOPNOTSUPP; vhost_set_backend_features(&vsock->dev, features); return 0; default: mutex_lock(&vsock->dev.mutex); r = vhost_dev_ioctl(&vsock->dev, ioctl, argp); if (r == -ENOIOCTLCMD) r = vhost_vring_ioctl(&vsock->dev, ioctl, argp); else vhost_vsock_flush(vsock); mutex_unlock(&vsock->dev.mutex); return r; } } static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; int noblock = file->f_flags & O_NONBLOCK; return vhost_chr_read_iter(dev, to, noblock); } static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_write_iter(dev, from); } static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait) { struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_poll(file, dev, wait); } static const struct file_operations vhost_vsock_fops = { .owner = THIS_MODULE, .open = vhost_vsock_dev_open, .release = vhost_vsock_dev_release, .llseek = noop_llseek, .unlocked_ioctl = vhost_vsock_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, .read_iter = vhost_vsock_chr_read_iter, .write_iter = vhost_vsock_chr_write_iter, .poll = vhost_vsock_chr_poll, }; static struct miscdevice vhost_vsock_misc = { .minor = VHOST_VSOCK_MINOR, .name = "vhost-vsock", .fops = &vhost_vsock_fops, }; static int __init vhost_vsock_init(void) { int ret; ret = vsock_core_register(&vhost_transport.transport, VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; ret = misc_register(&vhost_vsock_misc); if (ret) { vsock_core_unregister(&vhost_transport.transport); return ret; } return 0; }; static void __exit vhost_vsock_exit(void) { misc_deregister(&vhost_vsock_misc); vsock_core_unregister(&vhost_transport.transport); }; module_init(vhost_vsock_init); module_exit(vhost_vsock_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); MODULE_DESCRIPTION("vhost transport for vsock "); MODULE_ALIAS_MISCDEV(VHOST_VSOCK_MINOR); MODULE_ALIAS("devname:vhost-vsock"); |
| 3 1 1 2 2 10 3 4 1 7 2 5 3 4 1 4 12 12 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * read/write/select interface to device file * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include "seq_oss_synth.h" #include <sound/seq_oss_legacy.h> #include "seq_oss_event.h" #include "seq_oss_timer.h" #include "../seq_clientmgr.h" /* * protoypes */ static int insert_queue(struct seq_oss_devinfo *dp, union evrec *rec, struct file *opt); /* * read interface */ int snd_seq_oss_read(struct seq_oss_devinfo *dp, char __user *buf, int count) { struct seq_oss_readq *readq = dp->readq; int result = 0, err = 0; int ev_len; union evrec rec; unsigned long flags; if (readq == NULL || ! is_read_mode(dp->file_mode)) return -ENXIO; while (count >= SHORT_EVENT_SIZE) { snd_seq_oss_readq_lock(readq, flags); err = snd_seq_oss_readq_pick(readq, &rec); if (err == -EAGAIN && !is_nonblock_mode(dp->file_mode) && result == 0) { snd_seq_oss_readq_unlock(readq, flags); snd_seq_oss_readq_wait(readq); snd_seq_oss_readq_lock(readq, flags); if (signal_pending(current)) err = -ERESTARTSYS; else err = snd_seq_oss_readq_pick(readq, &rec); } if (err < 0) { snd_seq_oss_readq_unlock(readq, flags); break; } ev_len = ev_length(&rec); if (ev_len < count) { snd_seq_oss_readq_unlock(readq, flags); break; } snd_seq_oss_readq_free(readq); snd_seq_oss_readq_unlock(readq, flags); if (copy_to_user(buf, &rec, ev_len)) { err = -EFAULT; break; } result += ev_len; buf += ev_len; count -= ev_len; } return result > 0 ? result : err; } /* * write interface */ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int count, struct file *opt) { int result = 0, err = 0; int ev_size, fmt; union evrec rec; if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return -ENXIO; while (count >= SHORT_EVENT_SIZE) { if (copy_from_user(&rec, buf, SHORT_EVENT_SIZE)) { err = -EFAULT; break; } if (rec.s.code == SEQ_FULLSIZE) { /* load patch */ if (result > 0) { err = -EINVAL; break; } fmt = (*(unsigned short *)rec.c) & 0xffff; /* FIXME the return value isn't correct */ return snd_seq_oss_synth_load_patch(dp, rec.s.dev, fmt, buf, 0, count); } if (ev_is_long(&rec)) { /* extended code */ if (rec.s.code == SEQ_EXTENDED && dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { err = -EINVAL; break; } ev_size = LONG_EVENT_SIZE; if (count < ev_size) break; /* copy the reset 4 bytes */ if (copy_from_user(rec.c + SHORT_EVENT_SIZE, buf + SHORT_EVENT_SIZE, LONG_EVENT_SIZE - SHORT_EVENT_SIZE)) { err = -EFAULT; break; } } else { /* old-type code */ if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { err = -EINVAL; break; } ev_size = SHORT_EVENT_SIZE; } /* insert queue */ err = insert_queue(dp, &rec, opt); if (err < 0) break; result += ev_size; buf += ev_size; count -= ev_size; } return result > 0 ? result : err; } /* * insert event record to write queue * return: 0 = OK, non-zero = NG */ static int insert_queue(struct seq_oss_devinfo *dp, union evrec *rec, struct file *opt) { int rc = 0; struct snd_seq_event event; /* if this is a timing event, process the current time */ if (snd_seq_oss_process_timer_event(dp->timer, rec)) return 0; /* no need to insert queue */ /* parse this event */ memset(&event, 0, sizeof(event)); /* set dummy -- to be sure */ event.type = SNDRV_SEQ_EVENT_NOTEOFF; snd_seq_oss_fill_addr(dp, &event, dp->addr.client, dp->addr.port); if (snd_seq_oss_process_event(dp, rec, &event)) return 0; /* invalid event - no need to insert queue */ event.time.tick = snd_seq_oss_timer_cur_tick(dp->timer); if (dp->timer->realtime || !dp->timer->running) snd_seq_oss_dispatch(dp, &event, 0, 0); else rc = snd_seq_kernel_client_enqueue(dp->cseq, &event, opt, !is_nonblock_mode(dp->file_mode)); return rc; } /* * select / poll */ __poll_t snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait) { __poll_t mask = 0; /* input */ if (dp->readq && is_read_mode(dp->file_mode)) { if (snd_seq_oss_readq_poll(dp->readq, file, wait)) mask |= EPOLLIN | EPOLLRDNORM; } /* output */ if (dp->writeq && is_write_mode(dp->file_mode)) { if (snd_seq_kernel_client_write_poll(dp->cseq, file, wait)) mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } |
| 1 48 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/fs/hpfs/hpfs_fn.h * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * function headers */ //#define DBG //#define DEBUG_LOCKS #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/blkdev.h> #include <linux/unaligned.h> #include "hpfs.h" #define EIOERROR EIO #define EFSERROR EUCLEAN #define ANODE_ALLOC_FWD 512 #define FNODE_ALLOC_FWD 0 #define ALLOC_FWD_MIN 16 #define ALLOC_FWD_MAX 128 #define ALLOC_M 1 #define FNODE_RD_AHEAD 16 #define ANODE_RD_AHEAD 0 #define DNODE_RD_AHEAD 72 #define COUNT_RD_AHEAD 62 #define FREE_DNODES_ADD 58 #define FREE_DNODES_DEL 29 #define CHKCOND(x,y) if (!(x)) printk y struct hpfs_inode_info { loff_t mmu_private; ino_t i_parent_dir; /* (directories) gives fnode of parent dir */ unsigned i_dno; /* (directories) root dnode */ unsigned i_dpos; /* (directories) temp for readdir */ unsigned i_dsubdno; /* (directories) temp for readdir */ unsigned i_file_sec; /* (files) minimalist cache of alloc info */ unsigned i_disk_sec; /* (files) minimalist cache of alloc info */ unsigned i_n_secs; /* (files) minimalist cache of alloc info */ unsigned i_ea_size; /* size of extended attributes */ unsigned i_ea_mode : 1; /* file's permission is stored in ea */ unsigned i_ea_uid : 1; /* file's uid is stored in ea */ unsigned i_ea_gid : 1; /* file's gid is stored in ea */ unsigned i_dirty : 1; loff_t **i_rddir_off; struct inode vfs_inode; }; struct hpfs_sb_info { struct mutex hpfs_mutex; /* global hpfs lock */ ino_t sb_root; /* inode number of root dir */ unsigned sb_fs_size; /* file system size, sectors */ unsigned sb_bitmaps; /* sector number of bitmap list */ unsigned sb_dirband_start; /* directory band start sector */ unsigned sb_dirband_size; /* directory band size, dnodes */ unsigned sb_dmap; /* sector number of dnode bit map */ unsigned sb_n_free; /* free blocks for statfs, or -1 */ unsigned sb_n_free_dnodes; /* free dnodes for statfs, or -1 */ kuid_t sb_uid; /* uid from mount options */ kgid_t sb_gid; /* gid from mount options */ umode_t sb_mode; /* mode from mount options */ unsigned sb_eas : 2; /* eas: 0-ignore, 1-ro, 2-rw */ unsigned sb_err : 2; /* on errs: 0-cont, 1-ro, 2-panic */ unsigned sb_chk : 2; /* checks: 0-no, 1-normal, 2-strict */ unsigned sb_lowercase : 1; /* downcase filenames hackery */ unsigned sb_was_error : 1; /* there was an error, set dirty flag */ unsigned sb_chkdsk : 2; /* chkdsk: 0-no, 1-on errs, 2-allways */ unsigned char *sb_cp_table; /* code page tables: */ /* 128 bytes uppercasing table & */ /* 128 bytes lowercasing table */ __le32 *sb_bmp_dir; /* main bitmap directory */ unsigned sb_c_bitmap; /* current bitmap */ unsigned sb_max_fwd_alloc; /* max forwad allocation */ int sb_timeshift; struct rcu_head rcu; unsigned n_hotfixes; secno hotfix_from[256]; secno hotfix_to[256]; }; /* Four 512-byte buffers and the 2k block obtained by concatenating them */ struct quad_buffer_head { struct buffer_head *bh[4]; void *data; }; /* The b-tree down pointer from a dir entry */ static inline dnode_secno de_down_pointer (struct hpfs_dirent *de) { CHKCOND(de->down,("HPFS: de_down_pointer: !de->down\n")); return le32_to_cpu(*(__le32 *) ((void *) de + le16_to_cpu(de->length) - 4)); } /* The first dir entry in a dnode */ static inline struct hpfs_dirent *dnode_first_de (struct dnode *dnode) { return (void *) dnode->dirent; } /* The end+1 of the dir entries */ static inline struct hpfs_dirent *dnode_end_de (struct dnode *dnode) { CHKCOND(le32_to_cpu(dnode->first_free)>=0x14 && le32_to_cpu(dnode->first_free)<=0xa00,("HPFS: dnode_end_de: dnode->first_free = %x\n",(unsigned)le32_to_cpu(dnode->first_free))); return (void *) dnode + le32_to_cpu(dnode->first_free); } /* The dir entry after dir entry de */ static inline struct hpfs_dirent *de_next_de (struct hpfs_dirent *de) { CHKCOND(le16_to_cpu(de->length)>=0x20 && le16_to_cpu(de->length)<0x800,("HPFS: de_next_de: de->length = %x\n",(unsigned)le16_to_cpu(de->length))); return (void *) de + le16_to_cpu(de->length); } static inline struct extended_attribute *fnode_ea(struct fnode *fnode) { return (struct extended_attribute *)((char *)fnode + le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s)); } static inline struct extended_attribute *fnode_end_ea(struct fnode *fnode) { return (struct extended_attribute *)((char *)fnode + le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s) + le16_to_cpu(fnode->ea_size_s)); } static unsigned ea_valuelen(struct extended_attribute *ea) { return ea->valuelen_lo + 256 * ea->valuelen_hi; } static inline struct extended_attribute *next_ea(struct extended_attribute *ea) { return (struct extended_attribute *)((char *)ea + 5 + ea->namelen + ea_valuelen(ea)); } static inline secno ea_sec(struct extended_attribute *ea) { return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 9 + ea->namelen))); } static inline secno ea_len(struct extended_attribute *ea) { return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 5 + ea->namelen))); } static inline char *ea_data(struct extended_attribute *ea) { return (char *)((char *)ea + 5 + ea->namelen); } static inline unsigned de_size(int namelen, secno down_ptr) { return ((0x1f + namelen + 3) & ~3) + (down_ptr ? 4 : 0); } static inline void copy_de(struct hpfs_dirent *dst, struct hpfs_dirent *src) { int a; int n; if (!dst || !src) return; a = dst->down; n = dst->not_8x3; memcpy((char *)dst + 2, (char *)src + 2, 28); dst->down = a; dst->not_8x3 = n; } static inline unsigned tstbits(__le32 *bmp, unsigned b, unsigned n) { int i; if ((b >= 0x4000) || (b + n - 1 >= 0x4000)) return n; if (!((le32_to_cpu(bmp[(b & 0x3fff) >> 5]) >> (b & 0x1f)) & 1)) return 1; for (i = 1; i < n; i++) if (!((le32_to_cpu(bmp[((b+i) & 0x3fff) >> 5]) >> ((b+i) & 0x1f)) & 1)) return i + 1; return 0; } /* alloc.c */ int hpfs_chk_sectors(struct super_block *, secno, int, char *); secno hpfs_alloc_sector(struct super_block *, secno, unsigned, int); int hpfs_alloc_if_possible(struct super_block *, secno); void hpfs_free_sectors(struct super_block *, secno, unsigned); int hpfs_check_free_dnodes(struct super_block *, int); void hpfs_free_dnode(struct super_block *, secno); struct dnode *hpfs_alloc_dnode(struct super_block *, secno, dnode_secno *, struct quad_buffer_head *); struct fnode *hpfs_alloc_fnode(struct super_block *, secno, fnode_secno *, struct buffer_head **); struct anode *hpfs_alloc_anode(struct super_block *, secno, anode_secno *, struct buffer_head **); int hpfs_trim_fs(struct super_block *, u64, u64, u64, unsigned *); /* anode.c */ secno hpfs_bplus_lookup(struct super_block *, struct inode *, struct bplus_header *, unsigned, struct buffer_head *); secno hpfs_add_sector_to_btree(struct super_block *, secno, int, unsigned); void hpfs_remove_btree(struct super_block *, struct bplus_header *); int hpfs_ea_read(struct super_block *, secno, int, unsigned, unsigned, char *); int hpfs_ea_write(struct super_block *, secno, int, unsigned, unsigned, const char *); void hpfs_ea_remove(struct super_block *, secno, int, unsigned); void hpfs_truncate_btree(struct super_block *, secno, int, unsigned); void hpfs_remove_fnode(struct super_block *, fnode_secno fno); /* buffer.c */ secno hpfs_search_hotfix_map(struct super_block *s, secno sec); unsigned hpfs_search_hotfix_map_for_range(struct super_block *s, secno sec, unsigned n); void hpfs_prefetch_sectors(struct super_block *, unsigned, int); void *hpfs_map_sector(struct super_block *, unsigned, struct buffer_head **, int); void *hpfs_get_sector(struct super_block *, unsigned, struct buffer_head **); void *hpfs_map_4sectors(struct super_block *, unsigned, struct quad_buffer_head *, int); void *hpfs_get_4sectors(struct super_block *, unsigned, struct quad_buffer_head *); void hpfs_brelse4(struct quad_buffer_head *); void hpfs_mark_4buffers_dirty(struct quad_buffer_head *); /* dentry.c */ extern const struct dentry_operations hpfs_dentry_operations; /* dir.c */ struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int); extern const struct file_operations hpfs_dir_ops; /* dnode.c */ int hpfs_add_pos(struct inode *, loff_t *); void hpfs_del_pos(struct inode *, loff_t *); struct hpfs_dirent *hpfs_add_de(struct super_block *, struct dnode *, const unsigned char *, unsigned, secno); int hpfs_add_dirent(struct inode *, const unsigned char *, unsigned, struct hpfs_dirent *); int hpfs_remove_dirent(struct inode *, dnode_secno, struct hpfs_dirent *, struct quad_buffer_head *, int); void hpfs_count_dnodes(struct super_block *, dnode_secno, int *, int *, int *); dnode_secno hpfs_de_as_down_as_possible(struct super_block *, dnode_secno dno); struct hpfs_dirent *map_pos_dirent(struct inode *, loff_t *, struct quad_buffer_head *); struct hpfs_dirent *map_dirent(struct inode *, dnode_secno, const unsigned char *, unsigned, dnode_secno *, struct quad_buffer_head *); void hpfs_remove_dtree(struct super_block *, dnode_secno); struct hpfs_dirent *map_fnode_dirent(struct super_block *, fnode_secno, struct fnode *, struct quad_buffer_head *); /* ea.c */ void hpfs_ea_ext_remove(struct super_block *, secno, int, unsigned); int hpfs_read_ea(struct super_block *, struct fnode *, char *, char *, int); char *hpfs_get_ea(struct super_block *, struct fnode *, char *, int *); void hpfs_set_ea(struct inode *, struct fnode *, const char *, const char *, int); /* file.c */ int hpfs_file_fsync(struct file *, loff_t, loff_t, int); void hpfs_truncate(struct inode *); extern const struct file_operations hpfs_file_ops; extern const struct inode_operations hpfs_file_iops; extern const struct address_space_operations hpfs_aops; /* inode.c */ void hpfs_init_inode(struct inode *); void hpfs_read_inode(struct inode *); void hpfs_write_inode(struct inode *); void hpfs_write_inode_nolock(struct inode *); int hpfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); void hpfs_write_if_changed(struct inode *); void hpfs_evict_inode(struct inode *); /* map.c */ __le32 *hpfs_map_dnode_bitmap(struct super_block *, struct quad_buffer_head *); __le32 *hpfs_map_bitmap(struct super_block *, unsigned, struct quad_buffer_head *, char *); void hpfs_prefetch_bitmap(struct super_block *, unsigned); unsigned char *hpfs_load_code_page(struct super_block *, secno); __le32 *hpfs_load_bitmap_directory(struct super_block *, secno bmp); void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock); struct fnode *hpfs_map_fnode(struct super_block *s, ino_t, struct buffer_head **); struct anode *hpfs_map_anode(struct super_block *s, anode_secno, struct buffer_head **); struct dnode *hpfs_map_dnode(struct super_block *s, dnode_secno, struct quad_buffer_head *); dnode_secno hpfs_fnode_dno(struct super_block *s, ino_t ino); /* name.c */ unsigned char hpfs_upcase(unsigned char *, unsigned char); int hpfs_chk_name(const unsigned char *, unsigned *); unsigned char *hpfs_translate_name(struct super_block *, unsigned char *, unsigned, int, int); int hpfs_compare_names(struct super_block *, const unsigned char *, unsigned, const unsigned char *, unsigned, int); int hpfs_is_name_long(const unsigned char *, unsigned); void hpfs_adjust_length(const unsigned char *, unsigned *); /* namei.c */ extern const struct inode_operations hpfs_dir_iops; extern const struct address_space_operations hpfs_symlink_aops; static inline struct hpfs_inode_info *hpfs_i(struct inode *inode) { return container_of(inode, struct hpfs_inode_info, vfs_inode); } static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb) { return sb->s_fs_info; } /* super.c */ __printf(2, 3) void hpfs_error(struct super_block *, const char *, ...); int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *); unsigned hpfs_get_free_dnodes(struct super_block *); long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg); /* * local time (HPFS) to GMT (Unix) */ static inline time64_t local_to_gmt(struct super_block *s, time64_t t) { extern struct timezone sys_tz; return t + sys_tz.tz_minuteswest * 60 + hpfs_sb(s)->sb_timeshift; } static inline time32_t gmt_to_local(struct super_block *s, time64_t t) { extern struct timezone sys_tz; return t - sys_tz.tz_minuteswest * 60 - hpfs_sb(s)->sb_timeshift; } static inline time32_t local_get_seconds(struct super_block *s) { return gmt_to_local(s, ktime_get_real_seconds()); } /* * Locking: * * hpfs_lock() locks the whole filesystem. It must be taken * on any method called by the VFS. * * We don't do any per-file locking anymore, it is hard to * review and HPFS is not performance-sensitive anyway. */ static inline void hpfs_lock(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); mutex_lock(&sbi->hpfs_mutex); } static inline void hpfs_unlock(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); mutex_unlock(&sbi->hpfs_mutex); } static inline void hpfs_lock_assert(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); WARN_ON(!mutex_is_locked(&sbi->hpfs_mutex)); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 - wext compat code * * This is temporary code until all wireless functionality is migrated * into cfg80211, when that happens all the exports here go away and * we directly assign the wireless handlers of wireless interfaces. * * Copyright 2008-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2019-2023 Intel Corporation */ #include <linux/export.h> #include <linux/wireless.h> #include <linux/nl80211.h> #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "core.h" #include "rdev-ops.h" int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { strcpy(wrqu->name, "IEEE 802.11"); return 0; } int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; struct vif_params vifparams; enum nl80211_iftype type; rdev = wiphy_to_rdev(wdev->wiphy); switch (*mode) { case IW_MODE_INFRA: type = NL80211_IFTYPE_STATION; break; case IW_MODE_ADHOC: type = NL80211_IFTYPE_ADHOC; break; case IW_MODE_MONITOR: type = NL80211_IFTYPE_MONITOR; break; default: return -EINVAL; } if (type == wdev->iftype) return 0; memset(&vifparams, 0, sizeof(vifparams)); guard(wiphy)(wdev->wiphy); return cfg80211_change_iface(rdev, dev, type, &vifparams); } int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; switch (wdev->iftype) { case NL80211_IFTYPE_AP: *mode = IW_MODE_MASTER; break; case NL80211_IFTYPE_STATION: *mode = IW_MODE_INFRA; break; case NL80211_IFTYPE_ADHOC: *mode = IW_MODE_ADHOC; break; case NL80211_IFTYPE_MONITOR: *mode = IW_MODE_MONITOR; break; case NL80211_IFTYPE_WDS: *mode = IW_MODE_REPEAT; break; case NL80211_IFTYPE_AP_VLAN: *mode = IW_MODE_SECOND; /* FIXME */ break; default: *mode = IW_MODE_AUTO; break; } return 0; } int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum nl80211_band band; int i, c = 0; if (!wdev) return -EOPNOTSUPP; data->length = sizeof(struct iw_range); memset(range, 0, sizeof(struct iw_range)); range->we_version_compiled = WIRELESS_EXT; range->we_version_source = 21; range->retry_capa = IW_RETRY_LIMIT; range->retry_flags = IW_RETRY_LIMIT; range->min_retry = 0; range->max_retry = 255; range->min_rts = 0; range->max_rts = 2347; range->min_frag = 256; range->max_frag = 2346; range->max_encoding_tokens = 4; range->max_qual.updated = IW_QUAL_NOISE_INVALID; switch (wdev->wiphy->signal_type) { case CFG80211_SIGNAL_TYPE_NONE: break; case CFG80211_SIGNAL_TYPE_MBM: range->max_qual.level = (u8)-110; range->max_qual.qual = 70; range->avg_qual.qual = 35; range->max_qual.updated |= IW_QUAL_DBM; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; case CFG80211_SIGNAL_TYPE_UNSPEC: range->max_qual.level = 100; range->max_qual.qual = 100; range->avg_qual.qual = 50; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; } range->avg_qual.level = range->max_qual.level / 2; range->avg_qual.noise = range->max_qual.noise / 2; range->avg_qual.updated = range->max_qual.updated; for (i = 0; i < wdev->wiphy->n_cipher_suites; i++) { switch (wdev->wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_TKIP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_WPA); break; case WLAN_CIPHER_SUITE_CCMP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_CCMP | IW_ENC_CAPA_WPA2); break; case WLAN_CIPHER_SUITE_WEP40: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP40; break; case WLAN_CIPHER_SUITE_WEP104: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP104; break; } } for (band = 0; band < NUM_NL80211_BANDS; band ++) { struct ieee80211_supported_band *sband; sband = wdev->wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels && c < IW_MAX_FREQUENCIES; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (!(chan->flags & IEEE80211_CHAN_DISABLED)) { range->freq[c].i = ieee80211_frequency_to_channel( chan->center_freq); range->freq[c].m = chan->center_freq; range->freq[c].e = 6; c++; } } } range->num_channels = c; range->num_frequency = c; IW_EVENT_CAPA_SET_KERNEL(range->event_capa); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWSCAN); if (wdev->wiphy->max_scan_ssids > 0) range->scan_capa |= IW_SCAN_CAPA_ESSID; return 0; } /** * cfg80211_wext_freq - get wext frequency for non-"auto" * @freq: the wext freq encoding * * Returns: a frequency, or a negative error code, or 0 for auto. */ int cfg80211_wext_freq(struct iw_freq *freq) { /* * Parse frequency - return 0 for auto and * -EINVAL for impossible things. */ if (freq->e == 0) { enum nl80211_band band = NL80211_BAND_2GHZ; if (freq->m < 0) return 0; if (freq->m > 14) band = NL80211_BAND_5GHZ; return ieee80211_channel_to_frequency(freq->m, band); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div <= 0) return -EINVAL; return freq->m / div; } } int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 orts = wdev->wiphy->rts_threshold; int err; guard(wiphy)(&rdev->wiphy); if (rts->disabled || !rts->fixed) wdev->wiphy->rts_threshold = (u32) -1; else if (rts->value < 0) return -EINVAL; else wdev->wiphy->rts_threshold = rts->value; err = rdev_set_wiphy_params(rdev, -1, WIPHY_PARAM_RTS_THRESHOLD); if (err) wdev->wiphy->rts_threshold = orts; return err; } int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; rts->value = wdev->wiphy->rts_threshold; rts->disabled = rts->value == (u32) -1; rts->fixed = 1; return 0; } int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 ofrag = wdev->wiphy->frag_threshold; int err; guard(wiphy)(&rdev->wiphy); if (frag->disabled || !frag->fixed) { wdev->wiphy->frag_threshold = (u32) -1; } else if (frag->value < 256) { return -EINVAL; } else { /* Fragment length must be even, so strip LSB. */ wdev->wiphy->frag_threshold = frag->value & ~0x1; } err = rdev_set_wiphy_params(rdev, -1, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; return err; } int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; frag->value = wdev->wiphy->frag_threshold; frag->disabled = frag->value == (u32) -1; frag->fixed = 1; return 0; } static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 changed = 0; u8 olong = wdev->wiphy->retry_long; u8 oshort = wdev->wiphy->retry_short; int err; if (retry->disabled || retry->value < 1 || retry->value > 255 || (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; guard(wiphy)(&rdev->wiphy); if (retry->flags & IW_RETRY_LONG) { wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; } else if (retry->flags & IW_RETRY_SHORT) { wdev->wiphy->retry_short = retry->value; changed |= WIPHY_PARAM_RETRY_SHORT; } else { wdev->wiphy->retry_short = retry->value; wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; changed |= WIPHY_PARAM_RETRY_SHORT; } err = rdev_set_wiphy_params(rdev, -1, changed); if (err) { wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; } return err; } int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; retry->disabled = 0; if (retry->flags == 0 || (retry->flags & IW_RETRY_SHORT)) { /* * First return short value, iwconfig will ask long value * later if needed */ retry->flags |= IW_RETRY_LIMIT | IW_RETRY_SHORT; retry->value = wdev->wiphy->retry_short; if (wdev->wiphy->retry_long == wdev->wiphy->retry_short) retry->flags |= IW_RETRY_LONG; return 0; } if (retry->flags & IW_RETRY_LONG) { retry->flags = IW_RETRY_LIMIT | IW_RETRY_LONG; retry->value = wdev->wiphy->retry_long; } return 0; } static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, struct net_device *dev, bool pairwise, const u8 *addr, bool remove, bool tx_key, int idx, struct key_params *params) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err, i; bool rejoin = false; if (wdev->valid_links) return -EINVAL; if (pairwise && !addr) return -EINVAL; /* * In many cases we won't actually need this, but it's better * to do it first in case the allocation fails. Don't use wext. */ if (!wdev->wext.keys) { wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), GFP_KERNEL); if (!wdev->wext.keys) return -ENOMEM; for (i = 0; i < 4; i++) wdev->wext.keys->params[i].key = wdev->wext.keys->data[i]; } if (wdev->iftype != NL80211_IFTYPE_ADHOC && wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (!wdev->connected) return -ENOLINK; if (!rdev->ops->set_default_mgmt_key) return -EOPNOTSUPP; if (idx < 4 || idx > 5) return -EINVAL; } else if (idx < 0 || idx > 3) return -EINVAL; if (remove) { err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If removing the current TX key, we will need to * join a new IBSS without the privacy bit clear. */ if (idx == wdev->wext.default_key && wdev->iftype == NL80211_IFTYPE_ADHOC) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } if (!pairwise && addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; else err = rdev_del_key(rdev, dev, -1, idx, pairwise, addr); } wdev->wext.connect.privacy = false; /* * Applications using wireless extensions expect to be * able to delete keys that don't exist, so allow that. */ if (err == -ENOENT) err = 0; if (!err) { if (!addr && idx < 4) { memset(wdev->wext.keys->data[idx], 0, sizeof(wdev->wext.keys->data[idx])); wdev->wext.keys->params[idx].key_len = 0; wdev->wext.keys->params[idx].cipher = 0; } if (idx == wdev->wext.default_key) wdev->wext.default_key = -1; else if (idx == wdev->wext.default_mgmt_key) wdev->wext.default_mgmt_key = -1; } if (!err && rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); return err; } if (addr) tx_key = false; if (cfg80211_validate_key_settings(rdev, params, idx, pairwise, addr)) return -EINVAL; err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_add_key(rdev, dev, -1, idx, pairwise, addr, params); else if (params->cipher != WLAN_CIPHER_SUITE_WEP40 && params->cipher != WLAN_CIPHER_SUITE_WEP104) return -EINVAL; if (err) return err; /* * We only need to store WEP keys, since they're the only keys that * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104)) { wdev->wext.keys->params[idx] = *params; memcpy(wdev->wext.keys->data[idx], params->key, params->key_len); wdev->wext.keys->params[idx].key = wdev->wext.keys->data[idx]; } if ((params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104) && (tx_key || (!addr && wdev->wext.default_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If we are getting a new TX key from not having * had one before we need to join a new IBSS with * the privacy bit set. */ if (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->wext.default_key == -1) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } err = rdev_set_default_key(rdev, dev, -1, idx, true, true); } if (!err) { wdev->wext.default_key = idx; if (rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); } return err; } if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_mgmt_key(rdev, dev, -1, idx); if (!err) wdev->wext.default_mgmt_key = idx; return err; } return 0; } static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct key_params params; bool remove = false; int idx; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; guard(wiphy)(&rdev->wiphy); if (wdev->valid_links) return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) { return -EINVAL; } else { idx--; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; else if (erq->length == 0) { /* No key data - just set the default TX key index */ int err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_key(rdev, dev, -1, idx, true, true); if (!err) wdev->wext.default_key = idx; return err; } memset(¶ms, 0, sizeof(params)); params.key = keybuf; params.key_len = erq->length; if (erq->length == 5) params.cipher = WLAN_CIPHER_SUITE_WEP40; else if (erq->length == 13) params.cipher = WLAN_CIPHER_SUITE_WEP104; else if (!remove) return -EINVAL; return cfg80211_set_encryption(rdev, dev, false, NULL, remove, wdev->wext.default_key == -1, idx, ¶ms); } static int cfg80211_wext_siwencodeext(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; const u8 *addr; int idx; bool remove = false; struct key_params params; u32 cipher; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; if (wdev->valid_links) return -EOPNOTSUPP; switch (ext->alg) { case IW_ENCODE_ALG_NONE: remove = true; cipher = 0; break; case IW_ENCODE_ALG_WEP: if (ext->key_len == 5) cipher = WLAN_CIPHER_SUITE_WEP40; else if (ext->key_len == 13) cipher = WLAN_CIPHER_SUITE_WEP104; else return -EINVAL; break; case IW_ENCODE_ALG_TKIP: cipher = WLAN_CIPHER_SUITE_TKIP; break; case IW_ENCODE_ALG_CCMP: cipher = WLAN_CIPHER_SUITE_CCMP; break; case IW_ENCODE_ALG_AES_CMAC: cipher = WLAN_CIPHER_SUITE_AES_CMAC; break; default: return -EOPNOTSUPP; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; idx = erq->flags & IW_ENCODE_INDEX; if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (idx < 4 || idx > 5) { idx = wdev->wext.default_mgmt_key; if (idx < 0) return -EINVAL; } else idx--; } else { if (idx < 1 || idx > 4) { idx = wdev->wext.default_key; if (idx < 0) return -EINVAL; } else idx--; } addr = ext->addr.sa_data; if (is_broadcast_ether_addr(addr)) addr = NULL; memset(¶ms, 0, sizeof(params)); params.key = ext->key; params.key_len = ext->key_len; params.cipher = cipher; if (ext->ext_flags & IW_ENCODE_EXT_RX_SEQ_VALID) { params.seq = ext->rx_seq; params.seq_len = 6; } guard(wiphy)(wdev->wiphy); return cfg80211_set_encryption(rdev, dev, !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), addr, remove, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); } static int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) return -EINVAL; else idx--; erq->flags = idx + 1; if (!wdev->wext.keys || !wdev->wext.keys->params[idx].cipher) { erq->flags |= IW_ENCODE_DISABLED; erq->length = 0; return 0; } erq->length = min_t(size_t, erq->length, wdev->wext.keys->params[idx].key_len); memcpy(keybuf, wdev->wext.keys->params[idx].key, erq->length); erq->flags |= IW_ENCODE_ENABLED; return 0; } static int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *wextfreq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = { .width = NL80211_CHAN_WIDTH_20_NOHT, }; int freq; guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_MONITOR: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) return freq; if (freq == 0) return -EINVAL; chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) return -EINVAL; return cfg80211_set_monitor_channel(rdev, dev, &chandef); case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) return freq; if (freq == 0) return -EINVAL; chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) return -EINVAL; return cfg80211_set_mesh_channel(rdev, wdev, &chandef); default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *freq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = {}; int ret; guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); case NL80211_IFTYPE_MONITOR: if (!rdev->ops->get_channel) return -EINVAL; ret = rdev_get_channel(rdev, wdev, 0, &chandef); if (ret) return ret; freq->m = chandef.chan->center_freq; freq->e = 6; return ret; default: return -EINVAL; } } static int cfg80211_wext_siwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); enum nl80211_tx_power_setting type; int dbm = 0; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->set_tx_power) return -EOPNOTSUPP; /* only change when not disabling */ if (!data->txpower.disabled) { rfkill_set_sw_state(rdev->wiphy.rfkill, false); if (data->txpower.fixed) { /* * wext doesn't support negative values, see * below where it's for automatic */ if (data->txpower.value < 0) return -EINVAL; dbm = data->txpower.value; type = NL80211_TX_POWER_FIXED; /* TODO: do regulatory check! */ } else { /* * Automatic power level setting, max being the value * passed in from userland. */ if (data->txpower.value < 0) { type = NL80211_TX_POWER_AUTOMATIC; } else { dbm = data->txpower.value; type = NL80211_TX_POWER_LIMITED; } } } else { if (rfkill_set_sw_state(rdev->wiphy.rfkill, true)) schedule_work(&rdev->rfkill_block); return 0; } guard(wiphy)(&rdev->wiphy); return rdev_set_tx_power(rdev, wdev, -1, type, DBM_TO_MBM(dbm)); } static int cfg80211_wext_giwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err, val; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; scoped_guard(wiphy, &rdev->wiphy) { err = rdev_get_tx_power(rdev, wdev, -1, 0, &val); } if (err) return err; /* well... oh well */ data->txpower.fixed = 1; data->txpower.disabled = rfkill_blocked(rdev->wiphy.rfkill); data->txpower.value = val; data->txpower.flags = IW_TXPOW_DBM; return 0; } static int cfg80211_set_auth_alg(struct wireless_dev *wdev, s32 auth_alg) { int nr_alg = 0; if (!auth_alg) return -EINVAL; if (auth_alg & ~(IW_AUTH_ALG_OPEN_SYSTEM | IW_AUTH_ALG_SHARED_KEY | IW_AUTH_ALG_LEAP)) return -EINVAL; if (auth_alg & IW_AUTH_ALG_OPEN_SYSTEM) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } if (auth_alg & IW_AUTH_ALG_SHARED_KEY) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_SHARED_KEY; } if (auth_alg & IW_AUTH_ALG_LEAP) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; } if (nr_alg > 1) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; return 0; } static int cfg80211_set_wpa_version(struct wireless_dev *wdev, u32 wpa_versions) { if (wpa_versions & ~(IW_AUTH_WPA_VERSION_WPA | IW_AUTH_WPA_VERSION_WPA2| IW_AUTH_WPA_VERSION_DISABLED)) return -EINVAL; if ((wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) && (wpa_versions & (IW_AUTH_WPA_VERSION_WPA| IW_AUTH_WPA_VERSION_WPA2))) return -EINVAL; if (wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) wdev->wext.connect.crypto.wpa_versions &= ~(NL80211_WPA_VERSION_1|NL80211_WPA_VERSION_2); if (wpa_versions & IW_AUTH_WPA_VERSION_WPA) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_1; if (wpa_versions & IW_AUTH_WPA_VERSION_WPA2) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_2; return 0; } static int cfg80211_set_cipher_group(struct wireless_dev *wdev, u32 cipher) { if (cipher & IW_AUTH_CIPHER_WEP40) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP40; else if (cipher & IW_AUTH_CIPHER_WEP104) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP104; else if (cipher & IW_AUTH_CIPHER_TKIP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_TKIP; else if (cipher & IW_AUTH_CIPHER_CCMP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_CCMP; else if (cipher & IW_AUTH_CIPHER_AES_CMAC) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_AES_CMAC; else if (cipher & IW_AUTH_CIPHER_NONE) wdev->wext.connect.crypto.cipher_group = 0; else return -EINVAL; return 0; } static int cfg80211_set_cipher_pairwise(struct wireless_dev *wdev, u32 cipher) { int nr_ciphers = 0; u32 *ciphers_pairwise = wdev->wext.connect.crypto.ciphers_pairwise; if (cipher & IW_AUTH_CIPHER_WEP40) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP40; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_WEP104) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP104; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_TKIP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_TKIP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_CCMP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_CCMP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_AES_CMAC) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_AES_CMAC; nr_ciphers++; } BUILD_BUG_ON(NL80211_MAX_NR_CIPHER_SUITES < 5); wdev->wext.connect.crypto.n_ciphers_pairwise = nr_ciphers; return 0; } static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) { int nr_akm_suites = 0; if (key_mgt & ~(IW_AUTH_KEY_MGMT_802_1X | IW_AUTH_KEY_MGMT_PSK)) return -EINVAL; if (key_mgt & IW_AUTH_KEY_MGMT_802_1X) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_8021X; nr_akm_suites++; } if (key_mgt & IW_AUTH_KEY_MGMT_PSK) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_PSK; nr_akm_suites++; } wdev->wext.connect.crypto.n_akm_suites = nr_akm_suites; return 0; } static int cfg80211_wext_siwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *data = &wrqu->param; struct wireless_dev *wdev = dev->ieee80211_ptr; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; switch (data->flags & IW_AUTH_INDEX) { case IW_AUTH_PRIVACY_INVOKED: wdev->wext.connect.privacy = data->value; return 0; case IW_AUTH_WPA_VERSION: return cfg80211_set_wpa_version(wdev, data->value); case IW_AUTH_CIPHER_GROUP: return cfg80211_set_cipher_group(wdev, data->value); case IW_AUTH_KEY_MGMT: return cfg80211_set_key_mgt(wdev, data->value); case IW_AUTH_CIPHER_PAIRWISE: return cfg80211_set_cipher_pairwise(wdev, data->value); case IW_AUTH_80211_AUTH_ALG: return cfg80211_set_auth_alg(wdev, data->value); case IW_AUTH_WPA_ENABLED: case IW_AUTH_RX_UNENCRYPTED_EAPOL: case IW_AUTH_DROP_UNENCRYPTED: case IW_AUTH_MFP: return 0; default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { /* XXX: what do we need? */ return -EOPNOTSUPP; } static int cfg80211_wext_siwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); bool ps; int timeout = wdev->ps_timeout; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (!rdev->ops->set_power_mgmt) return -EOPNOTSUPP; if (wrq->disabled) { ps = false; } else { switch (wrq->flags & IW_POWER_MODE) { case IW_POWER_ON: /* If not specified */ case IW_POWER_MODE: /* If set all mask */ case IW_POWER_ALL_R: /* If explicitly state all */ ps = true; break; default: /* Otherwise we ignore */ return -EINVAL; } if (wrq->flags & ~(IW_POWER_MODE | IW_POWER_TIMEOUT)) return -EINVAL; if (wrq->flags & IW_POWER_TIMEOUT) timeout = wrq->value / 1000; } guard(wiphy)(&rdev->wiphy); err = rdev_set_power_mgmt(rdev, dev, ps, timeout); if (err) return err; wdev->ps = ps; wdev->ps_timeout = timeout; return 0; } static int cfg80211_wext_giwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; wrq->disabled = !wdev->ps; return 0; } static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bitrate_mask mask; u32 fixed, maxrate; struct ieee80211_supported_band *sband; bool match = false; int band, ridx; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; memset(&mask, 0, sizeof(mask)); fixed = 0; maxrate = (u32)-1; if (rate->value < 0) { /* nothing */ } else if (rate->fixed) { fixed = rate->value / 100000; } else { maxrate = rate->value / 100000; } for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wdev->wiphy->bands[band]; if (sband == NULL) continue; for (ridx = 0; ridx < sband->n_bitrates; ridx++) { struct ieee80211_rate *srate = &sband->bitrates[ridx]; if (fixed == srate->bitrate) { mask.control[band].legacy = 1 << ridx; match = true; break; } if (srate->bitrate <= maxrate) { mask.control[band].legacy |= 1 << ridx; match = true; } } } if (!match) return -EINVAL; guard(wiphy)(&rdev->wiphy); if (dev->ieee80211_ptr->valid_links) return -EOPNOTSUPP; return rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); } static int cfg80211_wext_giwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct station_info sinfo = {}; u8 addr[ETH_ALEN]; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!rdev->ops->get_station) return -EOPNOTSUPP; err = 0; if (!wdev->valid_links && wdev->links[0].client.current_bss) memcpy(addr, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else err = -EOPNOTSUPP; if (err) return err; scoped_guard(wiphy, &rdev->wiphy) { err = rdev_get_station(rdev, dev, addr, &sinfo); } if (err) return err; if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { err = -EOPNOTSUPP; goto free; } rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); free: cfg80211_sinfo_release_content(&sinfo); return err; } /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); /* we are under RTNL - globally locked - so can use static structs */ static struct iw_statistics wstats; static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; int ret; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) return NULL; if (!rdev->ops->get_station) return NULL; /* Grab BSSID of current BSS, if any */ wiphy_lock(&rdev->wiphy); if (wdev->valid_links || !wdev->links[0].client.current_bss) { wiphy_unlock(&rdev->wiphy); return NULL; } memcpy(bssid, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); memset(&sinfo, 0, sizeof(sinfo)); ret = rdev_get_station(rdev, dev, bssid, &sinfo); wiphy_unlock(&rdev->wiphy); if (ret) return NULL; memset(&wstats, 0, sizeof(wstats)); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { int sig = sinfo.signal; wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.updated |= IW_QUAL_DBM; wstats.qual.level = sig; if (sig < -110) sig = -110; else if (sig > -40) sig = -40; wstats.qual.qual = sig + 110; break; } fallthrough; case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.level = sinfo.signal; wstats.qual.qual = sinfo.signal; break; } fallthrough; default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC)) wstats.discard.misc = sinfo.rx_dropped_misc; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; cfg80211_sinfo_release_content(&sinfo); return &wstats; } static int cfg80211_wext_siwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); default: return -EOPNOTSUPP; } } static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwessid(dev, info, data, ssid); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_siwessid(dev, info, data, ssid); default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); data->flags = 0; data->length = 0; guard(wiphy)(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); case NL80211_IFTYPE_STATION: return cfg80211_mgd_wext_giwessid(dev, info, data, ssid); default: return -EOPNOTSUPP; } } static int cfg80211_wext_siwpmksa(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmksa cfg_pmksa; struct iw_pmksa *pmksa = (struct iw_pmksa *)extra; memset(&cfg_pmksa, 0, sizeof(struct cfg80211_pmksa)); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; cfg_pmksa.bssid = pmksa->bssid.sa_data; cfg_pmksa.pmkid = pmksa->pmkid; guard(wiphy)(&rdev->wiphy); switch (pmksa->cmd) { case IW_PMKSA_ADD: if (!rdev->ops->set_pmksa) return -EOPNOTSUPP; return rdev_set_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_REMOVE: if (!rdev->ops->del_pmksa) return -EOPNOTSUPP; return rdev_del_pmksa(rdev, dev, &cfg_pmksa); case IW_PMKSA_FLUSH: if (!rdev->ops->flush_pmksa) return -EOPNOTSUPP; return rdev_flush_pmksa(rdev, dev); default: return -EOPNOTSUPP; } } static const iw_handler cfg80211_handlers[] = { IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), IW_HANDLER(SIOCSIWFREQ, cfg80211_wext_siwfreq), IW_HANDLER(SIOCGIWFREQ, cfg80211_wext_giwfreq), IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), IW_HANDLER(SIOCSIWAP, cfg80211_wext_siwap), IW_HANDLER(SIOCGIWAP, cfg80211_wext_giwap), IW_HANDLER(SIOCSIWMLME, cfg80211_wext_siwmlme), IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), IW_HANDLER(SIOCSIWESSID, cfg80211_wext_siwessid), IW_HANDLER(SIOCGIWESSID, cfg80211_wext_giwessid), IW_HANDLER(SIOCSIWRATE, cfg80211_wext_siwrate), IW_HANDLER(SIOCGIWRATE, cfg80211_wext_giwrate), IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), IW_HANDLER(SIOCSIWTXPOW, cfg80211_wext_siwtxpower), IW_HANDLER(SIOCGIWTXPOW, cfg80211_wext_giwtxpower), IW_HANDLER(SIOCSIWRETRY, cfg80211_wext_siwretry), IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), IW_HANDLER(SIOCSIWENCODE, cfg80211_wext_siwencode), IW_HANDLER(SIOCGIWENCODE, cfg80211_wext_giwencode), IW_HANDLER(SIOCSIWPOWER, cfg80211_wext_siwpower), IW_HANDLER(SIOCGIWPOWER, cfg80211_wext_giwpower), IW_HANDLER(SIOCSIWGENIE, cfg80211_wext_siwgenie), IW_HANDLER(SIOCSIWAUTH, cfg80211_wext_siwauth), IW_HANDLER(SIOCGIWAUTH, cfg80211_wext_giwauth), IW_HANDLER(SIOCSIWENCODEEXT, cfg80211_wext_siwencodeext), IW_HANDLER(SIOCSIWPMKSA, cfg80211_wext_siwpmksa), }; const struct iw_handler_def cfg80211_wext_handler = { .num_standard = ARRAY_SIZE(cfg80211_handlers), .standard = cfg80211_handlers, .get_wireless_stats = cfg80211_wireless_stats, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2020 Red Hat, Inc. * Author: Jason Wang <jasowang@redhat.com> * * IOTLB implementation for vhost. */ #include <linux/slab.h> #include <linux/vhost_iotlb.h> #include <linux/module.h> #define MOD_VERSION "0.1" #define MOD_DESC "VHOST IOTLB" #define MOD_AUTHOR "Jason Wang <jasowang@redhat.com>" #define MOD_LICENSE "GPL v2" #define START(map) ((map)->start) #define LAST(map) ((map)->last) INTERVAL_TREE_DEFINE(struct vhost_iotlb_map, rb, __u64, __subtree_last, START, LAST, static inline, vhost_iotlb_itree); /** * vhost_iotlb_map_free - remove a map node and free it * @iotlb: the IOTLB * @map: the map that want to be remove and freed */ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb, struct vhost_iotlb_map *map) { vhost_iotlb_itree_remove(map, &iotlb->root); list_del(&map->link); kfree(map); iotlb->nmaps--; } EXPORT_SYMBOL_GPL(vhost_iotlb_map_free); /** * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB * @iotlb: the IOTLB * @start: start of the IOVA range * @last: last of IOVA range * @addr: the address that is mapped to @start * @perm: access permission of this range * @opaque: the opaque pointer for the new mapping * * Returns an error last is smaller than start or memory allocation * fails */ int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm, void *opaque) { struct vhost_iotlb_map *map; if (last < start) return -EFAULT; /* If the range being mapped is [0, ULONG_MAX], split it into two entries * otherwise its size would overflow u64. */ if (start == 0 && last == ULONG_MAX) { u64 mid = last / 2; int err = vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, perm, opaque); if (err) return err; addr += mid + 1; start = mid + 1; } if (iotlb->limit && iotlb->nmaps == iotlb->limit && iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { map = list_first_entry(&iotlb->list, typeof(*map), link); vhost_iotlb_map_free(iotlb, map); } map = kmalloc(sizeof(*map), GFP_ATOMIC); if (!map) return -ENOMEM; map->start = start; map->size = last - start + 1; map->last = last; map->addr = addr; map->perm = perm; map->opaque = opaque; iotlb->nmaps++; vhost_iotlb_itree_insert(map, &iotlb->root); INIT_LIST_HEAD(&map->link); list_add_tail(&map->link, &iotlb->list); return 0; } EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx); int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm) { return vhost_iotlb_add_range_ctx(iotlb, start, last, addr, perm, NULL); } EXPORT_SYMBOL_GPL(vhost_iotlb_add_range); /** * vhost_iotlb_del_range - delete overlapped ranges from vhost IOTLB * @iotlb: the IOTLB * @start: start of the IOVA range * @last: last of IOVA range */ void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last) { struct vhost_iotlb_map *map; while ((map = vhost_iotlb_itree_iter_first(&iotlb->root, start, last))) vhost_iotlb_map_free(iotlb, map); } EXPORT_SYMBOL_GPL(vhost_iotlb_del_range); /** * vhost_iotlb_init - initialize a vhost IOTLB * @iotlb: the IOTLB that needs to be initialized * @limit: maximum number of IOTLB entries * @flags: VHOST_IOTLB_FLAG_XXX */ void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, unsigned int flags) { iotlb->root = RB_ROOT_CACHED; iotlb->limit = limit; iotlb->nmaps = 0; iotlb->flags = flags; INIT_LIST_HEAD(&iotlb->list); } EXPORT_SYMBOL_GPL(vhost_iotlb_init); /** * vhost_iotlb_alloc - add a new vhost IOTLB * @limit: maximum number of IOTLB entries * @flags: VHOST_IOTLB_FLAG_XXX * * Returns an error is memory allocation fails */ struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags) { struct vhost_iotlb *iotlb = kzalloc(sizeof(*iotlb), GFP_KERNEL); if (!iotlb) return NULL; vhost_iotlb_init(iotlb, limit, flags); return iotlb; } EXPORT_SYMBOL_GPL(vhost_iotlb_alloc); /** * vhost_iotlb_reset - reset vhost IOTLB (free all IOTLB entries) * @iotlb: the IOTLB to be reset */ void vhost_iotlb_reset(struct vhost_iotlb *iotlb) { vhost_iotlb_del_range(iotlb, 0ULL, 0ULL - 1); } EXPORT_SYMBOL_GPL(vhost_iotlb_reset); /** * vhost_iotlb_free - reset and free vhost IOTLB * @iotlb: the IOTLB to be freed */ void vhost_iotlb_free(struct vhost_iotlb *iotlb) { if (iotlb) { vhost_iotlb_reset(iotlb); kfree(iotlb); } } EXPORT_SYMBOL_GPL(vhost_iotlb_free); /** * vhost_iotlb_itree_first - return the first overlapped range * @iotlb: the IOTLB * @start: start of IOVA range * @last: last byte in IOVA range */ struct vhost_iotlb_map * vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last) { return vhost_iotlb_itree_iter_first(&iotlb->root, start, last); } EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first); /** * vhost_iotlb_itree_next - return the next overlapped range * @map: the starting map node * @start: start of IOVA range * @last: last byte IOVA range */ struct vhost_iotlb_map * vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last) { return vhost_iotlb_itree_iter_next(map, start, last); } EXPORT_SYMBOL_GPL(vhost_iotlb_itree_next); MODULE_VERSION(MOD_VERSION); MODULE_DESCRIPTION(MOD_DESC); MODULE_AUTHOR(MOD_AUTHOR); MODULE_LICENSE(MOD_LICENSE); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/trace_events.h> #include <linux/thread_info.h> #include <asm/ptrace.h> /* * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) * @enter_fields: list of fields for syscall_enter trace event * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int syscall_nr; int nb_args; const char **types; const char **args; struct list_head enter_fields; struct trace_event_call *enter_event; struct trace_event_call *exit_event; }; #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) static inline void syscall_tracepoint_update(struct task_struct *p) { if (test_syscall_work(SYSCALL_TRACEPOINT)) set_task_syscall_work(p, SYSCALL_TRACEPOINT); else clear_task_syscall_work(p, SYSCALL_TRACEPOINT); } #else static inline void syscall_tracepoint_update(struct task_struct *p) { } #endif #endif /* _TRACE_SYSCALL_H */ |
| 133 389 13 15 4 288 307 11 14 9 3 3 2 8 296 296 8 8 10 10 8 8 8 4 4 4 4 4 8 8 3 5 8 1 1 8 8 2 4 1 1 1 1 1 4 7 16 16 16 7 6 1 1 1 1 9 9 9 3 9 9 8 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 188 188 188 3 3 3 3 188 188 188 186 4 4 4 4 4 5 1 2 1 1 1 4 3 1 1 1 1 1 1 1 1 1 1 1 13 13 14 2 14 14 14 14 14 14 14 14 13 12 7 4 9 9 9 9 9 4 4 4 4 4 4 15 15 267 267 140 137 3 9 9 9 140 141 109 106 6 6 5 2 2 5 71 77 14 8 15 349 342 14 329 329 44 40 4 161 157 9 9 11 11 11 11 11 7 294 287 12 12 12 11 62 61 61 383 186 186 287 282 9 189 189 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2011 STRATO. All rights reserved. */ #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/rbtree.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/btrfs.h> #include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" #include "disk-io.h" #include "locking.h" #include "ulist.h" #include "backref.h" #include "extent_io.h" #include "qgroup.h" #include "block-group.h" #include "sysfs.h" #include "tree-mod-log.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" #include "tree-checker.h" enum btrfs_qgroup_mode btrfs_qgroup_mode(const struct btrfs_fs_info *fs_info) { if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return BTRFS_QGROUP_MODE_DISABLED; if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) return BTRFS_QGROUP_MODE_SIMPLE; return BTRFS_QGROUP_MODE_FULL; } bool btrfs_qgroup_enabled(const struct btrfs_fs_info *fs_info) { return btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_DISABLED; } bool btrfs_qgroup_full_accounting(const struct btrfs_fs_info *fs_info) { return btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL; } /* * Helpers to access qgroup reservation * * Callers should ensure the lock context and type are valid */ static u64 qgroup_rsv_total(const struct btrfs_qgroup *qgroup) { u64 ret = 0; int i; for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) ret += qgroup->rsv.values[i]; return ret; } #ifdef CONFIG_BTRFS_DEBUG static const char *qgroup_rsv_type_str(enum btrfs_qgroup_rsv_type type) { if (type == BTRFS_QGROUP_RSV_DATA) return "data"; if (type == BTRFS_QGROUP_RSV_META_PERTRANS) return "meta_pertrans"; if (type == BTRFS_QGROUP_RSV_META_PREALLOC) return "meta_prealloc"; return NULL; } #endif static void qgroup_rsv_add(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup, u64 num_bytes, enum btrfs_qgroup_rsv_type type) { trace_btrfs_qgroup_update_reserve(fs_info, qgroup, num_bytes, type); qgroup->rsv.values[type] += num_bytes; } static void qgroup_rsv_release(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup, u64 num_bytes, enum btrfs_qgroup_rsv_type type) { trace_btrfs_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes, type); if (qgroup->rsv.values[type] >= num_bytes) { qgroup->rsv.values[type] -= num_bytes; return; } #ifdef CONFIG_BTRFS_DEBUG WARN_RATELIMIT(1, "qgroup %llu %s reserved space underflow, have %llu to free %llu", qgroup->qgroupid, qgroup_rsv_type_str(type), qgroup->rsv.values[type], num_bytes); #endif qgroup->rsv.values[type] = 0; } static void qgroup_rsv_add_by_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *dest, const struct btrfs_qgroup *src) { int i; for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) qgroup_rsv_add(fs_info, dest, src->rsv.values[i], i); } static void qgroup_rsv_release_by_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *dest, const struct btrfs_qgroup *src) { int i; for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) qgroup_rsv_release(fs_info, dest, src->rsv.values[i], i); } static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq, int mod) { if (qg->old_refcnt < seq) qg->old_refcnt = seq; qg->old_refcnt += mod; } static void btrfs_qgroup_update_new_refcnt(struct btrfs_qgroup *qg, u64 seq, int mod) { if (qg->new_refcnt < seq) qg->new_refcnt = seq; qg->new_refcnt += mod; } static inline u64 btrfs_qgroup_get_old_refcnt(const struct btrfs_qgroup *qg, u64 seq) { if (qg->old_refcnt < seq) return 0; return qg->old_refcnt - seq; } static inline u64 btrfs_qgroup_get_new_refcnt(const struct btrfs_qgroup *qg, u64 seq) { if (qg->new_refcnt < seq) return 0; return qg->new_refcnt - seq; } static int qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, int init_flags); static void qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info); static int btrfs_qgroup_qgroupid_key_cmp(const void *key, const struct rb_node *node) { const u64 *qgroupid = key; const struct btrfs_qgroup *qgroup = rb_entry(node, struct btrfs_qgroup, node); if (qgroup->qgroupid < *qgroupid) return -1; else if (qgroup->qgroupid > *qgroupid) return 1; return 0; } /* must be called with qgroup_ioctl_lock held */ static struct btrfs_qgroup *find_qgroup_rb(const struct btrfs_fs_info *fs_info, u64 qgroupid) { struct rb_node *node; node = rb_find(&qgroupid, &fs_info->qgroup_tree, btrfs_qgroup_qgroupid_key_cmp); return rb_entry_safe(node, struct btrfs_qgroup, node); } static int btrfs_qgroup_qgroupid_cmp(struct rb_node *new, const struct rb_node *existing) { const struct btrfs_qgroup *new_qgroup = rb_entry(new, struct btrfs_qgroup, node); return btrfs_qgroup_qgroupid_key_cmp(&new_qgroup->qgroupid, existing); } /* * Add qgroup to the filesystem's qgroup tree. * * Must be called with qgroup_lock held and @prealloc preallocated. * * The control on the lifespan of @prealloc would be transferred to this * function, thus caller should no longer touch @prealloc. */ static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *prealloc, u64 qgroupid) { struct rb_node *node; /* Caller must have pre-allocated @prealloc. */ ASSERT(prealloc); prealloc->qgroupid = qgroupid; node = rb_find_add(&prealloc->node, &fs_info->qgroup_tree, btrfs_qgroup_qgroupid_cmp); if (node) { kfree(prealloc); return rb_entry(node, struct btrfs_qgroup, node); } INIT_LIST_HEAD(&prealloc->groups); INIT_LIST_HEAD(&prealloc->members); INIT_LIST_HEAD(&prealloc->dirty); INIT_LIST_HEAD(&prealloc->iterator); INIT_LIST_HEAD(&prealloc->nested_iterator); return prealloc; } static void __del_qgroup_rb(struct btrfs_qgroup *qgroup) { struct btrfs_qgroup_list *list; list_del(&qgroup->dirty); while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, struct btrfs_qgroup_list, next_group); list_del(&list->next_group); list_del(&list->next_member); kfree(list); } while (!list_empty(&qgroup->members)) { list = list_first_entry(&qgroup->members, struct btrfs_qgroup_list, next_member); list_del(&list->next_group); list_del(&list->next_member); kfree(list); } } /* must be called with qgroup_lock held */ static int del_qgroup_rb(struct btrfs_fs_info *fs_info, u64 qgroupid) { struct btrfs_qgroup *qgroup = find_qgroup_rb(fs_info, qgroupid); if (!qgroup) return -ENOENT; rb_erase(&qgroup->node, &fs_info->qgroup_tree); __del_qgroup_rb(qgroup); return 0; } /* * Add relation specified by two qgroups. * * Must be called with qgroup_lock held, the ownership of @prealloc is * transferred to this function and caller should not touch it anymore. * * Return: 0 on success * -ENOENT if one of the qgroups is NULL * <0 other errors */ static int __add_relation_rb(struct btrfs_qgroup_list *prealloc, struct btrfs_qgroup *member, struct btrfs_qgroup *parent) { if (!member || !parent) { kfree(prealloc); return -ENOENT; } prealloc->group = parent; prealloc->member = member; list_add_tail(&prealloc->next_group, &member->groups); list_add_tail(&prealloc->next_member, &parent->members); return 0; } /* * Add relation specified by two qgroup ids. * * Must be called with qgroup_lock held. * * Return: 0 on success * -ENOENT if one of the ids does not exist * <0 other errors */ static int add_relation_rb(struct btrfs_fs_info *fs_info, struct btrfs_qgroup_list *prealloc, u64 memberid, u64 parentid) { struct btrfs_qgroup *member; struct btrfs_qgroup *parent; member = find_qgroup_rb(fs_info, memberid); parent = find_qgroup_rb(fs_info, parentid); return __add_relation_rb(prealloc, member, parent); } /* Must be called with qgroup_lock held */ static int del_relation_rb(struct btrfs_fs_info *fs_info, u64 memberid, u64 parentid) { struct btrfs_qgroup *member; struct btrfs_qgroup *parent; struct btrfs_qgroup_list *list; member = find_qgroup_rb(fs_info, memberid); parent = find_qgroup_rb(fs_info, parentid); if (!member || !parent) return -ENOENT; list_for_each_entry(list, &member->groups, next_group) { if (list->group == parent) { list_del(&list->next_group); list_del(&list->next_member); kfree(list); return 0; } } return -ENOENT; } #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int btrfs_verify_qgroup_counts(const struct btrfs_fs_info *fs_info, u64 qgroupid, u64 rfer, u64 excl) { struct btrfs_qgroup *qgroup; qgroup = find_qgroup_rb(fs_info, qgroupid); if (!qgroup) return -EINVAL; if (qgroup->rfer != rfer || qgroup->excl != excl) return -EINVAL; return 0; } #endif __printf(2, 3) static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info, const char *fmt, ...) { const u64 old_flags = fs_info->qgroup_flags; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) return; fs_info->qgroup_flags |= (BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT | BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN | BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING); if (!(old_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; btrfs_warn_rl(fs_info, "qgroup marked inconsistent, %pV", &vaf); va_end(args); } } static void qgroup_read_enable_gen(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, int slot, struct btrfs_qgroup_status_item *ptr) { ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)); ASSERT(btrfs_item_size(leaf, slot) >= sizeof(*ptr)); fs_info->qgroup_enable_gen = btrfs_qgroup_status_enable_gen(leaf, ptr); } /* * The full config is read in one go, only called from open_ctree() * It doesn't use any locking, as at this point we're still single-threaded */ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) { struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *quota_root = fs_info->quota_root; struct btrfs_path *path = NULL; struct extent_buffer *l; int slot; int ret = 0; u64 flags = 0; u64 rescan_progress = 0; if (!fs_info->quota_root) return 0; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; /* default this to quota off, in case no status key is found */ fs_info->qgroup_flags = 0; /* * pass 1: read status, all qgroup infos and limits */ key.objectid = 0; key.type = 0; key.offset = 0; ret = btrfs_search_slot_for_read(quota_root, &key, path, 1, 1); if (ret) goto out; while (1) { struct btrfs_qgroup *qgroup; slot = path->slots[0]; l = path->nodes[0]; btrfs_item_key_to_cpu(l, &found_key, slot); if (found_key.type == BTRFS_QGROUP_STATUS_KEY) { struct btrfs_qgroup_status_item *ptr; ptr = btrfs_item_ptr(l, slot, struct btrfs_qgroup_status_item); if (btrfs_qgroup_status_version(l, ptr) != BTRFS_QGROUP_STATUS_VERSION) { btrfs_err(fs_info, "old qgroup version, quota disabled"); goto out; } fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr); if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) qgroup_read_enable_gen(fs_info, l, slot, ptr); else if (btrfs_qgroup_status_generation(l, ptr) != fs_info->generation) qgroup_mark_inconsistent(fs_info, "qgroup generation mismatch"); rescan_progress = btrfs_qgroup_status_rescan(l, ptr); goto next1; } if (found_key.type != BTRFS_QGROUP_INFO_KEY && found_key.type != BTRFS_QGROUP_LIMIT_KEY) goto next1; qgroup = find_qgroup_rb(fs_info, found_key.offset); if ((qgroup && found_key.type == BTRFS_QGROUP_INFO_KEY) || (!qgroup && found_key.type == BTRFS_QGROUP_LIMIT_KEY)) qgroup_mark_inconsistent(fs_info, "inconsistent qgroup config"); if (!qgroup) { struct btrfs_qgroup *prealloc; struct btrfs_root *tree_root = fs_info->tree_root; prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL); if (!prealloc) { ret = -ENOMEM; goto out; } qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset); /* * If a qgroup exists for a subvolume ID, it is possible * that subvolume has been deleted, in which case * reusing that ID would lead to incorrect accounting. * * Ensure that we skip any such subvol ids. * * We don't need to lock because this is only called * during mount before we start doing things like creating * subvolumes. */ if (btrfs_is_fstree(qgroup->qgroupid) && qgroup->qgroupid > tree_root->free_objectid) /* * Don't need to check against BTRFS_LAST_FREE_OBJECTID, * as it will get checked on the next call to * btrfs_get_free_objectid. */ tree_root->free_objectid = qgroup->qgroupid + 1; } ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (ret < 0) goto out; switch (found_key.type) { case BTRFS_QGROUP_INFO_KEY: { struct btrfs_qgroup_info_item *ptr; ptr = btrfs_item_ptr(l, slot, struct btrfs_qgroup_info_item); qgroup->rfer = btrfs_qgroup_info_rfer(l, ptr); qgroup->rfer_cmpr = btrfs_qgroup_info_rfer_cmpr(l, ptr); qgroup->excl = btrfs_qgroup_info_excl(l, ptr); qgroup->excl_cmpr = btrfs_qgroup_info_excl_cmpr(l, ptr); /* generation currently unused */ break; } case BTRFS_QGROUP_LIMIT_KEY: { struct btrfs_qgroup_limit_item *ptr; ptr = btrfs_item_ptr(l, slot, struct btrfs_qgroup_limit_item); qgroup->lim_flags = btrfs_qgroup_limit_flags(l, ptr); qgroup->max_rfer = btrfs_qgroup_limit_max_rfer(l, ptr); qgroup->max_excl = btrfs_qgroup_limit_max_excl(l, ptr); qgroup->rsv_rfer = btrfs_qgroup_limit_rsv_rfer(l, ptr); qgroup->rsv_excl = btrfs_qgroup_limit_rsv_excl(l, ptr); break; } } next1: ret = btrfs_next_item(quota_root, path); if (ret < 0) goto out; if (ret) break; } btrfs_release_path(path); /* * pass 2: read all qgroup relations */ key.objectid = 0; key.type = BTRFS_QGROUP_RELATION_KEY; key.offset = 0; ret = btrfs_search_slot_for_read(quota_root, &key, path, 1, 0); if (ret) goto out; while (1) { struct btrfs_qgroup_list *list = NULL; slot = path->slots[0]; l = path->nodes[0]; btrfs_item_key_to_cpu(l, &found_key, slot); if (found_key.type != BTRFS_QGROUP_RELATION_KEY) goto next2; if (found_key.objectid > found_key.offset) { /* parent <- member, not needed to build config */ /* FIXME should we omit the key completely? */ goto next2; } list = kzalloc(sizeof(*list), GFP_KERNEL); if (!list) { ret = -ENOMEM; goto out; } ret = add_relation_rb(fs_info, list, found_key.objectid, found_key.offset); list = NULL; if (ret == -ENOENT) { btrfs_warn(fs_info, "orphan qgroup relation 0x%llx->0x%llx", found_key.objectid, found_key.offset); ret = 0; /* ignore the error */ } if (ret) goto out; next2: ret = btrfs_next_item(quota_root, path); if (ret < 0) goto out; if (ret) break; } out: btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (ret >= 0) { if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); } else { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; btrfs_sysfs_del_qgroups(fs_info); } return ret < 0 ? ret : 0; } /* * Called in close_ctree() when quota is still enabled. This verifies we don't * leak some reserved space. * * Return false if no reserved space is left. * Return true if some reserved space is leaked. */ bool btrfs_check_quota_leak(const struct btrfs_fs_info *fs_info) { struct rb_node *node; bool ret = false; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) return ret; /* * Since we're unmounting, there is no race and no need to grab qgroup * lock. And here we don't go post-order to provide a more user * friendly sorted result. */ for (node = rb_first(&fs_info->qgroup_tree); node; node = rb_next(node)) { struct btrfs_qgroup *qgroup; int i; qgroup = rb_entry(node, struct btrfs_qgroup, node); for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) { if (qgroup->rsv.values[i]) { ret = true; btrfs_warn(fs_info, "qgroup %hu/%llu has unreleased space, type %d rsv %llu", btrfs_qgroup_level(qgroup->qgroupid), btrfs_qgroup_subvolid(qgroup->qgroupid), i, qgroup->rsv.values[i]); } } } return ret; } /* * This is called from close_ctree() or open_ctree() or btrfs_quota_disable(), * first two are in single-threaded paths. */ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) { struct rb_node *n; struct btrfs_qgroup *qgroup; /* * btrfs_quota_disable() can be called concurrently with * btrfs_qgroup_rescan() -> qgroup_rescan_zero_tracking(), so take the * lock. */ spin_lock(&fs_info->qgroup_lock); while ((n = rb_first(&fs_info->qgroup_tree))) { qgroup = rb_entry(n, struct btrfs_qgroup, node); rb_erase(n, &fs_info->qgroup_tree); __del_qgroup_rb(qgroup); spin_unlock(&fs_info->qgroup_lock); btrfs_sysfs_del_one_qgroup(fs_info, qgroup); kfree(qgroup); spin_lock(&fs_info->qgroup_lock); } spin_unlock(&fs_info->qgroup_lock); btrfs_sysfs_del_qgroups(fs_info); } static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, u64 dst) { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = src; key.type = BTRFS_QGROUP_RELATION_KEY; key.offset = dst; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, 0); btrfs_free_path(path); return ret; } static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, u64 dst) { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = src; key.type = BTRFS_QGROUP_RELATION_KEY; key.offset = dst; ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) goto out; if (ret > 0) { ret = -ENOENT; goto out; } ret = btrfs_del_item(trans, quota_root, path); out: btrfs_free_path(path); return ret; } static int add_qgroup_item(struct btrfs_trans_handle *trans, struct btrfs_root *quota_root, u64 qgroupid) { int ret; struct btrfs_path *path; struct btrfs_qgroup_info_item *qgroup_info; struct btrfs_qgroup_limit_item *qgroup_limit; struct extent_buffer *leaf; struct btrfs_key key; if (btrfs_is_testing(quota_root->fs_info)) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = BTRFS_QGROUP_INFO_KEY; key.offset = qgroupid; /* * Avoid a transaction abort by catching -EEXIST here. In that * case, we proceed by re-initializing the existing structure * on disk. */ ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_info)); if (ret && ret != -EEXIST) goto out; leaf = path->nodes[0]; qgroup_info = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_qgroup_info_item); btrfs_set_qgroup_info_generation(leaf, qgroup_info, trans->transid); btrfs_set_qgroup_info_rfer(leaf, qgroup_info, 0); btrfs_set_qgroup_info_rfer_cmpr(leaf, qgroup_info, 0); btrfs_set_qgroup_info_excl(leaf, qgroup_info, 0); btrfs_set_qgroup_info_excl_cmpr(leaf, qgroup_info, 0); btrfs_release_path(path); key.type = BTRFS_QGROUP_LIMIT_KEY; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*qgroup_limit)); if (ret && ret != -EEXIST) goto out; leaf = path->nodes[0]; qgroup_limit = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_qgroup_limit_item); btrfs_set_qgroup_limit_flags(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_max_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_max_excl(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_excl(leaf, qgroup_limit, 0); ret = 0; out: btrfs_free_path(path); return ret; } static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid) { int ret; struct btrfs_root *quota_root = trans->fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = BTRFS_QGROUP_INFO_KEY; key.offset = qgroupid; ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) goto out; if (ret > 0) { ret = -ENOENT; goto out; } ret = btrfs_del_item(trans, quota_root, path); if (ret) goto out; btrfs_release_path(path); key.type = BTRFS_QGROUP_LIMIT_KEY; ret = btrfs_search_slot(trans, quota_root, &key, path, -1, 1); if (ret < 0) goto out; if (ret > 0) { ret = -ENOENT; goto out; } ret = btrfs_del_item(trans, quota_root, path); out: btrfs_free_path(path); return ret; } static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, struct btrfs_qgroup *qgroup) { struct btrfs_root *quota_root = trans->fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_limit_item *qgroup_limit; int ret; int slot; key.objectid = 0; key.type = BTRFS_QGROUP_LIMIT_KEY; key.offset = qgroup->qgroupid; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1); if (ret > 0) ret = -ENOENT; if (ret) goto out; l = path->nodes[0]; slot = path->slots[0]; qgroup_limit = btrfs_item_ptr(l, slot, struct btrfs_qgroup_limit_item); btrfs_set_qgroup_limit_flags(l, qgroup_limit, qgroup->lim_flags); btrfs_set_qgroup_limit_max_rfer(l, qgroup_limit, qgroup->max_rfer); btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, qgroup->max_excl); btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); out: btrfs_free_path(path); return ret; } static int update_qgroup_info_item(struct btrfs_trans_handle *trans, struct btrfs_qgroup *qgroup) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root = fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_info_item *qgroup_info; int ret; int slot; if (btrfs_is_testing(fs_info)) return 0; key.objectid = 0; key.type = BTRFS_QGROUP_INFO_KEY; key.offset = qgroup->qgroupid; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1); if (ret > 0) ret = -ENOENT; if (ret) goto out; l = path->nodes[0]; slot = path->slots[0]; qgroup_info = btrfs_item_ptr(l, slot, struct btrfs_qgroup_info_item); btrfs_set_qgroup_info_generation(l, qgroup_info, trans->transid); btrfs_set_qgroup_info_rfer(l, qgroup_info, qgroup->rfer); btrfs_set_qgroup_info_rfer_cmpr(l, qgroup_info, qgroup->rfer_cmpr); btrfs_set_qgroup_info_excl(l, qgroup_info, qgroup->excl); btrfs_set_qgroup_info_excl_cmpr(l, qgroup_info, qgroup->excl_cmpr); out: btrfs_free_path(path); return ret; } static int update_qgroup_status_item(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root = fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *l; struct btrfs_qgroup_status_item *ptr; int ret; int slot; key.objectid = 0; key.type = BTRFS_QGROUP_STATUS_KEY; key.offset = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1); if (ret > 0) ret = -ENOENT; if (ret) goto out; l = path->nodes[0]; slot = path->slots[0]; ptr = btrfs_item_ptr(l, slot, struct btrfs_qgroup_status_item); btrfs_set_qgroup_status_flags(l, ptr, fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_generation(l, ptr, trans->transid); btrfs_set_qgroup_status_rescan(l, ptr, fs_info->qgroup_rescan_progress.objectid); out: btrfs_free_path(path); return ret; } /* * called with qgroup_lock held */ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *leaf = NULL; int ret; int nr = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = 0; key.offset = 0; while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) goto out; leaf = path->nodes[0]; nr = btrfs_header_nritems(leaf); if (!nr) break; /* * delete the leaf one by one * since the whole tree is going * to be deleted. */ path->slots[0] = 0; ret = btrfs_del_items(trans, root, path, 0, nr); if (ret) goto out; btrfs_release_path(path); } ret = 0; out: btrfs_free_path(path); return ret; } int btrfs_quota_enable(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_quota_ctl_args *quota_ctl_args) { struct btrfs_root *quota_root; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_path *path = NULL; struct btrfs_qgroup_status_item *ptr; struct extent_buffer *leaf; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_qgroup *prealloc = NULL; struct btrfs_trans_handle *trans = NULL; const bool simple = (quota_ctl_args->cmd == BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA); int ret = 0; int slot; /* * We need to have subvol_sem write locked, to prevent races between * concurrent tasks trying to enable quotas, because we will unlock * and relock qgroup_ioctl_lock before setting fs_info->quota_root * and before setting BTRFS_FS_QUOTA_ENABLED. */ lockdep_assert_held_write(&fs_info->subvol_sem); if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) { btrfs_err(fs_info, "qgroups are currently unsupported in extent tree v2"); return -EINVAL; } mutex_lock(&fs_info->qgroup_ioctl_lock); if (fs_info->quota_root) goto out; ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; /* * Unlock qgroup_ioctl_lock before starting the transaction. This is to * avoid lock acquisition inversion problems (reported by lockdep) between * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we * start a transaction. * After we started the transaction lock qgroup_ioctl_lock again and * check if someone else created the quota root in the meanwhile. If so, * just return success and release the transaction handle. * * Also we don't need to worry about someone else calling * btrfs_sysfs_add_qgroups() after we unlock and getting an error because * that function returns 0 (success) when the sysfs entries already exist. */ mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item * * Yet we also need 2*n items for a QGROUP_INFO/QGROUP_LIMIT items * per subvolume. However those are not currently reserved since it * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } if (fs_info->quota_root) goto out; /* * initially create the quota tree */ quota_root = btrfs_create_tree(trans, BTRFS_QUOTA_TREE_OBJECTID); if (IS_ERR(quota_root)) { ret = PTR_ERR(quota_root); btrfs_abort_transaction(trans, ret); goto out; } path = btrfs_alloc_path(); if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); goto out_free_root; } key.objectid = 0; key.type = BTRFS_QGROUP_STATUS_KEY; key.offset = 0; ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*ptr)); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } leaf = path->nodes[0]; ptr = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_qgroup_status_item); btrfs_set_qgroup_status_generation(leaf, ptr, trans->transid); btrfs_set_qgroup_status_version(leaf, ptr, BTRFS_QGROUP_STATUS_VERSION); fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } btrfs_set_qgroup_status_flags(leaf, ptr, fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); key.objectid = 0; key.type = BTRFS_ROOT_REF_KEY; key.offset = 0; btrfs_release_path(path); ret = btrfs_search_slot_for_read(tree_root, &key, path, 1, 0); if (ret > 0) goto out_add_root; if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } while (1) { slot = path->slots[0]; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.type == BTRFS_ROOT_REF_KEY) { /* Release locks on tree_root before we access quota_root */ btrfs_release_path(path); /* We should not have a stray @prealloc pointer. */ ASSERT(prealloc == NULL); prealloc = kzalloc(sizeof(*prealloc), GFP_NOFS); if (unlikely(!prealloc)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); goto out_free_path; } ret = add_qgroup_item(trans, quota_root, found_key.offset); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset); prealloc = NULL; ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } ret = btrfs_search_slot_for_read(tree_root, &found_key, path, 1, 0); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } if (ret > 0) { /* * Shouldn't happen, but in case it does we * don't need to do the btrfs_next_item, just * continue. */ continue; } } ret = btrfs_next_item(tree_root, path); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } if (ret) break; } out_add_root: btrfs_release_path(path); ret = add_qgroup_item(trans, quota_root, BTRFS_FS_TREE_OBJECTID); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } ASSERT(prealloc == NULL); prealloc = kzalloc(sizeof(*prealloc), GFP_NOFS); if (!prealloc) { ret = -ENOMEM; goto out_free_path; } qgroup = add_qgroup_rb(fs_info, prealloc, BTRFS_FS_TREE_OBJECTID); prealloc = NULL; ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); goto out_free_path; } fs_info->qgroup_enable_gen = trans->transid; mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * Commit the transaction while not holding qgroup_ioctl_lock, to avoid * a deadlock with tasks concurrently doing other qgroup operations, such * adding/removing qgroups or adding/deleting qgroup relations for example, * because all qgroup operations first start or join a transaction and then * lock the qgroup_ioctl_lock mutex. * We are safe from a concurrent task trying to enable quotas, by calling * this function, since we are serialized by fs_info->subvol_sem. */ ret = btrfs_commit_transaction(trans); trans = NULL; mutex_lock(&fs_info->qgroup_ioctl_lock); if (ret) goto out_free_path; /* * Set quota enabled flag after committing the transaction, to avoid * deadlocks on fs_info->qgroup_ioctl_lock with concurrent snapshot * creation. */ spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) goto out_free_path; ret = qgroup_rescan_init(fs_info, 0, 1); if (!ret) { qgroup_rescan_zero_tracking(fs_info); fs_info->qgroup_rescan_running = true; btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); } else { /* * We have set both BTRFS_FS_QUOTA_ENABLED and * BTRFS_QGROUP_STATUS_FLAG_ON, so we can only fail with * -EINPROGRESS. That can happen because someone started the * rescan worker by calling quota rescan ioctl before we * attempted to initialize the rescan worker. Failure due to * quotas disabled in the meanwhile is not possible, because * we are holding a write lock on fs_info->subvol_sem, which * is also acquired when disabling quotas. * Ignore such error, and any other error would need to undo * everything we did in the transaction we just committed. */ ASSERT(ret == -EINPROGRESS); ret = 0; } out_free_path: btrfs_free_path(path); out_free_root: if (ret) btrfs_put_root(quota_root); out: if (ret) btrfs_sysfs_del_qgroups(fs_info); mutex_unlock(&fs_info->qgroup_ioctl_lock); if (ret && trans) btrfs_end_transaction(trans); else if (trans) ret = btrfs_end_transaction(trans); kfree(prealloc); return ret; } /* * It is possible to have outstanding ordered extents which reserved bytes * before we disabled. We need to fully flush delalloc, ordered extents, and a * commit to ensure that we don't leak such reservations, only to have them * come back if we re-enable. * * - enable simple quotas * - reserve space * - release it, store rsv_bytes in OE * - disable quotas * - enable simple quotas (qgroup rsv are all 0) * - OE finishes * - run delayed refs * - free rsv_bytes, resulting in miscounting or even underflow */ static int flush_reservations(struct btrfs_fs_info *fs_info) { int ret; ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) return ret; btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); return btrfs_commit_current_transaction(fs_info->tree_root); } int btrfs_quota_disable(struct btrfs_fs_info *fs_info) { struct btrfs_root *quota_root = NULL; struct btrfs_trans_handle *trans = NULL; int ret = 0; /* * We need to have subvol_sem write locked to prevent races with * snapshot creation. */ lockdep_assert_held_write(&fs_info->subvol_sem); /* * Relocation will mess with backrefs, so make sure we have the * cleaner_mutex held to protect us from relocate. */ lockdep_assert_held(&fs_info->cleaner_mutex); mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; /* * Unlock the qgroup_ioctl_lock mutex before waiting for the rescan worker to * complete. Otherwise we can deadlock because btrfs_remove_qgroup() needs * to lock that mutex while holding a transaction handle and the rescan * worker needs to commit a transaction. */ mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * Request qgroup rescan worker to complete and wait for it. This wait * must be done before transaction start for quota disable since it may * deadlock with transaction by the qgroup rescan worker. */ clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); /* * We have nothing held here and no trans handle, just return the error * if there is one and set back the quota enabled bit since we didn't * actually disable quotas. */ ret = flush_reservations(fs_info); if (ret) { set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); return ret; } /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. * * Also, we must always start a transaction without holding the mutex * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); goto out; } if (!fs_info->quota_root) goto out; spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; fs_info->qgroup_drop_subtree_thres = BTRFS_QGROUP_DROP_SUBTREE_THRES_DEFAULT; spin_unlock(&fs_info->qgroup_lock); btrfs_free_qgroup_config(fs_info); ret = btrfs_clean_quota_tree(trans, quota_root); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } spin_lock(&fs_info->trans_lock); list_del("a_root->dirty_list); spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(quota_root->node); btrfs_clear_buffer_dirty(trans, quota_root->node); btrfs_tree_unlock(quota_root->node); ret = btrfs_free_tree_block(trans, btrfs_root_id(quota_root), quota_root->node, 0, 1); if (ret < 0) btrfs_abort_transaction(trans, ret); out: btrfs_put_root(quota_root); mutex_unlock(&fs_info->qgroup_ioctl_lock); if (ret && trans) btrfs_end_transaction(trans); else if (trans) ret = btrfs_commit_transaction(trans); return ret; } static void qgroup_dirty(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { if (list_empty(&qgroup->dirty)) list_add(&qgroup->dirty, &fs_info->dirty_qgroups); } static void qgroup_iterator_add(struct list_head *head, struct btrfs_qgroup *qgroup) { if (!list_empty(&qgroup->iterator)) return; list_add_tail(&qgroup->iterator, head); } static void qgroup_iterator_clean(struct list_head *head) { while (!list_empty(head)) { struct btrfs_qgroup *qgroup; qgroup = list_first_entry(head, struct btrfs_qgroup, iterator); list_del_init(&qgroup->iterator); } } /* * The easy accounting, we're updating qgroup relationship whose child qgroup * only has exclusive extents. * * In this case, all exclusive extents will also be exclusive for parent, so * excl/rfer just get added/removed. * * So is qgroup reservation space, which should also be added/removed to * parent. * Or when child tries to release reservation space, parent will underflow its * reservation (for relationship adding case). * * Caller should hold fs_info->qgroup_lock. */ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *src, int sign) { struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; u64 num_bytes_cmpr = src->excl_cmpr; int ret = 0; qgroup = find_qgroup_rb(fs_info, ref_root); if (!qgroup) goto out; qgroup_iterator_add(&qgroup_list, qgroup); list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; qgroup->rfer_cmpr += sign * num_bytes_cmpr; WARN_ON(sign < 0 && qgroup->excl < num_bytes); WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr); qgroup->excl += sign * num_bytes; qgroup->excl_cmpr += sign * num_bytes_cmpr; if (sign > 0) qgroup_rsv_add_by_qgroup(fs_info, qgroup, src); else qgroup_rsv_release_by_qgroup(fs_info, qgroup, src); qgroup_dirty(fs_info, qgroup); /* Append parent qgroups to @qgroup_list. */ list_for_each_entry(glist, &qgroup->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); } ret = 0; out: qgroup_iterator_clean(&qgroup_list); return ret; } /* * Quick path for updating qgroup with only excl refs. * * In that case, just update all parent will be enough. * Or we needs to do a full rescan. * Caller should also hold fs_info->qgroup_lock. * * Return 0 for quick update, return >0 for need to full rescan * and mark INCONSISTENT flag. * Return < 0 for other error. */ static int quick_update_accounting(struct btrfs_fs_info *fs_info, u64 src, u64 dst, int sign) { struct btrfs_qgroup *qgroup; int ret = 1; qgroup = find_qgroup_rb(fs_info, src); if (!qgroup) goto out; if (qgroup->excl == qgroup->rfer) { ret = __qgroup_excl_accounting(fs_info, dst, qgroup, sign); if (ret < 0) goto out; ret = 0; } out: if (ret) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; return ret; } /* * Add relation between @src and @dst qgroup. The @prealloc is allocated by the * callers and transferred here (either used or freed on error). */ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst, struct btrfs_qgroup_list *prealloc) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup *parent; struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; int ret = 0; ASSERT(prealloc); /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) { kfree(prealloc); return -EINVAL; } mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { ret = -ENOTCONN; goto out; } member = find_qgroup_rb(fs_info, src); parent = find_qgroup_rb(fs_info, dst); if (!member || !parent) { ret = -EINVAL; goto out; } /* check if such qgroup relation exist firstly */ list_for_each_entry(list, &member->groups, next_group) { if (list->group == parent) { ret = -EEXIST; goto out; } } ret = add_qgroup_relation_item(trans, src, dst); if (ret) goto out; ret = add_qgroup_relation_item(trans, dst, src); if (ret) { del_qgroup_relation_item(trans, src, dst); goto out; } spin_lock(&fs_info->qgroup_lock); ret = __add_relation_rb(prealloc, member, parent); prealloc = NULL; if (ret < 0) { spin_unlock(&fs_info->qgroup_lock); goto out; } ret = quick_update_accounting(fs_info, src, dst, 1); spin_unlock(&fs_info->qgroup_lock); out: kfree(prealloc); mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup *parent; struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; bool found = false; int ret = 0; int ret2; if (!fs_info->quota_root) { ret = -ENOTCONN; goto out; } member = find_qgroup_rb(fs_info, src); parent = find_qgroup_rb(fs_info, dst); /* * The parent/member pair doesn't exist, then try to delete the dead * relation items only. */ if (!member || !parent) goto delete_item; /* check if such qgroup relation exist firstly */ list_for_each_entry(list, &member->groups, next_group) { if (list->group == parent) { found = true; break; } } delete_item: ret = del_qgroup_relation_item(trans, src, dst); if (ret < 0 && ret != -ENOENT) goto out; ret2 = del_qgroup_relation_item(trans, dst, src); if (ret2 < 0 && ret2 != -ENOENT) goto out; /* At least one deletion succeeded, return 0 */ if (!ret || !ret2) ret = 0; if (found) { spin_lock(&fs_info->qgroup_lock); del_relation_rb(fs_info, src, dst); ret = quick_update_accounting(fs_info, src, dst, -1); spin_unlock(&fs_info->qgroup_lock); } out: return ret; } int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; mutex_lock(&fs_info->qgroup_ioctl_lock); ret = __del_qgroup_relation(trans, src, dst); mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root; struct btrfs_qgroup *qgroup; struct btrfs_qgroup *prealloc = NULL; int ret = 0; mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { ret = -ENOTCONN; goto out; } quota_root = fs_info->quota_root; qgroup = find_qgroup_rb(fs_info, qgroupid); if (qgroup) { ret = -EEXIST; goto out; } prealloc = kzalloc(sizeof(*prealloc), GFP_NOFS); if (!prealloc) { ret = -ENOMEM; goto out; } ret = add_qgroup_item(trans, quota_root, qgroupid); if (ret) goto out; spin_lock(&fs_info->qgroup_lock); qgroup = add_qgroup_rb(fs_info, prealloc, qgroupid); spin_unlock(&fs_info->qgroup_lock); prealloc = NULL; ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); kfree(prealloc); return ret; } /* * Return 0 if we can not delete the qgroup (not empty or has children etc). * Return >0 if we can delete the qgroup. * Return <0 for other errors during tree search. */ static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup) { struct btrfs_key key; struct btrfs_path *path; int ret; /* * Squota would never be inconsistent, but there can still be case * where a dropped subvolume still has qgroup numbers, and squota * relies on such qgroup for future accounting. * * So for squota, do not allow dropping any non-zero qgroup. */ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && (qgroup->rfer || qgroup->excl || qgroup->excl_cmpr || qgroup->rfer_cmpr)) return 0; /* For higher level qgroup, we can only delete it if it has no child. */ if (btrfs_qgroup_level(qgroup->qgroupid)) { if (!list_empty(&qgroup->members)) return 0; return 1; } /* * For level-0 qgroups, we can only delete it if it has no subvolume * for it. * This means even a subvolume is unlinked but not yet fully dropped, * we can not delete the qgroup. */ key.objectid = qgroup->qgroupid; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = -1ULL; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL); btrfs_free_path(path); /* * The @ret from btrfs_find_root() exactly matches our definition for * the return value, thus can be returned directly. */ return ret; } int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup *qgroup; struct btrfs_qgroup_list *list; int ret = 0; mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { ret = -ENOTCONN; goto out; } qgroup = find_qgroup_rb(fs_info, qgroupid); if (!qgroup) { ret = -ENOENT; goto out; } ret = can_delete_qgroup(fs_info, qgroup); if (ret < 0) goto out; if (ret == 0) { ret = -EBUSY; goto out; } /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; goto out; } ret = del_qgroup_item(trans, qgroupid); if (ret && ret != -ENOENT) goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, struct btrfs_qgroup_list, next_group); ret = __del_qgroup_relation(trans, qgroupid, list->group->qgroupid); if (ret) goto out; } spin_lock(&fs_info->qgroup_lock); /* * Warn on reserved space. The subvolume should has no child nor * corresponding subvolume. * Thus its reserved space should all be zero, no matter if qgroup * is consistent or the mode. */ if (qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] || qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] || qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]) { DEBUG_WARN(); btrfs_warn_rl(fs_info, "to be deleted qgroup %u/%llu has non-zero numbers, data %llu meta prealloc %llu meta pertrans %llu", btrfs_qgroup_level(qgroup->qgroupid), btrfs_qgroup_subvolid(qgroup->qgroupid), qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA], qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC], qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]); } /* * The same for rfer/excl numbers, but that's only if our qgroup is * consistent and if it's in regular qgroup mode. * For simple mode it's not as accurate thus we can hit non-zero values * very frequently. */ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL && !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) { if (qgroup->rfer || qgroup->excl || qgroup->rfer_cmpr || qgroup->excl_cmpr) { DEBUG_WARN(); qgroup_mark_inconsistent(fs_info, "to be deleted qgroup %u/%llu has non-zero numbers, rfer %llu rfer_cmpr %llu excl %llu excl_cmpr %llu", btrfs_qgroup_level(qgroup->qgroupid), btrfs_qgroup_subvolid(qgroup->qgroupid), qgroup->rfer, qgroup->rfer_cmpr, qgroup->excl, qgroup->excl_cmpr); } } del_qgroup_rb(fs_info, qgroupid); spin_unlock(&fs_info->qgroup_lock); /* * Remove the qgroup from sysfs now without holding the qgroup_lock * spinlock, since the sysfs_remove_group() function needs to take * the mutex kernfs_mutex through kernfs_remove_by_name_ns(). */ btrfs_sysfs_del_one_qgroup(fs_info, qgroup); kfree(qgroup); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 subvolid) { struct btrfs_trans_handle *trans; int ret; if (!btrfs_is_fstree(subvolid) || !btrfs_qgroup_enabled(fs_info) || !fs_info->quota_root) return 0; /* * Commit current transaction to make sure all the rfer/excl numbers * get updated. */ ret = btrfs_commit_current_transaction(fs_info->quota_root); if (ret < 0) return ret; /* Start new trans to delete the qgroup info and limit items. */ trans = btrfs_start_transaction(fs_info->quota_root, 2); if (IS_ERR(trans)) return PTR_ERR(trans); ret = btrfs_remove_qgroup(trans, subvolid); btrfs_end_transaction(trans); /* * It's squota and the subvolume still has numbers needed for future * accounting, in this case we can not delete it. Just skip it. * * Or the qgroup is already removed by a qgroup rescan. For both cases we're * safe to ignore them. */ if (ret == -EBUSY || ret == -ENOENT) ret = 0; return ret; } int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid, struct btrfs_qgroup_limit *limit) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup *qgroup; int ret = 0; /* Sometimes we would want to clear the limit on this qgroup. * To meet this requirement, we treat the -1 as a special value * which tell kernel to clear the limit on this qgroup. */ const u64 CLEAR_VALUE = -1; mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { ret = -ENOTCONN; goto out; } qgroup = find_qgroup_rb(fs_info, qgroupid); if (!qgroup) { ret = -ENOENT; goto out; } spin_lock(&fs_info->qgroup_lock); if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER) { if (limit->max_rfer == CLEAR_VALUE) { qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER; limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER; qgroup->max_rfer = 0; } else { qgroup->max_rfer = limit->max_rfer; } } if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) { if (limit->max_excl == CLEAR_VALUE) { qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL; limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL; qgroup->max_excl = 0; } else { qgroup->max_excl = limit->max_excl; } } if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER) { if (limit->rsv_rfer == CLEAR_VALUE) { qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER; limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER; qgroup->rsv_rfer = 0; } else { qgroup->rsv_rfer = limit->rsv_rfer; } } if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL) { if (limit->rsv_excl == CLEAR_VALUE) { qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL; limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL; qgroup->rsv_excl = 0; } else { qgroup->rsv_excl = limit->rsv_excl; } } qgroup->lim_flags |= limit->flags; spin_unlock(&fs_info->qgroup_lock); ret = update_qgroup_limit_item(trans, qgroup); if (ret) qgroup_mark_inconsistent(fs_info, "qgroup item update error %d", ret); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; } /* * Inform qgroup to trace one dirty extent, its info is recorded in @record. * So qgroup can account it at transaction committing time. * * No lock version, caller must acquire delayed ref lock and allocated memory, * then call btrfs_qgroup_trace_extent_post() after exiting lock context. * * Return 0 for success insert * Return >0 for existing record, caller can free @record safely. * Return <0 for insertion failure, caller can free @record safely. */ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_qgroup_extent_record *record, u64 bytenr) { struct btrfs_qgroup_extent_record *existing, *ret; const unsigned long index = (bytenr >> fs_info->sectorsize_bits); if (!btrfs_qgroup_full_accounting(fs_info)) return 1; #if BITS_PER_LONG == 32 if (bytenr >= MAX_LFS_FILESIZE) { btrfs_err_rl(fs_info, "qgroup record for extent at %llu is beyond 32bit page cache and xarray index limit", bytenr); btrfs_err_32bit_limit(fs_info); return -EOVERFLOW; } #endif trace_btrfs_qgroup_trace_extent(fs_info, record, bytenr); xa_lock(&delayed_refs->dirty_extents); existing = xa_load(&delayed_refs->dirty_extents, index); if (existing) { if (record->data_rsv && !existing->data_rsv) { existing->data_rsv = record->data_rsv; existing->data_rsv_refroot = record->data_rsv_refroot; } xa_unlock(&delayed_refs->dirty_extents); return 1; } ret = __xa_store(&delayed_refs->dirty_extents, index, record, GFP_ATOMIC); xa_unlock(&delayed_refs->dirty_extents); if (xa_is_err(ret)) { qgroup_mark_inconsistent(fs_info, "xarray insert error: %d", xa_err(ret)); return xa_err(ret); } return 0; } /* * Post handler after qgroup_trace_extent_nolock(). * * NOTE: Current qgroup does the expensive backref walk at transaction * committing time with TRANS_STATE_COMMIT_DOING, this blocks incoming * new transaction. * This is designed to allow btrfs_find_all_roots() to get correct new_roots * result. * * However for old_roots there is no need to do backref walk at that time, * since we search commit roots to walk backref and result will always be * correct. * * Due to the nature of no lock version, we can't do backref there. * So we must call btrfs_qgroup_trace_extent_post() after exiting * spinlock context. * * TODO: If we can fix and prove btrfs_find_all_roots() can get correct result * using current root, then we can move all expensive backref walk out of * transaction committing, but not now as qgroup accounting will be wrong again. */ int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans, struct btrfs_qgroup_extent_record *qrecord, u64 bytenr) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_backref_walk_ctx ctx = { .bytenr = bytenr, .fs_info = fs_info, }; int ret; if (!btrfs_qgroup_full_accounting(fs_info)) return 0; /* * We are always called in a context where we are already holding a * transaction handle. Often we are called when adding a data delayed * reference from btrfs_truncate_inode_items() (truncating or unlinking), * in which case we will be holding a write lock on extent buffer from a * subvolume tree. In this case we can't allow btrfs_find_all_roots() to * acquire fs_info->commit_root_sem, because that is a higher level lock * that must be acquired before locking any extent buffers. * * So we want btrfs_find_all_roots() to not acquire the commit_root_sem * but we can't pass it a non-NULL transaction handle, because otherwise * it would not use commit roots and would lock extent buffers, causing * a deadlock if it ends up trying to read lock the same extent buffer * that was previously write locked at btrfs_truncate_inode_items(). * * So pass a NULL transaction handle to btrfs_find_all_roots() and * explicitly tell it to not acquire the commit_root_sem - if we are * holding a transaction handle we don't need its protection. */ ASSERT(trans != NULL); if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING) return 0; ret = btrfs_find_all_roots(&ctx, true); if (ret < 0) { qgroup_mark_inconsistent(fs_info, "error accounting new delayed refs extent: %d", ret); return 0; } /* * Here we don't need to get the lock of * trans->transaction->delayed_refs, since inserted qrecord won't * be deleted, only qrecord->node may be modified (new qrecord insert) * * So modifying qrecord->old_roots is safe here */ qrecord->old_roots = ctx.roots; return 0; } /* * Inform qgroup to trace one dirty extent, specified by @bytenr and * @num_bytes. * So qgroup can account it at commit trans time. * * Better encapsulated version, with memory allocation and backref walk for * commit roots. * So this can sleep. * * Return 0 if the operation is done. * Return <0 for error, like memory allocation failure or invalid parameter * (NULL trans) */ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup_extent_record *record; struct btrfs_delayed_ref_root *delayed_refs = &trans->transaction->delayed_refs; const unsigned long index = (bytenr >> fs_info->sectorsize_bits); int ret; if (!btrfs_qgroup_full_accounting(fs_info) || bytenr == 0 || num_bytes == 0) return 0; record = kzalloc(sizeof(*record), GFP_NOFS); if (!record) return -ENOMEM; if (xa_reserve(&delayed_refs->dirty_extents, index, GFP_NOFS)) { kfree(record); return -ENOMEM; } record->num_bytes = num_bytes; ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record, bytenr); if (ret) { /* Clean up if insertion fails or item exists. */ xa_release(&delayed_refs->dirty_extents, index); kfree(record); return 0; } return btrfs_qgroup_trace_extent_post(trans, record, bytenr); } /* * Inform qgroup to trace all leaf items of data * * Return 0 for success * Return <0 for error(ENOMEM) */ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = trans->fs_info; int nr = btrfs_header_nritems(eb); int i, extent_type, ret; struct btrfs_key key; struct btrfs_file_extent_item *fi; u64 bytenr, num_bytes; /* We can be called directly from walk_up_proc() */ if (!btrfs_qgroup_full_accounting(fs_info)) return 0; for (i = 0; i < nr; i++) { btrfs_item_key_to_cpu(eb, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item); /* filter out non qgroup-accountable extents */ extent_type = btrfs_file_extent_type(eb, fi); if (extent_type == BTRFS_FILE_EXTENT_INLINE) continue; bytenr = btrfs_file_extent_disk_bytenr(eb, fi); if (!bytenr) continue; num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); ret = btrfs_qgroup_trace_extent(trans, bytenr, num_bytes); if (ret) return ret; } cond_resched(); return 0; } /* * Walk up the tree from the bottom, freeing leaves and any interior * nodes which have had all slots visited. If a node (leaf or * interior) is freed, the node above it will have it's slot * incremented. The root node will never be freed. * * At the end of this function, we should have a path which has all * slots incremented to the next position for a search. If we need to * read a new node it will be NULL and the node above it will have the * correct slot selected for a later read. * * If we increment the root nodes slot counter past the number of * elements, 1 is returned to signal completion of the search. */ static int adjust_slots_upwards(struct btrfs_path *path, int root_level) { int level = 0; int nr, slot; struct extent_buffer *eb; if (root_level == 0) return 1; while (level <= root_level) { eb = path->nodes[level]; nr = btrfs_header_nritems(eb); path->slots[level]++; slot = path->slots[level]; if (slot >= nr || level == 0) { /* * Don't free the root - we will detect this * condition after our loop and return a * positive value for caller to stop walking the tree. */ if (level != root_level) { btrfs_tree_unlock_rw(eb, path->locks[level]); path->locks[level] = 0; free_extent_buffer(eb); path->nodes[level] = NULL; path->slots[level] = 0; } } else { /* * We have a valid slot to walk back down * from. Stop here so caller can process these * new nodes. */ break; } level++; } eb = path->nodes[root_level]; if (path->slots[root_level] >= btrfs_header_nritems(eb)) return 1; return 0; } /* * Helper function to trace a subtree tree block swap. * * The swap will happen in highest tree block, but there may be a lot of * tree blocks involved. * * For example: * OO = Old tree blocks * NN = New tree blocks allocated during balance * * File tree (257) Reloc tree for 257 * L2 OO NN * / \ / \ * L1 OO OO (a) OO NN (a) * / \ / \ / \ / \ * L0 OO OO OO OO OO OO NN NN * (b) (c) (b) (c) * * When calling qgroup_trace_extent_swap(), we will pass: * @src_eb = OO(a) * @dst_path = [ nodes[1] = NN(a), nodes[0] = NN(c) ] * @dst_level = 0 * @root_level = 1 * * In that case, qgroup_trace_extent_swap() will search from OO(a) to * reach OO(c), then mark both OO(c) and NN(c) as qgroup dirty. * * The main work of qgroup_trace_extent_swap() can be split into 3 parts: * * 1) Tree search from @src_eb * It should acts as a simplified btrfs_search_slot(). * The key for search can be extracted from @dst_path->nodes[dst_level] * (first key). * * 2) Mark the final tree blocks in @src_path and @dst_path qgroup dirty * NOTE: In above case, OO(a) and NN(a) won't be marked qgroup dirty. * They should be marked during previous (@dst_level = 1) iteration. * * 3) Mark file extents in leaves dirty * We don't have good way to pick out new file extents only. * So we still follow the old method by scanning all file extents in * the leave. * * This function can free us from keeping two paths, thus later we only need * to care about how to iterate all new tree blocks in reloc tree. */ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, struct extent_buffer *src_eb, struct btrfs_path *dst_path, int dst_level, int root_level, bool trace_leaf) { struct btrfs_key key; struct btrfs_path *src_path; struct btrfs_fs_info *fs_info = trans->fs_info; u32 nodesize = fs_info->nodesize; int cur_level = root_level; int ret; BUG_ON(dst_level > root_level); /* Level mismatch */ if (btrfs_header_level(src_eb) != root_level) return -EINVAL; src_path = btrfs_alloc_path(); if (!src_path) { ret = -ENOMEM; goto out; } if (dst_level) btrfs_node_key_to_cpu(dst_path->nodes[dst_level], &key, 0); else btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0); /* For src_path */ refcount_inc(&src_eb->refs); src_path->nodes[root_level] = src_eb; src_path->slots[root_level] = dst_path->slots[root_level]; src_path->locks[root_level] = 0; /* A simplified version of btrfs_search_slot() */ while (cur_level >= dst_level) { struct btrfs_key src_key; struct btrfs_key dst_key; if (src_path->nodes[cur_level] == NULL) { struct extent_buffer *eb; int parent_slot; eb = src_path->nodes[cur_level + 1]; parent_slot = src_path->slots[cur_level + 1]; eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; } src_path->nodes[cur_level] = eb; btrfs_tree_read_lock(eb); src_path->locks[cur_level] = BTRFS_READ_LOCK; } src_path->slots[cur_level] = dst_path->slots[cur_level]; if (cur_level) { btrfs_node_key_to_cpu(dst_path->nodes[cur_level], &dst_key, dst_path->slots[cur_level]); btrfs_node_key_to_cpu(src_path->nodes[cur_level], &src_key, src_path->slots[cur_level]); } else { btrfs_item_key_to_cpu(dst_path->nodes[cur_level], &dst_key, dst_path->slots[cur_level]); btrfs_item_key_to_cpu(src_path->nodes[cur_level], &src_key, src_path->slots[cur_level]); } /* Content mismatch, something went wrong */ if (btrfs_comp_cpu_keys(&dst_key, &src_key)) { ret = -ENOENT; goto out; } cur_level--; } /* * Now both @dst_path and @src_path have been populated, record the tree * blocks for qgroup accounting. */ ret = btrfs_qgroup_trace_extent(trans, src_path->nodes[dst_level]->start, nodesize); if (ret < 0) goto out; ret = btrfs_qgroup_trace_extent(trans, dst_path->nodes[dst_level]->start, nodesize); if (ret < 0) goto out; /* Record leaf file extents */ if (dst_level == 0 && trace_leaf) { ret = btrfs_qgroup_trace_leaf_items(trans, src_path->nodes[0]); if (ret < 0) goto out; ret = btrfs_qgroup_trace_leaf_items(trans, dst_path->nodes[0]); } out: btrfs_free_path(src_path); return ret; } /* * Helper function to do recursive generation-aware depth-first search, to * locate all new tree blocks in a subtree of reloc tree. * * E.g. (OO = Old tree blocks, NN = New tree blocks, whose gen == last_snapshot) * reloc tree * L2 NN (a) * / \ * L1 OO NN (b) * / \ / \ * L0 OO OO OO NN * (c) (d) * If we pass: * @dst_path = [ nodes[1] = NN(b), nodes[0] = NULL ], * @cur_level = 1 * @root_level = 1 * * We will iterate through tree blocks NN(b), NN(d) and info qgroup to trace * above tree blocks along with their counter parts in file tree. * While during search, old tree blocks OO(c) will be skipped as tree block swap * won't affect OO(c). */ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, struct extent_buffer *src_eb, struct btrfs_path *dst_path, int cur_level, int root_level, u64 last_snapshot, bool trace_leaf) { struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *eb; bool need_cleanup = false; int ret = 0; int i; /* Level sanity check */ if (unlikely(cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 || root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 || root_level < cur_level)) { btrfs_err_rl(fs_info, "%s: bad levels, cur_level=%d root_level=%d", __func__, cur_level, root_level); return -EUCLEAN; } /* Read the tree block if needed */ if (dst_path->nodes[cur_level] == NULL) { int parent_slot; u64 child_gen; /* * dst_path->nodes[root_level] must be initialized before * calling this function. */ if (unlikely(cur_level == root_level)) { btrfs_err_rl(fs_info, "%s: dst_path->nodes[%d] not initialized, root_level=%d cur_level=%d", __func__, root_level, root_level, cur_level); return -EUCLEAN; } /* * We need to get child blockptr/gen from parent before we can * read it. */ eb = dst_path->nodes[cur_level + 1]; parent_slot = dst_path->slots[cur_level + 1]; child_gen = btrfs_node_ptr_generation(eb, parent_slot); /* This node is old, no need to trace */ if (child_gen < last_snapshot) goto out; eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; } dst_path->nodes[cur_level] = eb; dst_path->slots[cur_level] = 0; btrfs_tree_read_lock(eb); dst_path->locks[cur_level] = BTRFS_READ_LOCK; need_cleanup = true; } /* Now record this tree block and its counter part for qgroups */ ret = qgroup_trace_extent_swap(trans, src_eb, dst_path, cur_level, root_level, trace_leaf); if (ret < 0) goto cleanup; eb = dst_path->nodes[cur_level]; if (cur_level > 0) { /* Iterate all child tree blocks */ for (i = 0; i < btrfs_header_nritems(eb); i++) { /* Skip old tree blocks as they won't be swapped */ if (btrfs_node_ptr_generation(eb, i) < last_snapshot) continue; dst_path->slots[cur_level] = i; /* Recursive call (at most 7 times) */ ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, cur_level - 1, root_level, last_snapshot, trace_leaf); if (ret < 0) goto cleanup; } } cleanup: if (need_cleanup) { /* Clean up */ btrfs_tree_unlock_rw(dst_path->nodes[cur_level], dst_path->locks[cur_level]); free_extent_buffer(dst_path->nodes[cur_level]); dst_path->nodes[cur_level] = NULL; dst_path->slots[cur_level] = 0; dst_path->locks[cur_level] = 0; } out: return ret; } static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans, struct extent_buffer *src_eb, struct extent_buffer *dst_eb, u64 last_snapshot, bool trace_leaf) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *dst_path = NULL; int level; int ret; if (!btrfs_qgroup_full_accounting(fs_info)) return 0; /* Wrong parameter order */ if (unlikely(btrfs_header_generation(src_eb) > btrfs_header_generation(dst_eb))) { btrfs_err_rl(fs_info, "%s: bad parameter order, src_gen=%llu dst_gen=%llu", __func__, btrfs_header_generation(src_eb), btrfs_header_generation(dst_eb)); return -EUCLEAN; } if (unlikely(!extent_buffer_uptodate(src_eb) || !extent_buffer_uptodate(dst_eb))) { ret = -EIO; goto out; } level = btrfs_header_level(dst_eb); dst_path = btrfs_alloc_path(); if (!dst_path) { ret = -ENOMEM; goto out; } /* For dst_path */ refcount_inc(&dst_eb->refs); dst_path->nodes[level] = dst_eb; dst_path->slots[level] = 0; dst_path->locks[level] = 0; /* Do the generation aware breadth-first search */ ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, level, level, last_snapshot, trace_leaf); if (ret < 0) goto out; ret = 0; out: btrfs_free_path(dst_path); if (ret < 0) qgroup_mark_inconsistent(fs_info, "%s error: %d", __func__, ret); return ret; } /* * Inform qgroup to trace a whole subtree, including all its child tree * blocks and data. * The root tree block is specified by @root_eb. * * Normally used by relocation(tree block swap) and subvolume deletion. * * Return 0 for success * Return <0 for error(ENOMEM or tree search error) */ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, struct extent_buffer *root_eb, u64 root_gen, int root_level) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; int level; u8 drop_subptree_thres; struct extent_buffer *eb = root_eb; struct btrfs_path *path = NULL; ASSERT(0 <= root_level && root_level < BTRFS_MAX_LEVEL); ASSERT(root_eb != NULL); if (!btrfs_qgroup_full_accounting(fs_info)) return 0; spin_lock(&fs_info->qgroup_lock); drop_subptree_thres = fs_info->qgroup_drop_subtree_thres; spin_unlock(&fs_info->qgroup_lock); /* * This function only gets called for snapshot drop, if we hit a high * node here, it means we are going to change ownership for quite a lot * of extents, which will greatly slow down btrfs_commit_transaction(). * * So here if we find a high tree here, we just skip the accounting and * mark qgroup inconsistent. */ if (root_level >= drop_subptree_thres) { qgroup_mark_inconsistent(fs_info, "subtree level reached threshold"); return 0; } if (!extent_buffer_uptodate(root_eb)) { struct btrfs_tree_parent_check check = { .transid = root_gen, .level = root_level }; ret = btrfs_read_extent_buffer(root_eb, &check); if (ret) goto out; } if (root_level == 0) { ret = btrfs_qgroup_trace_leaf_items(trans, root_eb); goto out; } path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* * Walk down the tree. Missing extent blocks are filled in as * we go. Metadata is accounted every time we read a new * extent block. * * When we reach a leaf, we account for file extent items in it, * walk back up the tree (adjusting slot pointers as we go) * and restart the search process. */ refcount_inc(&root_eb->refs); /* For path */ path->nodes[root_level] = root_eb; path->slots[root_level] = 0; path->locks[root_level] = 0; /* so release_path doesn't try to unlock */ walk_down: level = root_level; while (level >= 0) { if (path->nodes[level] == NULL) { int parent_slot; u64 child_bytenr; /* * We need to get child blockptr from parent before we * can read it. */ eb = path->nodes[level + 1]; parent_slot = path->slots[level + 1]; child_bytenr = btrfs_node_blockptr(eb, parent_slot); eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; } path->nodes[level] = eb; path->slots[level] = 0; btrfs_tree_read_lock(eb); path->locks[level] = BTRFS_READ_LOCK; ret = btrfs_qgroup_trace_extent(trans, child_bytenr, fs_info->nodesize); if (ret) goto out; } if (level == 0) { ret = btrfs_qgroup_trace_leaf_items(trans, path->nodes[level]); if (ret) goto out; /* Nonzero return here means we completed our search */ ret = adjust_slots_upwards(path, root_level); if (ret) break; /* Restart search with new slots */ goto walk_down; } level--; } ret = 0; out: btrfs_free_path(path); return ret; } static void qgroup_iterator_nested_add(struct list_head *head, struct btrfs_qgroup *qgroup) { if (!list_empty(&qgroup->nested_iterator)) return; list_add_tail(&qgroup->nested_iterator, head); } static void qgroup_iterator_nested_clean(struct list_head *head) { while (!list_empty(head)) { struct btrfs_qgroup *qgroup; qgroup = list_first_entry(head, struct btrfs_qgroup, nested_iterator); list_del_init(&qgroup->nested_iterator); } } #define UPDATE_NEW 0 #define UPDATE_OLD 1 /* * Walk all of the roots that points to the bytenr and adjust their refcnts. */ static void qgroup_update_refcnt(struct btrfs_fs_info *fs_info, struct ulist *roots, struct list_head *qgroups, u64 seq, bool update_old) { struct ulist_node *unode; struct ulist_iterator uiter; struct btrfs_qgroup *qg; if (!roots) return; ULIST_ITER_INIT(&uiter); while ((unode = ulist_next(roots, &uiter))) { LIST_HEAD(tmp); qg = find_qgroup_rb(fs_info, unode->val); if (!qg) continue; qgroup_iterator_nested_add(qgroups, qg); qgroup_iterator_add(&tmp, qg); list_for_each_entry(qg, &tmp, iterator) { struct btrfs_qgroup_list *glist; if (update_old) btrfs_qgroup_update_old_refcnt(qg, seq, 1); else btrfs_qgroup_update_new_refcnt(qg, seq, 1); list_for_each_entry(glist, &qg->groups, next_group) { qgroup_iterator_nested_add(qgroups, glist->group); qgroup_iterator_add(&tmp, glist->group); } } qgroup_iterator_clean(&tmp); } } /* * Update qgroup rfer/excl counters. * Rfer update is easy, codes can explain themselves. * * Excl update is tricky, the update is split into 2 parts. * Part 1: Possible exclusive <-> sharing detect: * | A | !A | * ------------------------------------- * B | * | - | * ------------------------------------- * !B | + | ** | * ------------------------------------- * * Conditions: * A: cur_old_roots < nr_old_roots (not exclusive before) * !A: cur_old_roots == nr_old_roots (possible exclusive before) * B: cur_new_roots < nr_new_roots (not exclusive now) * !B: cur_new_roots == nr_new_roots (possible exclusive now) * * Results: * +: Possible sharing -> exclusive -: Possible exclusive -> sharing * *: Definitely not changed. **: Possible unchanged. * * For !A and !B condition, the exception is cur_old/new_roots == 0 case. * * To make the logic clear, we first use condition A and B to split * combination into 4 results. * * Then, for result "+" and "-", check old/new_roots == 0 case, as in them * only on variant maybe 0. * * Lastly, check result **, since there are 2 variants maybe 0, split them * again(2x2). * But this time we don't need to consider other things, the codes and logic * is easy to understand now. */ static void qgroup_update_counters(struct btrfs_fs_info *fs_info, struct list_head *qgroups, u64 nr_old_roots, u64 nr_new_roots, u64 num_bytes, u64 seq) { struct btrfs_qgroup *qg; list_for_each_entry(qg, qgroups, nested_iterator) { u64 cur_new_count, cur_old_count; bool dirty = false; cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq); cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq); trace_btrfs_qgroup_update_counters(fs_info, qg, cur_old_count, cur_new_count); /* Rfer update part */ if (cur_old_count == 0 && cur_new_count > 0) { qg->rfer += num_bytes; qg->rfer_cmpr += num_bytes; dirty = true; } if (cur_old_count > 0 && cur_new_count == 0) { qg->rfer -= num_bytes; qg->rfer_cmpr -= num_bytes; dirty = true; } /* Excl update part */ /* Exclusive/none -> shared case */ if (cur_old_count == nr_old_roots && cur_new_count < nr_new_roots) { /* Exclusive -> shared */ if (cur_old_count != 0) { qg->excl -= num_bytes; qg->excl_cmpr -= num_bytes; dirty = true; } } /* Shared -> exclusive/none case */ if (cur_old_count < nr_old_roots && cur_new_count == nr_new_roots) { /* Shared->exclusive */ if (cur_new_count != 0) { qg->excl += num_bytes; qg->excl_cmpr += num_bytes; dirty = true; } } /* Exclusive/none -> exclusive/none case */ if (cur_old_count == nr_old_roots && cur_new_count == nr_new_roots) { if (cur_old_count == 0) { /* None -> exclusive/none */ if (cur_new_count != 0) { /* None -> exclusive */ qg->excl += num_bytes; qg->excl_cmpr += num_bytes; dirty = true; } /* None -> none, nothing changed */ } else { /* Exclusive -> exclusive/none */ if (cur_new_count == 0) { /* Exclusive -> none */ qg->excl -= num_bytes; qg->excl_cmpr -= num_bytes; dirty = true; } /* Exclusive -> exclusive, nothing changed */ } } if (dirty) qgroup_dirty(fs_info, qg); } } /* * Check if the @roots potentially is a list of fs tree roots * * Return 0 for definitely not a fs/subvol tree roots ulist * Return 1 for possible fs/subvol tree roots in the list (considering an empty * one as well) */ static int maybe_fs_roots(struct ulist *roots) { struct ulist_node *unode; struct ulist_iterator uiter; /* Empty one, still possible for fs roots */ if (!roots || roots->nnodes == 0) return 1; ULIST_ITER_INIT(&uiter); unode = ulist_next(roots, &uiter); if (!unode) return 1; /* * If it contains fs tree roots, then it must belong to fs/subvol * trees. * If it contains a non-fs tree, it won't be shared with fs/subvol trees. */ return btrfs_is_fstree(unode->val); } int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct ulist *old_roots, struct ulist *new_roots) { struct btrfs_fs_info *fs_info = trans->fs_info; LIST_HEAD(qgroups); u64 seq; u64 nr_new_roots = 0; u64 nr_old_roots = 0; int ret = 0; /* * If quotas get disabled meanwhile, the resources need to be freed and * we can't just exit here. */ if (!btrfs_qgroup_full_accounting(fs_info) || fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING) goto out_free; if (new_roots) { if (!maybe_fs_roots(new_roots)) goto out_free; nr_new_roots = new_roots->nnodes; } if (old_roots) { if (!maybe_fs_roots(old_roots)) goto out_free; nr_old_roots = old_roots->nnodes; } /* Quick exit, either not fs tree roots, or won't affect any qgroup */ if (nr_old_roots == 0 && nr_new_roots == 0) goto out_free; trace_btrfs_qgroup_account_extent(fs_info, trans->transid, bytenr, num_bytes, nr_old_roots, nr_new_roots); mutex_lock(&fs_info->qgroup_rescan_lock); if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { if (fs_info->qgroup_rescan_progress.objectid <= bytenr) { mutex_unlock(&fs_info->qgroup_rescan_lock); ret = 0; goto out_free; } } mutex_unlock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); seq = fs_info->qgroup_seq; /* Update old refcnts using old_roots */ qgroup_update_refcnt(fs_info, old_roots, &qgroups, seq, UPDATE_OLD); /* Update new refcnts using new_roots */ qgroup_update_refcnt(fs_info, new_roots, &qgroups, seq, UPDATE_NEW); qgroup_update_counters(fs_info, &qgroups, nr_old_roots, nr_new_roots, num_bytes, seq); /* * We're done using the iterator, release all its qgroups while holding * fs_info->qgroup_lock so that we don't race with btrfs_remove_qgroup() * and trigger use-after-free accesses to qgroups. */ qgroup_iterator_nested_clean(&qgroups); /* * Bump qgroup_seq to avoid seq overlap */ fs_info->qgroup_seq += max(nr_old_roots, nr_new_roots) + 1; spin_unlock(&fs_info->qgroup_lock); out_free: ulist_free(old_roots); ulist_free(new_roots); return ret; } int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_qgroup_extent_record *record; struct btrfs_delayed_ref_root *delayed_refs; struct ulist *new_roots = NULL; unsigned long index; u64 num_dirty_extents = 0; u64 qgroup_to_skip; int ret = 0; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) return 0; delayed_refs = &trans->transaction->delayed_refs; qgroup_to_skip = delayed_refs->qgroup_to_skip; xa_for_each(&delayed_refs->dirty_extents, index, record) { const u64 bytenr = (((u64)index) << fs_info->sectorsize_bits); num_dirty_extents++; trace_btrfs_qgroup_account_extents(fs_info, record, bytenr); if (!ret && !(fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING)) { struct btrfs_backref_walk_ctx ctx = { 0 }; ctx.bytenr = bytenr; ctx.fs_info = fs_info; /* * Old roots should be searched when inserting qgroup * extent record. * * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case, * we may have some record inserted during * NO_ACCOUNTING (thus no old_roots populated), but * later we start rescan, which clears NO_ACCOUNTING, * leaving some inserted records without old_roots * populated. * * Those cases are rare and should not cause too much * time spent during commit_transaction(). */ if (!record->old_roots) { /* Search commit root to find old_roots */ ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) goto cleanup; record->old_roots = ctx.roots; ctx.roots = NULL; } /* * Use BTRFS_SEQ_LAST as time_seq to do special search, * which doesn't lock tree or delayed_refs and search * current root. It's safe inside commit_transaction(). */ ctx.trans = trans; ctx.time_seq = BTRFS_SEQ_LAST; ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) goto cleanup; new_roots = ctx.roots; if (qgroup_to_skip) { ulist_del(new_roots, qgroup_to_skip, 0); ulist_del(record->old_roots, qgroup_to_skip, 0); } ret = btrfs_qgroup_account_extent(trans, bytenr, record->num_bytes, record->old_roots, new_roots); record->old_roots = NULL; new_roots = NULL; } /* Free the reserved data space */ btrfs_qgroup_free_refroot(fs_info, record->data_rsv_refroot, record->data_rsv, BTRFS_QGROUP_RSV_DATA); cleanup: ulist_free(record->old_roots); ulist_free(new_roots); new_roots = NULL; xa_erase(&delayed_refs->dirty_extents, index); kfree(record); } trace_btrfs_qgroup_num_dirty_extents(fs_info, trans->transid, num_dirty_extents); return ret; } /* * Writes all changed qgroups to disk. * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; /* * In case we are called from the qgroup assign ioctl, assert that we * are holding the qgroup_ioctl_lock, otherwise we can race with a quota * disable operation (ioctl) and access a freed quota root. */ if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) lockdep_assert_held(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) return ret; spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { struct btrfs_qgroup *qgroup; qgroup = list_first_entry(&fs_info->dirty_qgroups, struct btrfs_qgroup, dirty); list_del_init(&qgroup->dirty); spin_unlock(&fs_info->qgroup_lock); ret = update_qgroup_info_item(trans, qgroup); if (ret) qgroup_mark_inconsistent(fs_info, "qgroup info item update error %d", ret); ret = update_qgroup_limit_item(trans, qgroup); if (ret) qgroup_mark_inconsistent(fs_info, "qgroup limit item update error %d", ret); spin_lock(&fs_info->qgroup_lock); } if (btrfs_qgroup_enabled(fs_info)) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_ON; else fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; spin_unlock(&fs_info->qgroup_lock); ret = update_qgroup_status_item(trans); if (ret) qgroup_mark_inconsistent(fs_info, "qgroup status item update error %d", ret); return ret; } int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info, struct btrfs_qgroup_inherit *inherit, size_t size) { if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP) return -EOPNOTSUPP; if (size < sizeof(*inherit) || size > PAGE_SIZE) return -EINVAL; /* * In the past we allowed btrfs_qgroup_inherit to specify to copy * rfer/excl numbers directly from other qgroups. This behavior has * been disabled in userspace for a very long time, but here we should * also disable it in kernel, as this behavior is known to mark qgroup * inconsistent, and a rescan would wipe out the changes anyway. * * Reject any btrfs_qgroup_inherit with num_ref_copies or num_excl_copies. */ if (inherit->num_ref_copies > 0 || inherit->num_excl_copies > 0) return -EINVAL; if (size != struct_size(inherit, qgroups, inherit->num_qgroups)) return -EINVAL; /* * Skip the inherit source qgroups check if qgroup is not enabled. * Qgroup can still be later enabled causing problems, but in that case * btrfs_qgroup_inherit() would just ignore those invalid ones. */ if (!btrfs_qgroup_enabled(fs_info)) return 0; /* * Now check all the remaining qgroups, they should all: * * - Exist * - Be higher level qgroups. */ for (int i = 0; i < inherit->num_qgroups; i++) { struct btrfs_qgroup *qgroup; u64 qgroupid = inherit->qgroups[i]; if (btrfs_qgroup_level(qgroupid) == 0) return -EINVAL; spin_lock(&fs_info->qgroup_lock); qgroup = find_qgroup_rb(fs_info, qgroupid); if (!qgroup) { spin_unlock(&fs_info->qgroup_lock); return -ENOENT; } spin_unlock(&fs_info->qgroup_lock); } return 0; } static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info, u64 inode_rootid, struct btrfs_qgroup_inherit **inherit) { int i = 0; u64 num_qgroups = 0; struct btrfs_qgroup *inode_qg; struct btrfs_qgroup_list *qg_list; struct btrfs_qgroup_inherit *res; size_t struct_sz; u64 *qgids; if (*inherit) return -EEXIST; inode_qg = find_qgroup_rb(fs_info, inode_rootid); if (!inode_qg) return -ENOENT; num_qgroups = list_count_nodes(&inode_qg->groups); if (!num_qgroups) return 0; struct_sz = struct_size(res, qgroups, num_qgroups); if (struct_sz == SIZE_MAX) return -ERANGE; res = kzalloc(struct_sz, GFP_NOFS); if (!res) return -ENOMEM; res->num_qgroups = num_qgroups; qgids = res->qgroups; list_for_each_entry(qg_list, &inode_qg->groups, next_group) qgids[i++] = qg_list->group->qgroupid; *inherit = res; return 0; } /* * Check if we can skip rescan when inheriting qgroups. If @src has a single * @parent, and that @parent is owning all its bytes exclusively, we can skip * the full rescan, by just adding nodesize to the @parent's excl/rfer. * * Return <0 for fatal errors (like srcid/parentid has no qgroup). * Return 0 if a quick inherit is done. * Return >0 if a quick inherit is not possible, and a full rescan is needed. */ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, u64 srcid, u64 parentid) { struct btrfs_qgroup *src; struct btrfs_qgroup *parent; struct btrfs_qgroup_list *list; int nr_parents = 0; src = find_qgroup_rb(fs_info, srcid); if (!src) return -ENOENT; parent = find_qgroup_rb(fs_info, parentid); if (!parent) return -ENOENT; /* * Source has no parent qgroup, but our new qgroup would have one. * Qgroup numbers would become inconsistent. */ if (list_empty(&src->groups)) return 1; list_for_each_entry(list, &src->groups, next_group) { /* The parent is not the same, quick update is not possible. */ if (list->group->qgroupid != parentid) return 1; nr_parents++; /* * More than one parent qgroup, we can't be sure about accounting * consistency. */ if (nr_parents > 1) return 1; } /* * The parent is not exclusively owning all its bytes. We're not sure * if the source has any bytes not fully owned by the parent. */ if (parent->excl != parent->rfer) return 1; parent->excl += fs_info->nodesize; parent->rfer += fs_info->nodesize; return 0; } /* * Copy the accounting information between qgroups. This is necessary * when a snapshot or a subvolume is created. Throwing an error will * cause a transaction abort so we take extra care here to only error * when a readonly fs is a reasonable outcome. */ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, u64 objectid, u64 inode_rootid, struct btrfs_qgroup_inherit *inherit) { int ret = 0; u64 *i_qgroups; bool committing = false; struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *quota_root; struct btrfs_qgroup *srcgroup; struct btrfs_qgroup *dstgroup; struct btrfs_qgroup *prealloc; struct btrfs_qgroup_list **qlist_prealloc = NULL; bool free_inherit = false; bool need_rescan = false; u32 level_size = 0; u64 nums; if (!btrfs_qgroup_enabled(fs_info)) return 0; prealloc = kzalloc(sizeof(*prealloc), GFP_NOFS); if (!prealloc) return -ENOMEM; /* * There are only two callers of this function. * * One in create_subvol() in the ioctl context, which needs to hold * the qgroup_ioctl_lock. * * The other one in create_pending_snapshot() where no other qgroup * code can modify the fs as they all need to either start a new trans * or hold a trans handler, thus we don't need to hold * qgroup_ioctl_lock. * This would avoid long and complex lock chain and make lockdep happy. */ spin_lock(&fs_info->trans_lock); if (trans->transaction->state == TRANS_STATE_COMMIT_DOING) committing = true; spin_unlock(&fs_info->trans_lock); if (!committing) mutex_lock(&fs_info->qgroup_ioctl_lock); quota_root = fs_info->quota_root; if (!quota_root) { ret = -EINVAL; goto out; } if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && !inherit) { ret = qgroup_auto_inherit(fs_info, inode_rootid, &inherit); if (ret) goto out; free_inherit = true; } if (inherit) { i_qgroups = (u64 *)(inherit + 1); nums = inherit->num_qgroups + 2 * inherit->num_ref_copies + 2 * inherit->num_excl_copies; for (int i = 0; i < nums; i++) { srcgroup = find_qgroup_rb(fs_info, *i_qgroups); /* * Zero out invalid groups so we can ignore * them later. */ if (!srcgroup || ((srcgroup->qgroupid >> 48) <= (objectid >> 48))) *i_qgroups = 0ULL; ++i_qgroups; } } /* * create a tracking group for the subvol itself */ ret = add_qgroup_item(trans, quota_root, objectid); if (ret) goto out; /* * add qgroup to all inherited groups */ if (inherit) { i_qgroups = (u64 *)(inherit + 1); for (int i = 0; i < inherit->num_qgroups; i++, i_qgroups++) { if (*i_qgroups == 0) continue; ret = add_qgroup_relation_item(trans, objectid, *i_qgroups); if (ret && ret != -EEXIST) goto out; ret = add_qgroup_relation_item(trans, *i_qgroups, objectid); if (ret && ret != -EEXIST) goto out; } ret = 0; qlist_prealloc = kcalloc(inherit->num_qgroups, sizeof(struct btrfs_qgroup_list *), GFP_NOFS); if (!qlist_prealloc) { ret = -ENOMEM; goto out; } for (int i = 0; i < inherit->num_qgroups; i++) { qlist_prealloc[i] = kzalloc(sizeof(struct btrfs_qgroup_list), GFP_NOFS); if (!qlist_prealloc[i]) { ret = -ENOMEM; goto out; } } } spin_lock(&fs_info->qgroup_lock); dstgroup = add_qgroup_rb(fs_info, prealloc, objectid); prealloc = NULL; if (inherit && inherit->flags & BTRFS_QGROUP_INHERIT_SET_LIMITS) { dstgroup->lim_flags = inherit->lim.flags; dstgroup->max_rfer = inherit->lim.max_rfer; dstgroup->max_excl = inherit->lim.max_excl; dstgroup->rsv_rfer = inherit->lim.rsv_rfer; dstgroup->rsv_excl = inherit->lim.rsv_excl; qgroup_dirty(fs_info, dstgroup); } if (srcid && btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL) { srcgroup = find_qgroup_rb(fs_info, srcid); if (!srcgroup) goto unlock; /* * We call inherit after we clone the root in order to make sure * our counts don't go crazy, so at this point the only * difference between the two roots should be the root node. */ level_size = fs_info->nodesize; dstgroup->rfer = srcgroup->rfer; dstgroup->rfer_cmpr = srcgroup->rfer_cmpr; dstgroup->excl = level_size; dstgroup->excl_cmpr = level_size; srcgroup->excl = level_size; srcgroup->excl_cmpr = level_size; /* inherit the limit info */ dstgroup->lim_flags = srcgroup->lim_flags; dstgroup->max_rfer = srcgroup->max_rfer; dstgroup->max_excl = srcgroup->max_excl; dstgroup->rsv_rfer = srcgroup->rsv_rfer; dstgroup->rsv_excl = srcgroup->rsv_excl; qgroup_dirty(fs_info, dstgroup); qgroup_dirty(fs_info, srcgroup); /* * If the source qgroup has parent but the new one doesn't, * we need a full rescan. */ if (!inherit && !list_empty(&srcgroup->groups)) need_rescan = true; } if (!inherit) goto unlock; i_qgroups = (u64 *)(inherit + 1); for (int i = 0; i < inherit->num_qgroups; i++) { if (*i_qgroups) { ret = add_relation_rb(fs_info, qlist_prealloc[i], objectid, *i_qgroups); qlist_prealloc[i] = NULL; if (ret) goto unlock; } if (srcid) { /* Check if we can do a quick inherit. */ ret = qgroup_snapshot_quick_inherit(fs_info, srcid, *i_qgroups); if (ret < 0) goto unlock; if (ret > 0) need_rescan = true; ret = 0; } ++i_qgroups; } for (int i = 0; i < inherit->num_ref_copies; i++, i_qgroups += 2) { struct btrfs_qgroup *src; struct btrfs_qgroup *dst; if (!i_qgroups[0] || !i_qgroups[1]) continue; src = find_qgroup_rb(fs_info, i_qgroups[0]); dst = find_qgroup_rb(fs_info, i_qgroups[1]); if (!src || !dst) { ret = -EINVAL; goto unlock; } dst->rfer = src->rfer - level_size; dst->rfer_cmpr = src->rfer_cmpr - level_size; /* Manually tweaking numbers certainly needs a rescan */ need_rescan = true; } for (int i = 0; i < inherit->num_excl_copies; i++, i_qgroups += 2) { struct btrfs_qgroup *src; struct btrfs_qgroup *dst; if (!i_qgroups[0] || !i_qgroups[1]) continue; src = find_qgroup_rb(fs_info, i_qgroups[0]); dst = find_qgroup_rb(fs_info, i_qgroups[1]); if (!src || !dst) { ret = -EINVAL; goto unlock; } dst->excl = src->excl + level_size; dst->excl_cmpr = src->excl_cmpr + level_size; need_rescan = true; } unlock: spin_unlock(&fs_info->qgroup_lock); if (!ret) ret = btrfs_sysfs_add_one_qgroup(fs_info, dstgroup); out: if (!committing) mutex_unlock(&fs_info->qgroup_ioctl_lock); if (need_rescan) qgroup_mark_inconsistent(fs_info, "qgroup inherit needs a rescan"); if (qlist_prealloc) { for (int i = 0; i < inherit->num_qgroups; i++) kfree(qlist_prealloc[i]); kfree(qlist_prealloc); } if (free_inherit) kfree(inherit); kfree(prealloc); return ret; } static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes) { if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) && qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer) return false; if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) && qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl) return false; return true; } static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce, enum btrfs_qgroup_rsv_type type) { struct btrfs_qgroup *qgroup; struct btrfs_fs_info *fs_info = root->fs_info; u64 ref_root = btrfs_root_id(root); int ret = 0; LIST_HEAD(qgroup_list); if (!btrfs_is_fstree(ref_root)) return 0; if (num_bytes == 0) return 0; if (test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags) && capable(CAP_SYS_RESOURCE)) enforce = false; spin_lock(&fs_info->qgroup_lock); if (!fs_info->quota_root) goto out; qgroup = find_qgroup_rb(fs_info, ref_root); if (!qgroup) goto out; qgroup_iterator_add(&qgroup_list, qgroup); list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; if (enforce && !qgroup_check_limits(qgroup, num_bytes)) { ret = -EDQUOT; goto out; } list_for_each_entry(glist, &qgroup->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); } ret = 0; /* * no limits exceeded, now record the reservation into all qgroups */ list_for_each_entry(qgroup, &qgroup_list, iterator) qgroup_rsv_add(fs_info, qgroup, num_bytes, type); out: qgroup_iterator_clean(&qgroup_list); spin_unlock(&fs_info->qgroup_lock); return ret; } /* * Free @num_bytes of reserved space with @type for qgroup. (Normally level 0 * qgroup). * * Will handle all higher level qgroup too. * * NOTE: If @num_bytes is (u64)-1, this means to free all bytes of this qgroup. * This special case is only used for META_PERTRANS type. */ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info, u64 ref_root, u64 num_bytes, enum btrfs_qgroup_rsv_type type) { struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); if (!btrfs_is_fstree(ref_root)) return; if (num_bytes == 0) return; if (num_bytes == (u64)-1 && type != BTRFS_QGROUP_RSV_META_PERTRANS) { WARN(1, "%s: Invalid type to free", __func__); return; } spin_lock(&fs_info->qgroup_lock); if (!fs_info->quota_root) goto out; qgroup = find_qgroup_rb(fs_info, ref_root); if (!qgroup) goto out; if (num_bytes == (u64)-1) /* * We're freeing all pertrans rsv, get reserved value from * level 0 qgroup as real num_bytes to free. */ num_bytes = qgroup->rsv.values[type]; qgroup_iterator_add(&qgroup_list, qgroup); list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup_rsv_release(fs_info, qgroup, num_bytes, type); list_for_each_entry(glist, &qgroup->groups, next_group) { qgroup_iterator_add(&qgroup_list, glist->group); } } out: qgroup_iterator_clean(&qgroup_list); spin_unlock(&fs_info->qgroup_lock); } /* * Check if the leaf is the last leaf. Which means all node pointers * are at their last position. */ static bool is_last_leaf(struct btrfs_path *path) { int i; for (i = 1; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) { if (path->slots[i] != btrfs_header_nritems(path->nodes[i]) - 1) return false; } return true; } /* * returns < 0 on error, 0 when more leafs are to be scanned. * returns 1 when done. */ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *extent_root; struct btrfs_key found; struct extent_buffer *scratch_leaf = NULL; u64 num_bytes; bool done; int slot; int ret; if (!btrfs_qgroup_full_accounting(fs_info)) return 1; mutex_lock(&fs_info->qgroup_rescan_lock); extent_root = btrfs_extent_root(fs_info, fs_info->qgroup_rescan_progress.objectid); ret = btrfs_search_slot_for_read(extent_root, &fs_info->qgroup_rescan_progress, path, 1, 0); btrfs_debug(fs_info, "current progress key (%llu %u %llu), search_slot ret %d", fs_info->qgroup_rescan_progress.objectid, fs_info->qgroup_rescan_progress.type, fs_info->qgroup_rescan_progress.offset, ret); if (ret) { /* * The rescan is about to end, we will not be scanning any * further blocks. We cannot unset the RESCAN flag here, because * we want to commit the transaction if everything went well. * To make the live accounting work in this phase, we set our * scan progress pointer such that every real extent objectid * will be smaller. */ fs_info->qgroup_rescan_progress.objectid = (u64)-1; btrfs_release_path(path); mutex_unlock(&fs_info->qgroup_rescan_lock); return ret; } done = is_last_leaf(path); btrfs_item_key_to_cpu(path->nodes[0], &found, btrfs_header_nritems(path->nodes[0]) - 1); fs_info->qgroup_rescan_progress.objectid = found.objectid + 1; scratch_leaf = btrfs_clone_extent_buffer(path->nodes[0]); if (!scratch_leaf) { ret = -ENOMEM; mutex_unlock(&fs_info->qgroup_rescan_lock); goto out; } slot = path->slots[0]; btrfs_release_path(path); mutex_unlock(&fs_info->qgroup_rescan_lock); for (; slot < btrfs_header_nritems(scratch_leaf); ++slot) { struct btrfs_backref_walk_ctx ctx = { 0 }; btrfs_item_key_to_cpu(scratch_leaf, &found, slot); if (found.type != BTRFS_EXTENT_ITEM_KEY && found.type != BTRFS_METADATA_ITEM_KEY) continue; if (found.type == BTRFS_METADATA_ITEM_KEY) num_bytes = fs_info->nodesize; else num_bytes = found.offset; ctx.bytenr = found.objectid; ctx.fs_info = fs_info; ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) goto out; /* For rescan, just pass old_roots as NULL */ ret = btrfs_qgroup_account_extent(trans, found.objectid, num_bytes, NULL, ctx.roots); if (ret < 0) goto out; } out: if (scratch_leaf) free_extent_buffer(scratch_leaf); if (done && !ret) { ret = 1; fs_info->qgroup_rescan_progress.objectid = (u64)-1; } return ret; } static bool rescan_should_stop(struct btrfs_fs_info *fs_info) { if (btrfs_fs_closing(fs_info)) return true; if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) return true; if (!btrfs_qgroup_enabled(fs_info)) return true; if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) return true; return false; } static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, qgroup_rescan_work); struct btrfs_path *path; struct btrfs_trans_handle *trans = NULL; int ret = 0; bool stopped = false; bool did_leaf_rescans = false; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) return; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } /* * Rescan should only search for commit root, and any later difference * should be recorded by qgroup */ path->search_commit_root = 1; path->skip_locking = 1; while (!ret && !(stopped = rescan_should_stop(fs_info))) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); break; } ret = qgroup_rescan_leaf(trans, path); did_leaf_rescans = true; if (ret > 0) btrfs_commit_transaction(trans); else btrfs_end_transaction(trans); } out: btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); if (ret > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } else if (ret < 0 || stopped) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } mutex_unlock(&fs_info->qgroup_rescan_lock); /* * Only update status, since the previous part has already updated the * qgroup info, and only if we did any actual work. This also prevents * race with a concurrent quota disable, which has already set * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at * btrfs_quota_disable(). */ if (did_leaf_rescans) { trans = btrfs_start_transaction(fs_info->quota_root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; btrfs_err(fs_info, "fail to start transaction for status update: %d", ret); } } else { trans = NULL; } mutex_lock(&fs_info->qgroup_rescan_lock); if (!stopped || fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (trans) { int ret2 = update_qgroup_status_item(trans); if (ret2 < 0) { ret = ret2; btrfs_err(fs_info, "fail to update qgroup status: %d", ret); } } fs_info->qgroup_rescan_running = false; fs_info->qgroup_flags &= ~BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN; complete_all(&fs_info->qgroup_rescan_completion); mutex_unlock(&fs_info->qgroup_rescan_lock); if (!trans) return; btrfs_end_transaction(trans); if (stopped) { btrfs_info(fs_info, "qgroup scan paused"); } else if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN) { btrfs_info(fs_info, "qgroup scan cancelled"); } else if (ret >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", ret > 0 ? " (inconsistency flag cleared)" : ""); } else { btrfs_err(fs_info, "qgroup scan failed with %d", ret); } } /* * Checks that (a) no rescan is running and (b) quota is enabled. Allocates all * memory required for the rescan context. */ static int qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, int init_flags) { int ret = 0; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) { btrfs_warn(fs_info, "qgroup rescan init failed, running in simple mode"); return -EINVAL; } if (!init_flags) { /* we're resuming qgroup rescan at mount time */ if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)) { btrfs_debug(fs_info, "qgroup rescan init failed, qgroup rescan is not queued"); ret = -EINVAL; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); ret = -ENOTCONN; } if (ret) return ret; } mutex_lock(&fs_info->qgroup_rescan_lock); if (init_flags) { if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { ret = -EINPROGRESS; } else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) { btrfs_debug(fs_info, "qgroup rescan init failed, qgroup is not enabled"); ret = -ENOTCONN; } else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) { /* Quota disable is in progress */ ret = -EBUSY; } if (ret) { mutex_unlock(&fs_info->qgroup_rescan_lock); return ret; } fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_RESCAN; } memset(&fs_info->qgroup_rescan_progress, 0, sizeof(fs_info->qgroup_rescan_progress)); fs_info->qgroup_flags &= ~(BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN | BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING); fs_info->qgroup_rescan_progress.objectid = progress_objectid; init_completion(&fs_info->qgroup_rescan_completion); mutex_unlock(&fs_info->qgroup_rescan_lock); btrfs_init_work(&fs_info->qgroup_rescan_work, btrfs_qgroup_rescan_worker, NULL); return 0; } static void qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info) { struct rb_node *n; struct btrfs_qgroup *qgroup; spin_lock(&fs_info->qgroup_lock); /* clear all current qgroup tracking information */ for (n = rb_first(&fs_info->qgroup_tree); n; n = rb_next(n)) { qgroup = rb_entry(n, struct btrfs_qgroup, node); qgroup->rfer = 0; qgroup->rfer_cmpr = 0; qgroup->excl = 0; qgroup->excl_cmpr = 0; qgroup_dirty(fs_info, qgroup); } spin_unlock(&fs_info->qgroup_lock); } int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) { int ret = 0; ret = qgroup_rescan_init(fs_info, 0, 1); if (ret) return ret; /* * We have set the rescan_progress to 0, which means no more * delayed refs will be accounted by btrfs_qgroup_account_ref. * However, btrfs_qgroup_account_ref may be right after its call * to btrfs_find_all_roots, in which case it would still do the * accounting. * To solve this, we're committing the transaction, which will * ensure we run all delayed refs and only after that, we are * going to clear all tracking information for a clean start. */ ret = btrfs_commit_current_transaction(fs_info->fs_root); if (ret) { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; return ret; } qgroup_rescan_zero_tracking(fs_info); mutex_lock(&fs_info->qgroup_rescan_lock); /* * The rescan worker is only for full accounting qgroups, check if it's * enabled as it is pointless to queue it otherwise. A concurrent quota * disable may also have just cleared BTRFS_FS_QUOTA_ENABLED. */ if (btrfs_qgroup_full_accounting(fs_info)) { fs_info->qgroup_rescan_running = true; btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); } else { ret = -ENOTCONN; } mutex_unlock(&fs_info->qgroup_rescan_lock); return ret; } int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, bool interruptible) { int running; int ret = 0; mutex_lock(&fs_info->qgroup_rescan_lock); running = fs_info->qgroup_rescan_running; mutex_unlock(&fs_info->qgroup_rescan_lock); if (!running) return 0; if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); else wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } /* * this is only called from open_ctree where we're still single threaded, thus * locking is omitted here. */ void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) { if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) { mutex_lock(&fs_info->qgroup_rescan_lock); fs_info->qgroup_rescan_running = true; btrfs_queue_work(fs_info->qgroup_rescan_workers, &fs_info->qgroup_rescan_work); mutex_unlock(&fs_info->qgroup_rescan_lock); } } #define rbtree_iterate_from_safe(node, next, start) \ for (node = start; node && ({ next = rb_next(node); 1;}); node = next) static int qgroup_unreserve_range(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len) { struct rb_node *node; struct rb_node *next; struct ulist_node *entry; int ret = 0; node = reserved->range_changed.root.rb_node; if (!node) return 0; while (node) { entry = rb_entry(node, struct ulist_node, rb_node); if (entry->val < start) node = node->rb_right; else node = node->rb_left; } if (entry->val > start && rb_prev(&entry->rb_node)) entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, rb_node); rbtree_iterate_from_safe(node, next, &entry->rb_node) { u64 entry_start; u64 entry_end; u64 entry_len; int clear_ret; entry = rb_entry(node, struct ulist_node, rb_node); entry_start = entry->val; entry_end = entry->aux; entry_len = entry_end - entry_start + 1; if (entry_start >= start + len) break; if (entry_start + entry_len <= start) continue; /* * Now the entry is in [start, start + len), revert the * EXTENT_QGROUP_RESERVED bit. */ clear_ret = btrfs_clear_extent_bit(&inode->io_tree, entry_start, entry_end, EXTENT_QGROUP_RESERVED, NULL); if (!ret && clear_ret < 0) ret = clear_ret; ulist_del(&reserved->range_changed, entry->val, entry->aux); if (likely(reserved->bytes_changed >= entry_len)) { reserved->bytes_changed -= entry_len; } else { WARN_ON(1); reserved->bytes_changed = 0; } } return ret; } /* * Try to free some space for qgroup. * * For qgroup, there are only 3 ways to free qgroup space: * - Flush nodatacow write * Any nodatacow write will free its reserved data space at run_delalloc_range(). * In theory, we should only flush nodatacow inodes, but it's not yet * possible, so we need to flush the whole root. * * - Wait for ordered extents * When ordered extents are finished, their reserved metadata is finally * converted to per_trans status, which can be freed by later commit * transaction. * * - Commit transaction * This would free the meta_per_trans space. * In theory this shouldn't provide much space, but any more qgroup space * is needed. */ static int try_flush_qgroup(struct btrfs_root *root) { int ret; /* Can't hold an open transaction or we run the risk of deadlocking. */ ASSERT(current->journal_info == NULL); if (WARN_ON(current->journal_info)) return 0; /* * We don't want to run flush again and again, so if there is a running * one, we won't try to start a new flush, but exit directly. */ if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { wait_event(root->qgroup_flush_wait, !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); return 0; } ret = btrfs_start_delalloc_snapshot(root, true); if (ret < 0) goto out; btrfs_wait_ordered_extents(root, U64_MAX, NULL); /* * After waiting for ordered extents run delayed iputs in order to free * space from unlinked files before committing the current transaction, * as ordered extents may have been holding the last reference of an * inode and they add a delayed iput when they complete. */ btrfs_run_delayed_iputs(root->fs_info); btrfs_wait_on_delayed_iputs(root->fs_info); ret = btrfs_commit_current_transaction(root); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); return ret; } static int qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved_ret, u64 start, u64 len) { struct btrfs_root *root = inode->root; struct extent_changeset *reserved; bool new_reserved = false; u64 orig_reserved; u64 to_reserve; int ret; if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED || !btrfs_is_fstree(btrfs_root_id(root)) || len == 0) return 0; /* @reserved parameter is mandatory for qgroup */ if (WARN_ON(!reserved_ret)) return -EINVAL; if (!*reserved_ret) { new_reserved = true; *reserved_ret = extent_changeset_alloc(); if (!*reserved_ret) return -ENOMEM; } reserved = *reserved_ret; /* Record already reserved space */ orig_reserved = reserved->bytes_changed; ret = btrfs_set_record_extent_bits(&inode->io_tree, start, start + len - 1, EXTENT_QGROUP_RESERVED, reserved); /* Newly reserved space */ to_reserve = reserved->bytes_changed - orig_reserved; trace_btrfs_qgroup_reserve_data(&inode->vfs_inode, start, len, to_reserve, QGROUP_RESERVE); if (ret < 0) goto out; ret = qgroup_reserve(root, to_reserve, true, BTRFS_QGROUP_RSV_DATA); if (ret < 0) goto cleanup; return ret; cleanup: qgroup_unreserve_range(inode, reserved, start, len); out: if (new_reserved) { extent_changeset_free(reserved); *reserved_ret = NULL; } return ret; } /* * Reserve qgroup space for range [start, start + len). * * This function will either reserve space from related qgroups or do nothing * if the range is already reserved. * * Return 0 for successful reservation * Return <0 for error (including -EQUOT) * * NOTE: This function may sleep for memory allocation, dirty page flushing and * commit transaction. So caller should not hold any dirty page locked. */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved_ret, u64 start, u64 len) { int ret; ret = qgroup_reserve_data(inode, reserved_ret, start, len); if (ret <= 0 && ret != -EDQUOT) return ret; ret = try_flush_qgroup(inode->root); if (ret < 0) return ret; return qgroup_reserve_data(inode, reserved_ret, start, len); } /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; u64 freed = 0; int ret; extent_changeset_init(&changeset); len = round_up(start + len, root->fs_info->sectorsize); start = round_down(start, root->fs_info->sectorsize); ULIST_ITER_INIT(&uiter); while ((unode = ulist_next(&reserved->range_changed, &uiter))) { u64 range_start = unode->val; /* unode->aux is the inclusive end */ u64 range_len = unode->aux - range_start + 1; u64 free_start; u64 free_len; extent_changeset_release(&changeset); /* Only free range in range [start, start + len) */ if (range_start >= start + len || range_start + range_len <= start) continue; free_start = max(range_start, start); free_len = min(start + len, range_start + range_len) - free_start; /* * TODO: To also modify reserved->ranges_reserved to reflect * the modification. * * However as long as we free qgroup reserved according to * EXTENT_QGROUP_RESERVED, we won't double free. * So not need to rush. */ ret = btrfs_clear_record_extent_bits(&inode->io_tree, free_start, free_start + free_len - 1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) goto out; freed += changeset.bytes_changed; } btrfs_qgroup_free_refroot(root->fs_info, btrfs_root_id(root), freed, BTRFS_QGROUP_RSV_DATA); if (freed_ret) *freed_ret = freed; ret = 0; out: extent_changeset_release(&changeset); return ret; } static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; int ret; if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) { return btrfs_clear_record_extent_bits(&inode->io_tree, start, start + len - 1, EXTENT_QGROUP_RESERVED, NULL); } /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = btrfs_clear_record_extent_bits(&inode->io_tree, start, start + len - 1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) goto out; if (free) trace_op = QGROUP_FREE; trace_btrfs_qgroup_release_data(&inode->vfs_inode, start, len, changeset.bytes_changed, trace_op); if (free) btrfs_qgroup_free_refroot(inode->root->fs_info, btrfs_root_id(inode->root), changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); if (released) *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; } /* * Free a reserved space range from io_tree and related qgroups * * Should be called when a range of pages get invalidated before reaching disk. * Or for error cleanup case. * if @reserved is given, only reserved range in [@start, @start + @len) will * be freed. * * For data written to disk, use btrfs_qgroup_release_data(). * * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, u64 *freed) { return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* * Release a reserved space range from io_tree only. * * Should be called when a range of pages get written to disk and corresponding * FILE_EXTENT is inserted into corresponding root. * * Since new qgroup accounting framework will only update qgroup numbers at * commit_transaction() time, its reserved space shouldn't be freed from * related qgroups. * * But we should release the range from io_tree, to allow further write to be * COWed. * * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type) { if (type != BTRFS_QGROUP_RSV_META_PREALLOC && type != BTRFS_QGROUP_RSV_META_PERTRANS) return; if (num_bytes == 0) return; spin_lock(&root->qgroup_meta_rsv_lock); if (type == BTRFS_QGROUP_RSV_META_PREALLOC) root->qgroup_meta_rsv_prealloc += num_bytes; else root->qgroup_meta_rsv_pertrans += num_bytes; spin_unlock(&root->qgroup_meta_rsv_lock); } static int sub_root_meta_rsv(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type) { if (type != BTRFS_QGROUP_RSV_META_PREALLOC && type != BTRFS_QGROUP_RSV_META_PERTRANS) return 0; if (num_bytes == 0) return 0; spin_lock(&root->qgroup_meta_rsv_lock); if (type == BTRFS_QGROUP_RSV_META_PREALLOC) { num_bytes = min_t(u64, root->qgroup_meta_rsv_prealloc, num_bytes); root->qgroup_meta_rsv_prealloc -= num_bytes; } else { num_bytes = min_t(u64, root->qgroup_meta_rsv_pertrans, num_bytes); root->qgroup_meta_rsv_pertrans -= num_bytes; } spin_unlock(&root->qgroup_meta_rsv_lock); return num_bytes; } int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !btrfs_is_fstree(btrfs_root_id(root)) || num_bytes == 0) return 0; BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); trace_btrfs_qgroup_meta_reserve(root, (s64)num_bytes, type); ret = qgroup_reserve(root, num_bytes, enforce, type); if (ret < 0) return ret; /* * Record what we have reserved into root. * * To avoid quota disabled->enabled underflow. * In that case, we may try to free space we haven't reserved * (since quota was disabled), so record what we reserved into root. * And ensure later release won't underflow this number. */ add_root_meta_rsv(root, num_bytes, type); return ret; } int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce, bool noflush) { int ret; ret = btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce); if ((ret <= 0 && ret != -EDQUOT) || noflush) return ret; ret = try_flush_qgroup(root); if (ret < 0) return ret; return btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce); } /* * Per-transaction meta reservation should be all freed at transaction commit * time */ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !btrfs_is_fstree(btrfs_root_id(root))) return; /* TODO: Update trace point to handle such free */ trace_btrfs_qgroup_meta_free_all_pertrans(root); /* Special value -1 means to free all reserved space */ btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), (u64)-1, BTRFS_QGROUP_RSV_META_PERTRANS); } void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type) { struct btrfs_fs_info *fs_info = root->fs_info; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !btrfs_is_fstree(btrfs_root_id(root))) return; /* * reservation for META_PREALLOC can happen before quota is enabled, * which can lead to underflow. * Here ensure we will only free what we really have reserved. */ num_bytes = sub_root_meta_rsv(root, num_bytes, type); BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize)); trace_btrfs_qgroup_meta_reserve(root, -(s64)num_bytes, type); btrfs_qgroup_free_refroot(fs_info, btrfs_root_id(root), num_bytes, type); } static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, int num_bytes) { struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); if (num_bytes == 0) return; if (!fs_info->quota_root) return; spin_lock(&fs_info->qgroup_lock); qgroup = find_qgroup_rb(fs_info, ref_root); if (!qgroup) goto out; qgroup_iterator_add(&qgroup_list, qgroup); list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup_rsv_release(fs_info, qgroup, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); if (!sb_rdonly(fs_info->sb)) qgroup_rsv_add(fs_info, qgroup, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); list_for_each_entry(glist, &qgroup->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); } out: qgroup_iterator_clean(&qgroup_list); spin_unlock(&fs_info->qgroup_lock); } /* * Convert @num_bytes of META_PREALLOCATED reservation to META_PERTRANS. * * This is called when preallocated meta reservation needs to be used. * Normally after btrfs_join_transaction() call. */ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) { struct btrfs_fs_info *fs_info = root->fs_info; if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED || !btrfs_is_fstree(btrfs_root_id(root))) return; /* Same as btrfs_qgroup_free_meta_prealloc() */ num_bytes = sub_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); trace_btrfs_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, btrfs_root_id(root), num_bytes); if (!sb_rdonly(fs_info->sb)) add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* * Check qgroup reserved space leaking, normally at destroy inode * time */ void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode) { struct extent_changeset changeset; struct ulist_node *unode; struct ulist_iterator iter; int ret; extent_changeset_init(&changeset); ret = btrfs_clear_record_extent_bits(&inode->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); WARN_ON(ret < 0); if (WARN_ON(changeset.bytes_changed)) { ULIST_ITER_INIT(&iter); while ((unode = ulist_next(&changeset.range_changed, &iter))) { btrfs_warn(inode->root->fs_info, "leaking qgroup reserved space, ino: %llu, start: %llu, end: %llu", btrfs_ino(inode), unode->val, unode->aux); } btrfs_qgroup_free_refroot(inode->root->fs_info, btrfs_root_id(inode->root), changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); } extent_changeset_release(&changeset); } void btrfs_qgroup_init_swapped_blocks( struct btrfs_qgroup_swapped_blocks *swapped_blocks) { int i; spin_lock_init(&swapped_blocks->lock); for (i = 0; i < BTRFS_MAX_LEVEL; i++) swapped_blocks->blocks[i] = RB_ROOT; swapped_blocks->swapped = false; } /* * Delete all swapped blocks record of @root. * Every record here means we skipped a full subtree scan for qgroup. * * Gets called when committing one transaction. */ void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root) { struct btrfs_qgroup_swapped_blocks *swapped_blocks; int i; swapped_blocks = &root->swapped_blocks; spin_lock(&swapped_blocks->lock); if (!swapped_blocks->swapped) goto out; for (i = 0; i < BTRFS_MAX_LEVEL; i++) { struct rb_root *cur_root = &swapped_blocks->blocks[i]; struct btrfs_qgroup_swapped_block *entry; struct btrfs_qgroup_swapped_block *next; rbtree_postorder_for_each_entry_safe(entry, next, cur_root, node) kfree(entry); swapped_blocks->blocks[i] = RB_ROOT; } swapped_blocks->swapped = false; out: spin_unlock(&swapped_blocks->lock); } static int qgroup_swapped_block_bytenr_key_cmp(const void *key, const struct rb_node *node) { const u64 *bytenr = key; const struct btrfs_qgroup_swapped_block *block = rb_entry(node, struct btrfs_qgroup_swapped_block, node); if (block->subvol_bytenr < *bytenr) return -1; else if (block->subvol_bytenr > *bytenr) return 1; return 0; } static int qgroup_swapped_block_bytenr_cmp(struct rb_node *new, const struct rb_node *existing) { const struct btrfs_qgroup_swapped_block *new_block = rb_entry(new, struct btrfs_qgroup_swapped_block, node); return qgroup_swapped_block_bytenr_key_cmp(&new_block->subvol_bytenr, existing); } /* * Add subtree roots record into @subvol_root. * * @subvol_root: tree root of the subvolume tree get swapped * @bg: block group under balance * @subvol_parent/slot: pointer to the subtree root in subvolume tree * @reloc_parent/slot: pointer to the subtree root in reloc tree * BOTH POINTERS ARE BEFORE TREE SWAP * @last_snapshot: last snapshot generation of the subvolume tree */ int btrfs_qgroup_add_swapped_blocks(struct btrfs_root *subvol_root, struct btrfs_block_group *bg, struct extent_buffer *subvol_parent, int subvol_slot, struct extent_buffer *reloc_parent, int reloc_slot, u64 last_snapshot) { struct btrfs_fs_info *fs_info = subvol_root->fs_info; struct btrfs_qgroup_swapped_blocks *blocks = &subvol_root->swapped_blocks; struct btrfs_qgroup_swapped_block *block; struct rb_node *node; int level = btrfs_header_level(subvol_parent) - 1; int ret = 0; if (!btrfs_qgroup_full_accounting(fs_info)) return 0; if (unlikely(btrfs_node_ptr_generation(subvol_parent, subvol_slot) > btrfs_node_ptr_generation(reloc_parent, reloc_slot))) { btrfs_err_rl(fs_info, "%s: bad parameter order, subvol_gen=%llu reloc_gen=%llu", __func__, btrfs_node_ptr_generation(subvol_parent, subvol_slot), btrfs_node_ptr_generation(reloc_parent, reloc_slot)); return -EUCLEAN; } block = kmalloc(sizeof(*block), GFP_NOFS); if (!block) { ret = -ENOMEM; goto out; } /* * @reloc_parent/slot is still before swap, while @block is going to * record the bytenr after swap, so we do the swap here. */ block->subvol_bytenr = btrfs_node_blockptr(reloc_parent, reloc_slot); block->subvol_generation = btrfs_node_ptr_generation(reloc_parent, reloc_slot); block->reloc_bytenr = btrfs_node_blockptr(subvol_parent, subvol_slot); block->reloc_generation = btrfs_node_ptr_generation(subvol_parent, subvol_slot); block->last_snapshot = last_snapshot; block->level = level; /* * If we have bg == NULL, we're called from btrfs_recover_relocation(), * no one else can modify tree blocks thus we qgroup will not change * no matter the value of trace_leaf. */ if (bg && bg->flags & BTRFS_BLOCK_GROUP_DATA) block->trace_leaf = true; else block->trace_leaf = false; btrfs_node_key_to_cpu(reloc_parent, &block->first_key, reloc_slot); /* Insert @block into @blocks */ spin_lock(&blocks->lock); node = rb_find_add(&block->node, &blocks->blocks[level], qgroup_swapped_block_bytenr_cmp); if (node) { struct btrfs_qgroup_swapped_block *entry; entry = rb_entry(node, struct btrfs_qgroup_swapped_block, node); if (entry->subvol_generation != block->subvol_generation || entry->reloc_bytenr != block->reloc_bytenr || entry->reloc_generation != block->reloc_generation) { /* * Duplicated but mismatch entry found. Shouldn't happen. * Marking qgroup inconsistent should be enough for end * users. */ DEBUG_WARN("duplicated but mismatched entry found"); ret = -EEXIST; } kfree(block); goto out_unlock; } blocks->swapped = true; out_unlock: spin_unlock(&blocks->lock); out: if (ret < 0) qgroup_mark_inconsistent(fs_info, "%s error: %d", __func__, ret); return ret; } /* * Check if the tree block is a subtree root, and if so do the needed * delayed subtree trace for qgroup. * * This is called during btrfs_cow_block(). */ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *subvol_eb) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_tree_parent_check check = { 0 }; struct btrfs_qgroup_swapped_blocks *blocks = &root->swapped_blocks; struct btrfs_qgroup_swapped_block *block; struct extent_buffer *reloc_eb = NULL; struct rb_node *node; bool swapped = false; int level = btrfs_header_level(subvol_eb); int ret = 0; int i; if (!btrfs_qgroup_full_accounting(fs_info)) return 0; if (!btrfs_is_fstree(btrfs_root_id(root)) || !root->reloc_root) return 0; spin_lock(&blocks->lock); if (!blocks->swapped) { spin_unlock(&blocks->lock); return 0; } node = rb_find(&subvol_eb->start, &blocks->blocks[level], qgroup_swapped_block_bytenr_key_cmp); if (!node) { spin_unlock(&blocks->lock); goto out; } block = rb_entry(node, struct btrfs_qgroup_swapped_block, node); /* Found one, remove it from @blocks first and update blocks->swapped */ rb_erase(&block->node, &blocks->blocks[level]); for (i = 0; i < BTRFS_MAX_LEVEL; i++) { if (RB_EMPTY_ROOT(&blocks->blocks[i])) { swapped = true; break; } } blocks->swapped = swapped; spin_unlock(&blocks->lock); check.level = block->level; check.transid = block->reloc_generation; check.has_first_key = true; memcpy(&check.first_key, &block->first_key, sizeof(check.first_key)); /* Read out reloc subtree root */ reloc_eb = read_tree_block(fs_info, block->reloc_bytenr, &check); if (IS_ERR(reloc_eb)) { ret = PTR_ERR(reloc_eb); reloc_eb = NULL; goto free_out; } if (unlikely(!extent_buffer_uptodate(reloc_eb))) { ret = -EIO; goto free_out; } ret = qgroup_trace_subtree_swap(trans, reloc_eb, subvol_eb, block->last_snapshot, block->trace_leaf); free_out: kfree(block); free_extent_buffer(reloc_eb); out: if (ret < 0) { qgroup_mark_inconsistent(fs_info, "failed to account subtree at bytenr %llu: %d", subvol_eb->start, ret); } return ret; } void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) { struct btrfs_qgroup_extent_record *entry; unsigned long index; xa_for_each(&trans->delayed_refs.dirty_extents, index, entry) { ulist_free(entry->old_roots); kfree(entry); } xa_destroy(&trans->delayed_refs.dirty_extents); } int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info, const struct btrfs_squota_delta *delta) { int ret; struct btrfs_qgroup *qgroup; struct btrfs_qgroup *qg; LIST_HEAD(qgroup_list); u64 root = delta->root; u64 num_bytes = delta->num_bytes; const int sign = (delta->is_inc ? 1 : -1); if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE) return 0; if (!btrfs_is_fstree(root)) return 0; /* If the extent predates enabling quotas, don't count it. */ if (delta->generation < fs_info->qgroup_enable_gen) return 0; spin_lock(&fs_info->qgroup_lock); qgroup = find_qgroup_rb(fs_info, root); if (!qgroup) { ret = -ENOENT; goto out; } ret = 0; qgroup_iterator_add(&qgroup_list, qgroup); list_for_each_entry(qg, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qg->excl += num_bytes * sign; qg->rfer += num_bytes * sign; qgroup_dirty(fs_info, qg); list_for_each_entry(glist, &qg->groups, next_group) qgroup_iterator_add(&qgroup_list, glist->group); } qgroup_iterator_clean(&qgroup_list); out: spin_unlock(&fs_info->qgroup_lock); return ret; } |
| 24 23 3 786 5524 5386 784 5529 130 1 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> #include <linux/srcu.h> #include <linux/rw_hint.h> #include <linux/rwsem.h> struct blk_mq_tags; struct blk_flush_queue; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 enum rq_end_io_ret { RQ_END_IO_NONE, RQ_END_IO_FREE, }; typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ __RQF_FLUSH_SEQ, /* merge of different types, fail separately */ __RQF_MIXED_MERGE, /* don't call prep for this one */ __RQF_DONTPREP, /* use hctx->sched_tags */ __RQF_SCHED_TAGS, /* use an I/O scheduler for this request */ __RQF_USE_SCHED, /* vaguely specified driver internal error. Ignored by block layer */ __RQF_FAILED, /* don't warn about errors */ __RQF_QUIET, /* account into disk and partition IO statistics */ __RQF_IO_STAT, /* runtime pm request */ __RQF_PM, /* on IO scheduler merge hash */ __RQF_HASHED, /* track IO completion time */ __RQF_STATS, /* Look at ->special_vec for the actual data payload instead of the bio chain. */ __RQF_SPECIAL_PAYLOAD, /* request completion needs to be signaled to zone write plugging. */ __RQF_ZONE_WRITE_PLUGGING, /* ->timeout has been called, don't expire again */ __RQF_TIMED_OUT, __RQF_RESV, __RQF_BITS }; #define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) #define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) #define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) #define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) #define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) #define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) #define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) #define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) #define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) #define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) #define RQF_SPECIAL_PAYLOAD \ ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) #define RQF_ZONE_WRITE_PLUGGING \ ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) #define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) #define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; unsigned int timeout; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; union { struct list_head queuelist; struct request *rq_next; }; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; unsigned short nr_integrity_segments; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif enum mq_rq_state state; atomic_t ref; unsigned long deadline; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct llist_node ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. special_vec must * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; rq_end_io_fn *saved_end_io; } flush; u64 fifo_time; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; static inline enum req_op req_op(const struct request *req) { return req->cmd_flags & REQ_OP_MASK; } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) { if (req->bio) return req->bio->bi_ioprio; return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) static inline int rq_list_empty(const struct rq_list *rl) { return rl->head == NULL; } static inline void rq_list_init(struct rq_list *rl) { rl->head = NULL; rl->tail = NULL; } static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) { rq->rq_next = NULL; if (rl->tail) rl->tail->rq_next = rq; else rl->head = rq; rl->tail = rq; } static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) { rq->rq_next = rl->head; rl->head = rq; if (!rl->tail) rl->tail = rq; } static inline struct request *rq_list_pop(struct rq_list *rl) { struct request *rq = rl->head; if (rq) { rl->head = rl->head->rq_next; if (!rl->head) rl->tail = NULL; rq->rq_next = NULL; } return rq; } static inline struct request *rq_list_peek(struct rq_list *rl) { return rl->head; } #define rq_list_for_each(rl, pos) \ for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) #define rq_list_for_each_safe(rl, pos, nxt) \ for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at * a later time. * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the * request to complete. */ enum blk_eh_timer_return { BLK_EH_DONE, BLK_EH_RESET_TIMER, }; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_type - Type of hardware queue * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. * @HCTX_TYPE_READ: Just for READ I/O. * @HCTX_TYPE_POLL: Polled I/O of any kind. * @HCTX_MAX_TYPES: Number of types of hctx. */ enum hctx_type { HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; /** * struct blk_mq_tag_set - tag set that can be shared between request queues * @ops: Pointers to functions that implement block driver behavior. * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the * same size, and it's perfectly legal to share maps between * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag * allocations. * @cmd_size: Number of additional bytes to allocate per request. The block * driver owns these additional bytes. * @numa_node: NUMA node the storage adapter has been connected to. * @timeout: Request processing timeout in jiffies. * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @shared_tags: * Shared set of tags. Has @nr_hw_queues elements. If set, * shared by all @tags. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. * @srcu: Use as lock when type of the request queue is blocking * (BLK_MQ_F_BLOCKING). * @tags_srcu: SRCU used to defer freeing of tags page_list to prevent * use-after-free when iterating tags. * @update_nr_hwq_lock: * Synchronize updating nr_hw_queues with add/del disk & * switching elevator. */ struct blk_mq_tag_set { const struct blk_mq_ops *ops; struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; unsigned int cmd_size; int numa_node; unsigned int timeout; unsigned int flags; void *driver_data; struct blk_mq_tags **tags; struct blk_mq_tags *shared_tags; struct mutex tag_list_lock; struct list_head tag_list; struct srcu_struct *srcu; struct srcu_struct tags_srcu; struct rw_semaphore update_nr_hwq_lock; }; /** * struct blk_mq_queue_data - Data about a request inserted in a queue * * @rq: Request pointer. * @last: If it is the last request in the queue. */ struct blk_mq_queue_data { struct request *rq; bool last; }; typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver * behaviour. */ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit * requests to hardware, it must define this function. In case of errors * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @queue_rqs: Queue a list of new requests. Driver is guaranteed * that each request belongs to the same queue. If the driver doesn't * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ int (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ void (*put_budget)(struct request_queue *, int); /** * @set_rq_budget_token: store rq's budget token */ void (*set_rq_budget_token)(struct request *, int); /** * @get_rq_budget_token: retrieve rq's budget token */ int (*get_rq_budget_token)(struct request *); /** * @timeout: Called on request timeout. */ enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. */ int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *); /** * @complete: Mark the request as complete. */ void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. */ int (*init_request)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); /** * @exit_request: Ditto for exit/teardown. */ void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); #endif }; /* Keep hctx_flag_name[] in sync with the definitions below */ enum { BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 4, /* * Alloc tags on a round-robin base instead of the first available one. */ BLK_MQ_F_TAG_RR = 1 << 5, /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, BLK_MQ_F_MAX = 1 << 7, }; #define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) enum { /* Keep hctx_state_name[] in sync with the definitions below */ BLK_MQ_S_STOPPED, BLK_MQ_S_TAG_ACTIVE, BLK_MQ_S_SCHED_RESTART, /* hw queue is inactive after all its CPUs become offline */ BLK_MQ_S_INACTIVE, BLK_MQ_S_MAX }; struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, lim, queuedata) \ ({ \ static struct lock_class_key __key; \ \ __blk_mq_alloc_disk(set, lim, queuedata, &__key); \ }) struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass); struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_destroy_queue(struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_free_request(struct request *rq); int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags); bool blk_mq_queue_inflight(struct request_queue *q); enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), /* set RQF_PM */ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx); /* * Tag address space map. */ struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; struct request **rqs; struct request **static_rqs; struct list_head page_list; /* * used to clear request reference in rqs[] before freeing one * request pool */ spinlock_t lock; struct rcu_head rcu_head; }; static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; } enum { BLK_MQ_UNIQUE_TAG_BITS = 16, BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1, }; u32 blk_mq_unique_tag(struct request *rq); static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag) { return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS; } static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) { return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } /** * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { return READ_ONCE(rq->state); } static inline int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } static inline int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } /* * * Set the state to complete when completing a request from inside ->queue_rq. * This is used by drivers that want to ensure special complete actions that * need access to the request are called on failure, e.g. by nvme for * multipathing. */ static inline void blk_mq_set_request_complete(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } /* * Complete the request directly instead of deferring it to softirq or * completing it another CPU. Useful in preemptible instead of an interrupt. */ static inline void blk_mq_complete_request_direct(struct request *rq, void (*complete)(struct request *rq)) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); complete(rq); } void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_end_request_batch(struct io_comp_batch *ib); /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. */ static inline bool blk_mq_need_time_stamp(struct request *rq) { return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) { return rq->rq_flags & RQF_RESV; } /** * blk_mq_add_to_batch() - add a request to the completion batch * @req: The request to add to batch * @iob: The batch to add the request * @is_error: Specify true if the request failed with an error * @complete: The completaion handler for the request * * Batched completions only work when there is no I/O error and no special * ->end_io handler. * * Return: true when the request was added to the batch, otherwise false */ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, bool is_error, void (*complete)(struct io_comp_batch *)) { /* * Check various conditions that exclude batch processing: * 1) No batch container * 2) Has scheduler data attached * 3) Not a passthrough request and end_io set * 4) Not a passthrough request and failed with an error */ if (!iob) return false; if (req->rq_flags & RQF_SCHED_TAGS) return false; if (!blk_rq_is_passthrough(req)) { if (req->end_io) return false; if (is_error) return false; } if (!iob->complete) iob->complete = complete; else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); rq_list_add_tail(&iob->req_list, req); return true; } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); void blk_mq_freeze_queue_nomemsave(struct request_queue *q); void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); static inline unsigned int __must_check blk_mq_freeze_queue(struct request_queue *q) { unsigned int memflags = memalloc_noio_save(); blk_mq_freeze_queue_nomemsave(q); return memflags; } static inline void blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) { blk_mq_unfreeze_queue_nomemrestore(q); memalloc_noio_restore(memflags); } void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); void blk_freeze_queue_start_non_owner(struct request_queue *q); unsigned int blk_mq_num_possible_queues(unsigned int max_queues); unsigned int blk_mq_num_online_queues(unsigned int max_queues); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); bool __blk_should_fake_timeout(struct request_queue *q); static inline bool blk_should_fake_timeout(struct request_queue *q) { if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return __blk_should_fake_timeout(q); return false; } /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted * * Return: request * * Driver command data is immediately after the request. So subtract request * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } /** * blk_mq_rq_to_pdu - cast a request to a PDU * @rq: the request to be casted * * Return: pointer to the PDU * * Driver command data is immediately after the request. So add request to get * the PDU. */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; } #define queue_for_each_hw_ctx(q, hctx, i) \ xa_for_each(&(q)->hctx_table, (i), (hctx)) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) rq->q->mq_ops->cleanup_rq(rq); } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } void blk_rq_init(struct request_queue *q, struct request *rq); int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; unsigned long offset; unsigned short page_order; unsigned short nr_entries; bool null_mapped; bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); int blk_rq_map_user_io(struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t, bool, int, bool, int); int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp); int blk_rq_append_bio(struct request *rq, struct bio *bio); void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); bool blk_rq_is_poll(struct request *rq); struct req_iterator { struct bvec_iter iter; struct bio *bio; }; #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { if (!rq->bio) return 0; if (!bio_has_data(rq->bio)) /* dataless requests such as discard */ return rq->bio->bi_iter.bi_size; return bio_iovec(rq->bio).bv_len; } static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); void blk_abort_request(struct request *); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(rq, sglist, &last_sg); } void blk_dump_rq_flags(struct request *, char *); #endif /* BLK_MQ_H */ |
| 574 20 41 144 999 30 12 294 316 316 9275 354 3816 294 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H /* * Copyright 1992, Linus Torvalds. * * Note: inlines with more than a single statement should be marked * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> #include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 #elif BITS_PER_LONG == 64 # define _BITOPS_LONG_SHIFT 6 #else # error "Unexpected BITS_PER_LONG" #endif #define BIT_64(n) (U64_C(1) << (n)) /* * These have to be done with inline assembly: that way the bit-setting * is guaranteed to be atomic. All bit operations return 0 if the bit * was cleared before the operation and != 0 if it was not. * * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ #define RLONG_ADDR(x) "m" (*(volatile long *) (x)) #define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) #define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr)) : "memory"); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch___set_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (~CONST_MASK(nr))); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); arch_clear_bit(nr, addr); } static __always_inline void arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { bool negative; asm_inline volatile(LOCK_PREFIX "xorb %2,%1" : "=@ccs" (negative), WBYTE_ADDR(addr) : "iq" ((char)mask) : "memory"); return negative; } #define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { arch___clear_bit(nr, addr); } static __always_inline void arch___change_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm_inline volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr))); } else { asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline bool arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } static __always_inline bool arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return arch_test_and_set_bit(nr, addr); } static __always_inline bool arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. * KVM relies on this behaviour on x86 for modifying memory that is also * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" : "=@ccc" (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) { bool oldbit; asm volatile("testb %2,%1" : "=@ccnz" (oldbit) : "m" (((unsigned char *)addr)[nr >> 3]), "i" (1 << (nr & 7)) :"memory"); return oldbit; } static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" : "=@ccc" (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) : variable_test_bit(nr, addr); } static __always_inline bool arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : variable_test_bit(nr, addr); } static __always_inline __attribute_const__ unsigned long variable__ffs(unsigned long word) { asm("tzcnt %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ #define __ffs(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(word) : \ variable__ffs(word)) static __always_inline __attribute_const__ unsigned long variable_ffz(unsigned long word) { return variable__ffs(~word); } /** * ffz - find first zero bit in word * @word: The word to search * * Undefined if no zero exists, so code should check against ~0UL first. */ #define ffz(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(~word) : \ variable_ffz(word)) /* * __fls: find last set bit in word * @word: The word to search * * Undefined if no set bit exists, so code should check against 0 first. */ static __always_inline __attribute_const__ unsigned long __fls(unsigned long word) { if (__builtin_constant_p(word)) return BITS_PER_LONG - 1 - __builtin_clzl(word); asm("bsr %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } #undef ADDR #ifdef __KERNEL__ static __always_inline __attribute_const__ int variable_ffs(int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsfl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * ffs - find first set bit in word * @x: the word to search * * This is defined the same way as the libc and compiler builtin ffs * routines, therefore differs in spirit from the other bitops. * * ffs(value) returns 0 if value is 0 or the position of the first * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ #define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) /** * fls - find last set bit in word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffs, but returns the position of the most significant set bit. * * fls(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ static __always_inline __attribute_const__ int fls(unsigned int x) { int r; if (__builtin_constant_p(x)) return x ? 32 - __builtin_clz(x) : 0; #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsrl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); #else asm("bsrl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls64 - find last set bit in a 64-bit word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffsll, but returns the position of the most significant set bit. * * fls64(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 64. */ #ifdef CONFIG_X86_64 static __always_inline __attribute_const__ int fls64(__u64 x) { int bitpos = -1; if (__builtin_constant_p(x)) return x ? 64 - __builtin_clzll(x) : 0; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ asm("bsrq %1,%q0" : "+r" (bitpos) : ASM_INPUT_RM (x)); return bitpos + 1; } #else #include <asm-generic/bitops/fls64.h> #endif #include <asm-generic/bitops/sched.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ |
| 95 28 67 67 50 52 151 6 2 150 263 153 106 2 10 99 323 323 24 254 229 322 322 1 14 70 83 82 1 9 8 10 76 89 84 3 85 3 2 84 100 3 100 91 2 3 88 3 83 21 1 1 81 1 80 1 58 22 91 56 25 10 6 1 1 3 1 4 5 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * Directory handling functions for NTFS-based filesystems. * */ #include <linux/fs.h> #include <linux/nls.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* Convert little endian UTF-16 to NLS string. */ int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const __le16 *name, u32 len, u8 *buf, int buf_len) { int ret, warn; u8 *op; struct nls_table *nls = sbi->options->nls; static_assert(sizeof(wchar_t) == sizeof(__le16)); if (!nls) { /* UTF-16 -> UTF-8 */ ret = utf16s_to_utf8s((wchar_t *)name, len, UTF16_LITTLE_ENDIAN, buf, buf_len); buf[ret] = '\0'; return ret; } op = buf; warn = 0; while (len--) { u16 ec; int charlen; char dump[5]; if (buf_len < NLS_MAX_CHARSET_SIZE) { ntfs_warn(sbi->sb, "filename was truncated while converting."); break; } ec = le16_to_cpu(*name++); charlen = nls->uni2char(ec, op, buf_len); if (charlen > 0) { op += charlen; buf_len -= charlen; continue; } *op++ = '_'; buf_len -= 1; if (warn) continue; warn = 1; hex_byte_pack(&dump[0], ec >> 8); hex_byte_pack(&dump[2], ec); dump[4] = 0; ntfs_err(sbi->sb, "failed to convert \"%s\" to %s", dump, nls->charset); } *op = '\0'; return op - buf; } // clang-format off #define PLANE_SIZE 0x00010000 #define SURROGATE_PAIR 0x0000d800 #define SURROGATE_LOW 0x00000400 #define SURROGATE_BITS 0x000003ff // clang-format on /* * put_utf16 - Modified version of put_utf16 from fs/nls/nls_base.c * * Function is sparse warnings free. */ static inline void put_utf16(wchar_t *s, unsigned int c, enum utf16_endian endian) { static_assert(sizeof(wchar_t) == sizeof(__le16)); static_assert(sizeof(wchar_t) == sizeof(__be16)); switch (endian) { default: *s = (wchar_t)c; break; case UTF16_LITTLE_ENDIAN: *(__le16 *)s = __cpu_to_le16(c); break; case UTF16_BIG_ENDIAN: *(__be16 *)s = __cpu_to_be16(c); break; } } /* * _utf8s_to_utf16s * * Modified version of 'utf8s_to_utf16s' allows to * detect -ENAMETOOLONG without writing out of expected maximum. */ static int _utf8s_to_utf16s(const u8 *s, int inlen, enum utf16_endian endian, wchar_t *pwcs, int maxout) { u16 *op; int size; unicode_t u; op = pwcs; while (inlen > 0 && *s) { if (*s & 0x80) { size = utf8_to_utf32(s, inlen, &u); if (size < 0) return -EINVAL; s += size; inlen -= size; if (u >= PLANE_SIZE) { if (maxout < 2) return -ENAMETOOLONG; u -= PLANE_SIZE; put_utf16(op++, SURROGATE_PAIR | ((u >> 10) & SURROGATE_BITS), endian); put_utf16(op++, SURROGATE_PAIR | SURROGATE_LOW | (u & SURROGATE_BITS), endian); maxout -= 2; } else { if (maxout < 1) return -ENAMETOOLONG; put_utf16(op++, u, endian); maxout--; } } else { if (maxout < 1) return -ENAMETOOLONG; put_utf16(op++, *s++, endian); inlen--; maxout--; } } return op - pwcs; } /* * ntfs_nls_to_utf16 - Convert input string to UTF-16. * @name: Input name. * @name_len: Input name length. * @uni: Destination memory. * @max_ulen: Destination memory. * @endian: Endian of target UTF-16 string. * * This function is called: * - to create NTFS name * - to create symlink * * Return: UTF-16 string length or error (if negative). */ int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, struct cpu_str *uni, u32 max_ulen, enum utf16_endian endian) { int ret, slen; const u8 *end; struct nls_table *nls = sbi->options->nls; u16 *uname = uni->name; static_assert(sizeof(wchar_t) == sizeof(u16)); if (!nls) { /* utf8 -> utf16 */ ret = _utf8s_to_utf16s(name, name_len, endian, uname, max_ulen); uni->len = ret; return ret; } for (ret = 0, end = name + name_len; name < end; ret++, name += slen) { if (ret >= max_ulen) return -ENAMETOOLONG; slen = nls->char2uni(name, end - name, uname + ret); if (!slen) return -EINVAL; if (slen < 0) return slen; } #ifdef __BIG_ENDIAN if (endian == UTF16_LITTLE_ENDIAN) { int i = ret; while (i--) { __cpu_to_le16s(uname); uname++; } } #else if (endian == UTF16_BIG_ENDIAN) { int i = ret; while (i--) { __cpu_to_be16s(uname); uname++; } } #endif uni->len = ret; return ret; } /* * dir_search_u - Helper function. */ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, struct ntfs_fnd *fnd) { int err = 0; struct super_block *sb = dir->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(dir); struct NTFS_DE *e; int diff; struct inode *inode = NULL; struct ntfs_fnd *fnd_a = NULL; if (!fnd) { fnd_a = fnd_get(); if (!fnd_a) { err = -ENOMEM; goto out; } fnd = fnd_a; } err = indx_find(&ni->dir, ni, NULL, uni, 0, sbi, &diff, &e, fnd); if (err) goto out; if (diff) { err = -ENOENT; goto out; } inode = ntfs_iget5(sb, &e->ref, uni); if (!IS_ERR(inode) && is_bad_inode(inode)) { iput(inode); err = -EINVAL; } out: fnd_put(fnd_a); return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode; } /* * returns false if 'ctx' if full */ static inline bool ntfs_dir_emit(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, const struct NTFS_DE *e, u8 *name, struct dir_context *ctx) { const struct ATTR_FILE_NAME *fname; unsigned long ino; int name_len; u32 dt_type; fname = Add2Ptr(e, sizeof(struct NTFS_DE)); if (fname->type == FILE_NAME_DOS) return true; if (!mi_is_ref(&ni->mi, &fname->home)) return true; ino = ino_get(&e->ref); if (ino == MFT_REC_ROOT) return true; /* Skip meta files. Unless option to show metafiles is set. */ if (!sbi->options->showmeta && ntfs_is_meta_file(sbi, ino)) return true; if (sbi->options->nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN)) return true; if (fname->name_len + sizeof(struct NTFS_DE) > le16_to_cpu(e->size)) return true; name_len = ntfs_utf16_to_nls(sbi, fname->name, fname->name_len, name, PATH_MAX); if (name_len <= 0) { ntfs_warn(sbi->sb, "failed to convert name for inode %lx.", ino); return true; } /* * NTFS: symlinks are "dir + reparse" or "file + reparse" * Unfortunately reparse attribute is used for many purposes (several dozens). * It is not possible here to know is this name symlink or not. * To get exactly the type of name we should to open inode (read mft). * getattr for opened file (fstat) correctly returns symlink. */ dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; /* * It is not reliable to detect the type of name using duplicated information * stored in parent directory. * The only correct way to get the type of name - read MFT record and find ATTR_STD. * The code below is not good idea. * It does additional locks/reads just to get the type of name. * Should we use additional mount option to enable branch below? */ if (fname->dup.extend_data && ino != ni->mi.rno) { struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); if (!IS_ERR_OR_NULL(inode)) { dt_type = fs_umode_to_dtype(inode->i_mode); iput(inode); } } return dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } /* * ntfs_read_hdr - Helper function for ntfs_readdir(). * * returns 0 if ok. * returns -EINVAL if directory is corrupted. * returns +1 if 'ctx' is full. */ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, const struct INDEX_HDR *hdr, u64 vbo, u64 pos, u8 *name, struct dir_context *ctx) { const struct NTFS_DE *e; u32 e_size; u32 end = le32_to_cpu(hdr->used); u32 off = le32_to_cpu(hdr->de_off); for (;; off += e_size) { if (off + sizeof(struct NTFS_DE) > end) return -EINVAL; e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) return -EINVAL; if (de_is_last(e)) return 0; /* Skip already enumerated. */ if (vbo + off < pos) continue; if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME) return -EINVAL; ctx->pos = vbo + off; /* Submit the name to the filldir callback. */ if (!ntfs_dir_emit(sbi, ni, e, name, ctx)) { /* ctx is full. */ return +1; } } } /* * ntfs_readdir - file_operations::iterate_shared * * Use non sorted enumeration. * We have an example of broken volume where sorted enumeration * counts each name twice. */ static int ntfs_readdir(struct file *file, struct dir_context *ctx) { const struct INDEX_ROOT *root; u64 vbo; size_t bit; loff_t eod; int err = 0; struct inode *dir = file_inode(file); struct ntfs_inode *ni = ntfs_i(dir); struct super_block *sb = dir->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; loff_t i_size = i_size_read(dir); u32 pos = ctx->pos; u8 *name = NULL; struct indx_node *node = NULL; u8 index_bits = ni->dir.index_bits; /* Name is a buffer of PATH_MAX length. */ static_assert(NTFS_NAME_LEN * 4 < PATH_MAX); eod = i_size + sbi->record_size; if (pos >= eod) return 0; if (!dir_emit_dots(file, ctx)) return 0; /* Allocate PATH_MAX bytes. */ name = __getname(); if (!name) return -ENOMEM; if (!ni->mi_loaded && ni->attr_list.size) { /* * Directory inode is locked for read. * Load all subrecords to avoid 'write' access to 'ni' during * directory reading. */ ni_lock(ni); if (!ni->mi_loaded && ni->attr_list.size) { err = ni_load_all_mi(ni); if (!err) ni->mi_loaded = true; } ni_unlock(ni); if (err) goto out; } root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) { err = -EINVAL; goto out; } if (pos >= sbi->record_size) { bit = (pos - sbi->record_size) >> index_bits; } else { err = ntfs_read_hdr(sbi, ni, &root->ihdr, 0, pos, name, ctx); if (err) goto out; bit = 0; } if (!i_size) { ctx->pos = eod; goto out; } for (;;) { vbo = (u64)bit << index_bits; if (vbo >= i_size) { ctx->pos = eod; goto out; } err = indx_used_bit(&ni->dir, ni, &bit); if (err) goto out; if (bit == MINUS_ONE_T) { ctx->pos = eod; goto out; } vbo = (u64)bit << index_bits; if (vbo >= i_size) { err = -EINVAL; goto out; } err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, &node); if (err) goto out; err = ntfs_read_hdr(sbi, ni, &node->index->ihdr, vbo + sbi->record_size, pos, name, ctx); if (err) goto out; bit += 1; } out: __putname(name); put_indx_node(node); if (err == 1) { /* 'ctx' is full. */ err = 0; } else if (err == -ENOENT) { err = 0; ctx->pos = pos; } else if (err < 0) { if (err == -EINVAL) _ntfs_bad_inode(dir); ctx->pos = eod; } return err; } static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, size_t *files) { int err = 0; struct ntfs_inode *ni = ntfs_i(dir); struct NTFS_DE *e = NULL; struct INDEX_ROOT *root; struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; size_t drs = 0, fles = 0, bit = 0; struct indx_node *node = NULL; size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits; if (is_empty) *is_empty = true; root = indx_get_root(&ni->dir, ni, NULL, NULL); if (!root) return -EINVAL; hdr = &root->ihdr; for (;;) { end = le32_to_cpu(hdr->used); off = le32_to_cpu(hdr->de_off); for (; off + sizeof(struct NTFS_DE) <= end; off += e_size) { e = Add2Ptr(hdr, off); e_size = le16_to_cpu(e->size); if (e_size < sizeof(struct NTFS_DE) || off + e_size > end) { /* Looks like corruption. */ break; } if (de_is_last(e)) break; fname = de_get_fname(e); if (!fname) continue; if (fname->type == FILE_NAME_DOS) continue; if (is_empty) { *is_empty = false; if (!dirs && !files) goto out; } if (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) drs += 1; else fles += 1; } if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); if (err) goto out; if (bit == MINUS_ONE_T) goto out; if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, &node); if (err) goto out; hdr = &node->index->ihdr; bit += 1; } out: put_indx_node(node); if (dirs) *dirs = drs; if (files) *files = fles; return err; } bool dir_is_empty(struct inode *dir) { bool is_empty = false; ntfs_dir_count(dir, &is_empty, NULL, NULL); return is_empty; } // clang-format off const struct file_operations ntfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = ntfs_readdir, .fsync = generic_file_fsync, .open = ntfs_file_open, .unlocked_ioctl = ntfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ntfs_compat_ioctl, #endif }; #if IS_ENABLED(CONFIG_NTFS_FS) const struct file_operations ntfs_legacy_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = ntfs_readdir, .open = ntfs_file_open, }; #endif // clang-format on |
| 105 2953 1 1 30 46 29 1 1 17 96 6 7 63 20 9 52 22 6 1 91 4 65 1 57 3 18 60 12 454 409 32 26 54 13 1 1 2 1 6 1 1 11 6 1 1 1 1 3421 1 1 1 10 2 1 92 1 2 9 58 16 53 53 1 6 75 8 79 2 2 2579 450 3438 335 525 2902 3386 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ static int vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static int ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { CLASS(fd, src_file)(srcfd); loff_t cloned; int ret; if (fd_empty(src_file)) return -EBADF; cloned = vfs_clone_file_range(fd_file(src_file), off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; return ret; } static int ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); return freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); return thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = struct_size(same, info, count); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } static int ioctl_getfsuuid(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; struct fsuuid2 u = { .len = sb->s_uuid_len, }; if (!sb->s_uuid_len) return -ENOTTY; memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; if (!strlen(sb->s_sysfs_name)) return -ENOTTY; struct fs_sysfs_path u = {}; u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. * * The LSM mailing list should also be notified of any command additions or * changes, as specific LSMs may be affected. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode) || IS_ANON_FILE(inode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); case FS_IOC_GETFSUUID: return ioctl_getfsuuid(filp, argp); case FS_IOC_GETFSSYSFSPATH: return ioctl_get_fs_sysfs_path(filp, argp); default: if (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd, f)(fd); int error; if (fd_empty(f)) return -EBADF; error = security_file_ioctl(fd_file(f), cmd, arg); if (error) return error; error = do_vfs_ioctl(fd_file(f), fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(fd_file(f), cmd, arg); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * @file: The file to operate on. * @cmd: The ioctl command number. * @arg: The argument to the ioctl. * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { CLASS(fd, f)(fd); int error; if (fd_empty(f)) return -EBADF; error = security_file_ioctl_compat(fd_file(f), cmd, arg); if (error) return error; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(fd_file(f), arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(fd_file(f), 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(fd_file(f), FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(fd_file(f), fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (fd_file(f)->f_op->compat_ioctl) error = fd_file(f)->f_op->compat_ioctl(fd_file(f), cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } return error; } #endif |
| 23 16 23 33 | 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 | /* * linux/fs/nls/nls_cp855.c * * Charset cp855 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0452, 0x0402, 0x0453, 0x0403, 0x0451, 0x0401, 0x0454, 0x0404, 0x0455, 0x0405, 0x0456, 0x0406, 0x0457, 0x0407, 0x0458, 0x0408, /* 0x90*/ 0x0459, 0x0409, 0x045a, 0x040a, 0x045b, 0x040b, 0x045c, 0x040c, 0x045e, 0x040e, 0x045f, 0x040f, 0x044e, 0x042e, 0x044a, 0x042a, /* 0xa0*/ 0x0430, 0x0410, 0x0431, 0x0411, 0x0446, 0x0426, 0x0434, 0x0414, 0x0435, 0x0415, 0x0444, 0x0424, 0x0433, 0x0413, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x0445, 0x0425, 0x0438, 0x0418, 0x2563, 0x2551, 0x2557, 0x255d, 0x0439, 0x0419, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x043a, 0x041a, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4, /* 0xd0*/ 0x043b, 0x041b, 0x043c, 0x041c, 0x043d, 0x041d, 0x043e, 0x041e, 0x043f, 0x2518, 0x250c, 0x2588, 0x2584, 0x041f, 0x044f, 0x2580, /* 0xe0*/ 0x042f, 0x0440, 0x0420, 0x0441, 0x0421, 0x0442, 0x0422, 0x0443, 0x0423, 0x0436, 0x0416, 0x0432, 0x0412, 0x044c, 0x042c, 0x2116, /* 0xf0*/ 0x00ad, 0x044b, 0x042b, 0x0437, 0x0417, 0x0448, 0x0428, 0x044d, 0x042d, 0x0449, 0x0429, 0x0447, 0x0427, 0x00a7, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x00, 0x00, 0xcf, 0x00, 0x00, 0xfd, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0xae, 0x00, 0xf0, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xaf, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ }; static const unsigned char page04[256] = { 0x00, 0x85, 0x81, 0x83, 0x87, 0x89, 0x8b, 0x8d, /* 0x00-0x07 */ 0x8f, 0x91, 0x93, 0x95, 0x97, 0x00, 0x99, 0x9b, /* 0x08-0x0f */ 0xa1, 0xa3, 0xec, 0xad, 0xa7, 0xa9, 0xea, 0xf4, /* 0x10-0x17 */ 0xb8, 0xbe, 0xc7, 0xd1, 0xd3, 0xd5, 0xd7, 0xdd, /* 0x18-0x1f */ 0xe2, 0xe4, 0xe6, 0xe8, 0xab, 0xb6, 0xa5, 0xfc, /* 0x20-0x27 */ 0xf6, 0xfa, 0x9f, 0xf2, 0xee, 0xf8, 0x9d, 0xe0, /* 0x28-0x2f */ 0xa0, 0xa2, 0xeb, 0xac, 0xa6, 0xa8, 0xe9, 0xf3, /* 0x30-0x37 */ 0xb7, 0xbd, 0xc6, 0xd0, 0xd2, 0xd4, 0xd6, 0xd8, /* 0x38-0x3f */ 0xe1, 0xe3, 0xe5, 0xe7, 0xaa, 0xb5, 0xa4, 0xfb, /* 0x40-0x47 */ 0xf5, 0xf9, 0x9e, 0xf1, 0xed, 0xf7, 0x9c, 0xde, /* 0x48-0x4f */ 0x00, 0x84, 0x80, 0x82, 0x86, 0x88, 0x8a, 0x8c, /* 0x50-0x57 */ 0x8e, 0x90, 0x92, 0x94, 0x96, 0x00, 0x98, 0x9a, /* 0x58-0x5f */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xef, 0x00, /* 0x10-0x17 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0x00, 0x00, 0xc9, 0x00, 0x00, 0xbb, /* 0x50-0x57 */ 0x00, 0x00, 0xc8, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x58-0x5f */ 0xcc, 0x00, 0x00, 0xb9, 0x00, 0x00, 0xcb, 0x00, /* 0x60-0x67 */ 0x00, 0xca, 0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page21, NULL, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x80, 0x82, 0x82, 0x84, 0x84, 0x86, 0x86, /* 0x80-0x87 */ 0x88, 0x88, 0x8a, 0x8a, 0x8c, 0x8c, 0x8e, 0x8e, /* 0x88-0x8f */ 0x90, 0x90, 0x92, 0x92, 0x94, 0x94, 0x96, 0x96, /* 0x90-0x97 */ 0x98, 0x98, 0x9a, 0x9a, 0x9c, 0x9c, 0x9e, 0x9e, /* 0x98-0x9f */ 0xa0, 0xa0, 0xa2, 0xa2, 0xa4, 0xa4, 0xa6, 0xa6, /* 0xa0-0xa7 */ 0xa8, 0xa8, 0xaa, 0xaa, 0xac, 0xac, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb5, 0xb7, /* 0xb0-0xb7 */ 0xb7, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbd, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc6, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd0, 0xd2, 0xd2, 0xd4, 0xd4, 0xd6, 0xd6, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xd8, 0xde, 0xdf, /* 0xd8-0xdf */ 0xde, 0xe1, 0xe1, 0xe3, 0xe3, 0xe5, 0xe5, 0xe7, /* 0xe0-0xe7 */ 0xe7, 0xe9, 0xe9, 0xeb, 0xeb, 0xed, 0xed, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf1, 0xf3, 0xf3, 0xf5, 0xf5, 0xf7, /* 0xf0-0xf7 */ 0xf7, 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x81, 0x81, 0x83, 0x83, 0x85, 0x85, 0x87, 0x87, /* 0x80-0x87 */ 0x89, 0x89, 0x8b, 0x8b, 0x8d, 0x8d, 0x8f, 0x8f, /* 0x88-0x8f */ 0x91, 0x91, 0x93, 0x93, 0x95, 0x95, 0x97, 0x97, /* 0x90-0x97 */ 0x99, 0x99, 0x9b, 0x9b, 0x9d, 0x9d, 0x9f, 0x9f, /* 0x98-0x9f */ 0xa1, 0xa1, 0xa3, 0xa3, 0xa5, 0xa5, 0xa7, 0xa7, /* 0xa0-0xa7 */ 0xa9, 0xa9, 0xab, 0xab, 0xad, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb6, 0xb6, 0xb8, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbe, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc7, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd1, 0xd1, 0xd3, 0xd3, 0xd5, 0xd5, 0xd7, 0xd7, /* 0xd0-0xd7 */ 0xdd, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xe0, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe2, 0xe2, 0xe4, 0xe4, 0xe6, 0xe6, 0xe8, /* 0xe0-0xe7 */ 0xe8, 0xea, 0xea, 0xec, 0xec, 0xee, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6, 0xf8, /* 0xf0-0xf7 */ 0xf8, 0xfa, 0xfa, 0xfc, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp855", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp855(void) { return register_nls(&table); } static void __exit exit_nls_cp855(void) { unregister_nls(&table); } module_init(init_nls_cp855) module_exit(exit_nls_cp855) MODULE_DESCRIPTION("NLS Codepage 855 (Cyrillic)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 9 9 9 9 9 9 9 9 9 9 9 18 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 | #include <linux/atomic.h> #include <linux/export.h> #include <linux/generic-radix-tree.h> #include <linux/gfp.h> #include <linux/kmemleak.h> /* * Returns pointer to the specified byte @offset within @radix, or NULL if not * allocated */ void *__genradix_ptr(struct __genradix *radix, size_t offset) { return __genradix_ptr_inlined(radix, offset); } EXPORT_SYMBOL(__genradix_ptr); /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: */ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, struct genradix_node **preallocated, gfp_t gfp_mask) { struct genradix_root *v = READ_ONCE(radix->root); struct genradix_node *n, *new_node = NULL; unsigned level; if (preallocated) swap(new_node, *preallocated); /* Increase tree depth if necessary: */ while (1) { struct genradix_root *r = v, *new_root; n = genradix_root_to_node(r); level = genradix_root_to_depth(r); if (n && ilog2(offset) < genradix_depth_shift(level)) break; if (!new_node) { new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } new_node->children[0] = n; new_root = ((struct genradix_root *) ((unsigned long) new_node | (n ? level + 1 : 0))); if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) { v = new_root; new_node = NULL; } else { new_node->children[0] = NULL; } } while (level--) { struct genradix_node **p = &n->children[offset >> genradix_depth_shift(level)]; offset &= genradix_depth_size(level) - 1; n = READ_ONCE(*p); if (!n) { if (!new_node) { new_node = genradix_alloc_node(gfp_mask); if (!new_node) return NULL; } if (!(n = cmpxchg_release(p, NULL, new_node))) swap(n, new_node); } } if (new_node) genradix_free_node(new_node); return &n->data[offset]; } EXPORT_SYMBOL(__genradix_ptr_alloc); void *__genradix_iter_peek(struct genradix_iter *iter, struct __genradix *radix, size_t objs_per_page) { struct genradix_root *r; struct genradix_node *n; unsigned level, i; if (iter->offset == SIZE_MAX) return NULL; restart: r = READ_ONCE(radix->root); if (!r) return NULL; n = genradix_root_to_node(r); level = genradix_root_to_depth(r); if (ilog2(iter->offset) >= genradix_depth_shift(level)) return NULL; while (level) { level--; i = (iter->offset >> genradix_depth_shift(level)) & (GENRADIX_ARY - 1); while (!n->children[i]) { size_t objs_per_ptr = genradix_depth_size(level); if (iter->offset + objs_per_ptr < iter->offset) { iter->offset = SIZE_MAX; iter->pos = SIZE_MAX; return NULL; } i++; iter->offset = round_down(iter->offset + objs_per_ptr, objs_per_ptr); iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page; if (i == GENRADIX_ARY) goto restart; } n = n->children[i]; } return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)]; } EXPORT_SYMBOL(__genradix_iter_peek); void *__genradix_iter_peek_prev(struct genradix_iter *iter, struct __genradix *radix, size_t objs_per_page, size_t obj_size_plus_page_remainder) { struct genradix_root *r; struct genradix_node *n; unsigned level, i; if (iter->offset == SIZE_MAX) return NULL; restart: r = READ_ONCE(radix->root); if (!r) return NULL; n = genradix_root_to_node(r); level = genradix_root_to_depth(r); if (ilog2(iter->offset) >= genradix_depth_shift(level)) { iter->offset = genradix_depth_size(level); iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page; iter->offset -= obj_size_plus_page_remainder; iter->pos--; } while (level) { level--; i = (iter->offset >> genradix_depth_shift(level)) & (GENRADIX_ARY - 1); while (!n->children[i]) { size_t objs_per_ptr = genradix_depth_size(level); iter->offset = round_down(iter->offset, objs_per_ptr); iter->pos = (iter->offset >> GENRADIX_NODE_SHIFT) * objs_per_page; if (!iter->offset) return NULL; iter->offset -= obj_size_plus_page_remainder; iter->pos--; if (!i) goto restart; --i; } n = n->children[i]; } return &n->data[iter->offset & (GENRADIX_NODE_SIZE - 1)]; } EXPORT_SYMBOL(__genradix_iter_peek_prev); static void genradix_free_recurse(struct genradix_node *n, unsigned level) { if (level) { unsigned i; for (i = 0; i < GENRADIX_ARY; i++) if (n->children[i]) genradix_free_recurse(n->children[i], level - 1); } genradix_free_node(n); } int __genradix_prealloc(struct __genradix *radix, size_t size, gfp_t gfp_mask) { size_t offset; for (offset = 0; offset < size; offset += GENRADIX_NODE_SIZE) if (!__genradix_ptr_alloc(radix, offset, NULL, gfp_mask)) return -ENOMEM; return 0; } EXPORT_SYMBOL(__genradix_prealloc); void __genradix_free(struct __genradix *radix) { struct genradix_root *r = xchg(&radix->root, NULL); genradix_free_recurse(genradix_root_to_node(r), genradix_root_to_depth(r)); } EXPORT_SYMBOL(__genradix_free); |
| 5 78 247 567 151 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2007 Oracle. All rights reserved. */ #ifndef BTRFS_CTREE_H #define BTRFS_CTREE_H #include <linux/cleanup.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/mutex.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/atomic.h> #include <linux/xarray.h> #include <linux/refcount.h> #include <uapi/linux/btrfs_tree.h> #include "locking.h" #include "fs.h" #include "accessors.h" #include "extent-io-tree.h" struct extent_buffer; struct btrfs_block_rsv; struct btrfs_trans_handle; struct btrfs_block_group; /* Read ahead values for struct btrfs_path.reada */ enum { READA_NONE, READA_BACK, READA_FORWARD, /* * Similar to READA_FORWARD but unlike it: * * 1) It will trigger readahead even for leaves that are not close to * each other on disk; * 2) It also triggers readahead for nodes; * 3) During a search, even when a node or leaf is already in memory, it * will still trigger readahead for other nodes and leaves that follow * it. * * This is meant to be used only when we know we are iterating over the * entire tree or a very large part of it. */ READA_FORWARD_ALWAYS, }; /* * btrfs_paths remember the path taken from the root down to the leaf. * level 0 is always the leaf, and nodes[1...BTRFS_MAX_LEVEL] will point * to any other levels that are present. * * The slots array records the index of the item or block pointer * used while walking the tree. */ struct btrfs_path { struct extent_buffer *nodes[BTRFS_MAX_LEVEL]; int slots[BTRFS_MAX_LEVEL]; /* if there is real range locking, this locks field will change */ u8 locks[BTRFS_MAX_LEVEL]; u8 reada; u8 lowest_level; /* * set by btrfs_split_item, tells search_slot to keep all locks * and to force calls to keep space in the nodes */ unsigned int search_for_split:1; /* Keep some upper locks as we walk down. */ unsigned int keep_locks:1; unsigned int skip_locking:1; unsigned int search_commit_root:1; unsigned int need_commit_sem:1; unsigned int skip_release_on_error:1; /* * Indicate that new item (btrfs_search_slot) is extending already * existing item and ins_len contains only the data size and not item * header (ie. sizeof(struct btrfs_item) is not included). */ unsigned int search_for_extension:1; /* Stop search if any locks need to be taken (for read) */ unsigned int nowait:1; }; #define BTRFS_PATH_AUTO_FREE(path_name) \ struct btrfs_path *path_name __free(btrfs_free_path) = NULL /* * The state of btrfs root */ enum { /* * btrfs_record_root_in_trans is a multi-step process, and it can race * with the balancing code. But the race is very small, and only the * first time the root is added to each transaction. So IN_TRANS_SETUP * is used to tell us when more checks are required */ BTRFS_ROOT_IN_TRANS_SETUP, /* * Set if tree blocks of this root can be shared by other roots. * Only subvolume trees and their reloc trees have this bit set. * Conflicts with TRACK_DIRTY bit. * * This affects two things: * * - How balance works * For shareable roots, we need to use reloc tree and do path * replacement for balance, and need various pre/post hooks for * snapshot creation to handle them. * * While for non-shareable trees, we just simply do a tree search * with COW. * * - How dirty roots are tracked * For shareable roots, btrfs_record_root_in_trans() is needed to * track them, while non-subvolume roots have TRACK_DIRTY bit, they * don't need to set this manually. */ BTRFS_ROOT_SHAREABLE, BTRFS_ROOT_TRACK_DIRTY, BTRFS_ROOT_IN_RADIX, BTRFS_ROOT_ORPHAN_ITEM_INSERTED, BTRFS_ROOT_DEFRAG_RUNNING, BTRFS_ROOT_FORCE_COW, BTRFS_ROOT_MULTI_LOG_TASKS, BTRFS_ROOT_DIRTY, BTRFS_ROOT_DELETING, /* * Reloc tree is orphan, only kept here for qgroup delayed subtree scan * * Set for the subvolume tree owning the reloc tree. */ BTRFS_ROOT_DEAD_RELOC_TREE, /* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE, /* The root has a log tree. Used for subvolume roots and the tree root. */ BTRFS_ROOT_HAS_LOG_TREE, /* Qgroup flushing is in progress */ BTRFS_ROOT_QGROUP_FLUSHING, /* We started the orphan cleanup for this root. */ BTRFS_ROOT_ORPHAN_CLEANUP, /* This root has a drop operation that was started previously. */ BTRFS_ROOT_UNFINISHED_DROP, /* This reloc root needs to have its buffers lockdep class reset. */ BTRFS_ROOT_RESET_LOCKDEP_CLASS, }; /* * Record swapped tree blocks of a subvolume tree for delayed subtree trace * code. For detail check comment in fs/btrfs/qgroup.c. */ struct btrfs_qgroup_swapped_blocks { spinlock_t lock; /* RM_EMPTY_ROOT() of above blocks[] */ bool swapped; struct rb_root blocks[BTRFS_MAX_LEVEL]; }; /* * in ram representation of the tree. extent_root is used for all allocations * and for the extent tree extent_root root. */ struct btrfs_root { struct rb_node rb_node; struct extent_buffer *node; struct extent_buffer *commit_root; struct btrfs_root *log_root; struct btrfs_root *reloc_root; unsigned long state; struct btrfs_root_item root_item; struct btrfs_key root_key; struct btrfs_fs_info *fs_info; struct extent_io_tree dirty_log_pages; struct mutex objectid_mutex; spinlock_t accounting_lock; struct btrfs_block_rsv *block_rsv; struct mutex log_mutex; wait_queue_head_t log_writer_wait; wait_queue_head_t log_commit_wait[2]; struct list_head log_ctxs[2]; /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_writers; atomic_t log_commit[2]; /* Used only for log trees of subvolumes, not for the log root tree */ atomic_t log_batch; /* * Protected by the 'log_mutex' lock but can be read without holding * that lock to avoid unnecessary lock contention, in which case it * should be read using btrfs_get_root_log_transid() except if it's a * log tree in which case it can be directly accessed. Updates to this * field should always use btrfs_set_root_log_transid(), except for log * trees where the field can be updated directly. */ int log_transid; /* No matter the commit succeeds or not*/ int log_transid_committed; /* * Just be updated when the commit succeeds. Use * btrfs_get_root_last_log_commit() and btrfs_set_root_last_log_commit() * to access this field. */ int last_log_commit; pid_t log_start_pid; u64 last_trans; u64 free_objectid; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; /* The dirty list is only used by non-shareable roots */ struct list_head dirty_list; struct list_head root_list; /* Xarray that keeps track of in-memory inodes. */ struct xarray inodes; /* Xarray that keeps track of delayed nodes of every inode. */ struct xarray delayed_nodes; /* * right now this just gets used so that a root has its own devid * for stat. It may be used for more later */ dev_t anon_dev; spinlock_t root_item_lock; refcount_t refs; struct mutex delalloc_mutex; spinlock_t delalloc_lock; /* * all of the inodes that have delalloc bytes. It is possible for * this list to be empty even when there is still dirty data=ordered * extents waiting to finish IO. */ struct list_head delalloc_inodes; struct list_head delalloc_root; u64 nr_delalloc_inodes; struct mutex ordered_extent_mutex; /* * this is used by the balancing code to wait for all the pending * ordered extents */ spinlock_t ordered_extent_lock; /* * all of the data=ordered extents pending writeback * these can span multiple transactions and basically include * every dirty data page that isn't from nodatacow */ struct list_head ordered_extents; struct list_head ordered_root; u64 nr_ordered_extents; /* * Not empty if this subvolume root has gone through tree block swap * (relocation) * * Will be used by reloc_control::dirty_subvol_roots. */ struct list_head reloc_dirty_list; /* * Number of currently running SEND ioctls to prevent * manipulation with the read-only status via SUBVOL_SETFLAGS */ int send_in_progress; /* * Number of currently running deduplication operations that have a * destination inode belonging to this root. Protected by the lock * root_item_lock. */ int dedupe_in_progress; /* For exclusion of snapshot creation and nocow writes */ struct btrfs_drew_lock snapshot_lock; atomic_t snapshot_force_cow; /* For qgroup metadata reserved space */ spinlock_t qgroup_meta_rsv_lock; u64 qgroup_meta_rsv_pertrans; u64 qgroup_meta_rsv_prealloc; wait_queue_head_t qgroup_flush_wait; /* Number of active swapfiles */ atomic_t nr_swapfiles; /* Record pairs of swapped blocks for qgroup */ struct btrfs_qgroup_swapped_blocks swapped_blocks; /* Used only by log trees, when logging csum items */ struct extent_io_tree log_csum_range; /* Used in simple quotas, track root during relocation. */ u64 relocation_src_root; #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS u64 alloc_bytenr; #endif #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif }; static inline bool btrfs_root_readonly(const struct btrfs_root *root) { /* Byte-swap the constant at compile time, root_item::flags is LE */ return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0; } static inline bool btrfs_root_dead(const struct btrfs_root *root) { /* Byte-swap the constant at compile time, root_item::flags is LE */ return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0; } static inline u64 btrfs_root_id(const struct btrfs_root *root) { return root->root_key.objectid; } static inline int btrfs_get_root_log_transid(const struct btrfs_root *root) { return READ_ONCE(root->log_transid); } static inline void btrfs_set_root_log_transid(struct btrfs_root *root, int log_transid) { WRITE_ONCE(root->log_transid, log_transid); } static inline int btrfs_get_root_last_log_commit(const struct btrfs_root *root) { return READ_ONCE(root->last_log_commit); } static inline void btrfs_set_root_last_log_commit(struct btrfs_root *root, int commit_id) { WRITE_ONCE(root->last_log_commit, commit_id); } static inline u64 btrfs_get_root_last_trans(const struct btrfs_root *root) { return READ_ONCE(root->last_trans); } static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transid) { WRITE_ONCE(root->last_trans, transid); } /* * Return the generation this root started with. * * Every normal root that is created with root->root_key.offset set to it's * originating generation. If it is a snapshot it is the generation when the * snapshot was created. * * However for TREE_RELOC roots root_key.offset is the objectid of the owning * tree root. Thankfully we copy the root item of the owning tree root, which * has it's last_snapshot set to what we would have root_key.offset set to, so * return that if this is a TREE_RELOC root. */ static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) { if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) return btrfs_root_last_snapshot(&root->root_item); return root->root_key.offset; } /* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ struct btrfs_replace_extent_info { u64 disk_offset; u64 disk_len; u64 data_offset; u64 data_len; u64 file_offset; /* Pointer to a file extent item of type regular or prealloc. */ char *extent_buf; /* * Set to true when attempting to replace a file range with a new extent * described by this structure, set to false when attempting to clone an * existing extent into a file range. */ bool is_new_extent; /* Indicate if we should update the inode's mtime and ctime. */ bool update_times; /* Meaningful only if is_new_extent is true. */ int qgroup_reserved; /* * Meaningful only if is_new_extent is true. * Used to track how many extent items we have already inserted in a * subvolume tree that refer to the extent described by this structure, * so that we know when to create a new delayed ref or update an existing * one. */ int insertions; }; /* Arguments for btrfs_drop_extents() */ struct btrfs_drop_extents_args { /* Input parameters */ /* * If NULL, btrfs_drop_extents() will allocate and free its own path. * If 'replace_extent' is true, this must not be NULL. Also the path * is always released except if 'replace_extent' is true and * btrfs_drop_extents() sets 'extent_inserted' to true, in which case * the path is kept locked. */ struct btrfs_path *path; /* Start offset of the range to drop extents from */ u64 start; /* End (exclusive, last byte + 1) of the range to drop extents from */ u64 end; /* If true drop all the extent maps in the range */ bool drop_cache; /* * If true it means we want to insert a new extent after dropping all * the extents in the range. If this is true, the 'extent_item_size' * parameter must be set as well and the 'extent_inserted' field will * be set to true by btrfs_drop_extents() if it could insert the new * extent. * Note: when this is set to true the path must not be NULL. */ bool replace_extent; /* * Used if 'replace_extent' is true. Size of the file extent item to * insert after dropping all existing extents in the range */ u32 extent_item_size; /* Output parameters */ /* * Set to the minimum between the input parameter 'end' and the end * (exclusive, last byte + 1) of the last dropped extent. This is always * set even if btrfs_drop_extents() returns an error. */ u64 drop_end; /* * The number of allocated bytes found in the range. This can be smaller * than the range's length when there are holes in the range. */ u64 bytes_found; /* * Only set if 'replace_extent' is true. Set to true if we were able * to insert a replacement extent after dropping all extents in the * range, otherwise set to false by btrfs_drop_extents(). * Also, if btrfs_drop_extents() has set this to true it means it * returned with the path locked, otherwise if it has set this to * false it has returned with the path released. */ bool extent_inserted; }; struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; /* Task that allocated this structure. */ struct task_struct *owner_task; }; static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) { return info->nodesize - sizeof(struct btrfs_header); } static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info) { return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item); } static inline u32 BTRFS_NODEPTRS_PER_BLOCK(const struct btrfs_fs_info *info) { return BTRFS_LEAF_DATA_SIZE(info) / sizeof(struct btrfs_key_ptr); } static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) { return BTRFS_MAX_ITEM_SIZE(info) - sizeof(struct btrfs_dir_item); } int __init btrfs_ctree_init(void); void __cold btrfs_ctree_exit(void); int btrfs_bin_search(const struct extent_buffer *eb, int first_slot, const struct btrfs_key *key, int *slot); int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2); #ifdef __LITTLE_ENDIAN /* * Compare two keys, on little-endian the disk order is same as CPU order and * we can avoid the conversion. */ static inline int btrfs_comp_keys(const struct btrfs_disk_key *disk_key, const struct btrfs_key *k2) { const struct btrfs_key *k1 = (const struct btrfs_key *)disk_key; return btrfs_comp_cpu_keys(k1, k2); } #else /* Compare two keys in a memcmp fashion. */ static inline int btrfs_comp_keys(const struct btrfs_disk_key *disk, const struct btrfs_key *k2) { struct btrfs_key k1; btrfs_disk_key_to_cpu(&k1, disk); return btrfs_comp_cpu_keys(&k1, k2); } #endif int btrfs_previous_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid, int type); int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid); void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, const struct btrfs_path *path, const struct btrfs_key *new_key); struct extent_buffer *btrfs_root_node(struct btrfs_root *root); int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *key, int lowest_level, u64 min_trans); int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key, struct btrfs_path *path, u64 min_trans); struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent, int slot); int btrfs_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, enum btrfs_lock_nesting nest); int btrfs_force_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *parent, int parent_slot, struct extent_buffer **cow_ret, u64 search_start, u64 empty_size, enum btrfs_lock_nesting nest); int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid); bool btrfs_block_can_be_shared(const struct btrfs_trans_handle *trans, const struct btrfs_root *root, const struct extent_buffer *buf); int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); void btrfs_extend_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 data_size); void btrfs_truncate_item(struct btrfs_trans_handle *trans, const struct btrfs_path *path, u32 new_size, int from_end); int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset); int btrfs_duplicate_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *new_key); int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path, u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key); int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow); int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, u64 time_seq); int btrfs_search_slot_for_read(struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_path *p, int find_higher, int return_any); void btrfs_release_path(struct btrfs_path *p); struct btrfs_path *btrfs_alloc_path(void); void btrfs_free_path(struct btrfs_path *p); DEFINE_FREE(btrfs_free_path, struct btrfs_path *, btrfs_free_path(_T)) int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int slot, int nr); static inline int btrfs_del_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path) { return btrfs_del_items(trans, root, path, path->slots[0], 1); } /* * Describes a batch of items to insert in a btree. This is used by * btrfs_insert_empty_items(). */ struct btrfs_item_batch { /* * Pointer to an array containing the keys of the items to insert (in * sorted order). */ const struct btrfs_key *keys; /* Pointer to an array containing the data size for each item to insert. */ const u32 *data_sizes; /* * The sum of data sizes for all items. The caller can compute this while * setting up the data_sizes array, so it ends up being more efficient * than having btrfs_insert_empty_items() or setup_item_for_insert() * doing it, as it would avoid an extra loop over a potentially large * array, and in the case of setup_item_for_insert(), we would be doing * it while holding a write lock on a leaf and often on upper level nodes * too, unnecessarily increasing the size of a critical section. */ u32 total_data_size; /* Size of the keys and data_sizes arrays (number of items in the batch). */ int nr; }; void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size); int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, void *data, u32 data_size); int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch); static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size) { struct btrfs_item_batch batch; batch.keys = key; batch.data_sizes = &data_size; batch.total_data_size = data_size; batch.nr = 1; return btrfs_insert_empty_items(trans, root, path, &batch); } int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq); int btrfs_search_backwards(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path); int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *path); /* * Search in @root for a given @key, and store the slot found in @found_key. * * @root: The root node of the tree. * @key: The key we are looking for. * @found_key: Will hold the found item. * @path: Holds the current slot/leaf. * @iter_ret: Contains the value returned from btrfs_search_slot or * btrfs_get_next_valid_item, whichever was executed last. * * The @iter_ret is an output variable that will contain the return value of * btrfs_search_slot, if it encountered an error, or the value returned from * btrfs_get_next_valid_item otherwise. That return value can be 0, if a valid * slot was found, 1 if there were no more leaves, and <0 if there was an error. * * It's recommended to use a separate variable for iter_ret and then use it to * set the function return value so there's no confusion of the 0/1/errno * values stemming from btrfs_search_slot. */ #define btrfs_for_each_slot(root, key, found_key, path, iter_ret) \ for (iter_ret = btrfs_search_slot(NULL, (root), (key), (path), 0, 0); \ (iter_ret) >= 0 && \ (iter_ret = btrfs_get_next_valid_item((root), (found_key), (path))) == 0; \ (path)->slots[0]++ \ ) int btrfs_next_old_item(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq); /* * Search the tree again to find a leaf with greater keys. * * Returns 0 if it found something or 1 if there are no greater leaves. * Returns < 0 on error. */ static inline int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) { return btrfs_next_old_leaf(root, path, 0); } static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) { return btrfs_next_old_item(root, p, 0); } int btrfs_leaf_free_space(const struct extent_buffer *leaf); static inline bool btrfs_is_fstree(u64 rootid) { if (rootid == BTRFS_FS_TREE_OBJECTID) return true; if ((s64)rootid < (s64)BTRFS_FIRST_FREE_OBJECTID) return false; if (btrfs_qgroup_level(rootid) != 0) return false; return true; } static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) { return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID; } #endif |
| 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/fs/befs/endian.h * * Copyright (C) 2001 Will Dyson <will_dyson@pobox.com> * * Partially based on similar funtions in the sysv driver. */ #ifndef LINUX_BEFS_ENDIAN #define LINUX_BEFS_ENDIAN #include <asm/byteorder.h> static inline u64 fs64_to_cpu(const struct super_block *sb, fs64 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return le64_to_cpu((__force __le64)n); else return be64_to_cpu((__force __be64)n); } static inline fs64 cpu_to_fs64(const struct super_block *sb, u64 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return (__force fs64)cpu_to_le64(n); else return (__force fs64)cpu_to_be64(n); } static inline u32 fs32_to_cpu(const struct super_block *sb, fs32 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return le32_to_cpu((__force __le32)n); else return be32_to_cpu((__force __be32)n); } static inline fs32 cpu_to_fs32(const struct super_block *sb, u32 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return (__force fs32)cpu_to_le32(n); else return (__force fs32)cpu_to_be32(n); } static inline u16 fs16_to_cpu(const struct super_block *sb, fs16 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return le16_to_cpu((__force __le16)n); else return be16_to_cpu((__force __be16)n); } static inline fs16 cpu_to_fs16(const struct super_block *sb, u16 n) { if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) return (__force fs16)cpu_to_le16(n); else return (__force fs16)cpu_to_be16(n); } /* Composite types below here */ static inline befs_block_run fsrun_to_cpu(const struct super_block *sb, befs_disk_block_run n) { befs_block_run run; if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) { run.allocation_group = le32_to_cpu((__force __le32)n.allocation_group); run.start = le16_to_cpu((__force __le16)n.start); run.len = le16_to_cpu((__force __le16)n.len); } else { run.allocation_group = be32_to_cpu((__force __be32)n.allocation_group); run.start = be16_to_cpu((__force __be16)n.start); run.len = be16_to_cpu((__force __be16)n.len); } return run; } static inline befs_disk_block_run cpu_to_fsrun(const struct super_block *sb, befs_block_run n) { befs_disk_block_run run; if (BEFS_SB(sb)->byte_order == BEFS_BYTESEX_LE) { run.allocation_group = cpu_to_le32(n.allocation_group); run.start = cpu_to_le16(n.start); run.len = cpu_to_le16(n.len); } else { run.allocation_group = cpu_to_be32(n.allocation_group); run.start = cpu_to_be16(n.start); run.len = cpu_to_be16(n.len); } return run; } static inline befs_data_stream fsds_to_cpu(const struct super_block *sb, const befs_disk_data_stream *n) { befs_data_stream data; int i; for (i = 0; i < BEFS_NUM_DIRECT_BLOCKS; ++i) data.direct[i] = fsrun_to_cpu(sb, n->direct[i]); data.max_direct_range = fs64_to_cpu(sb, n->max_direct_range); data.indirect = fsrun_to_cpu(sb, n->indirect); data.max_indirect_range = fs64_to_cpu(sb, n->max_indirect_range); data.double_indirect = fsrun_to_cpu(sb, n->double_indirect); data.max_double_indirect_range = fs64_to_cpu(sb, n-> max_double_indirect_range); data.size = fs64_to_cpu(sb, n->size); return data; } #endif //LINUX_BEFS_ENDIAN |
| 530 533 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage high resolution tick * related events. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include "tick-internal.h" /** * tick_program_event - program the CPU local timer device for the next event */ int tick_program_event(ktime_t expires, int force) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); if (unlikely(expires == KTIME_MAX)) { /* * We don't need the clock event device any more, stop it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); dev->next_event = KTIME_MAX; return 0; } if (unlikely(clockevent_state_oneshot_stopped(dev))) { /* * We need the clock event again, configure it in ONESHOT mode * before using it. */ clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); } return clockevents_program_event(dev, expires, force); } /** * tick_resume_oneshot - resume oneshot mode */ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } /** * tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz) */ void tick_setup_oneshot(struct clock_event_device *newdev, void (*handler)(struct clock_event_device *), ktime_t next_event) { newdev->event_handler = handler; clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } /** * tick_switch_to_oneshot - switch to oneshot mode */ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *dev = td->evtdev; if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || !tick_device_is_functional(dev)) { pr_info("Clockevents: could not switch to one-shot mode:"); if (!dev) { pr_cont(" no tick device\n"); } else { if (!tick_device_is_functional(dev)) pr_cont(" %s is not functional.\n", dev->name); else pr_cont(" %s does not support one-shot mode.\n", dev->name); } return -EINVAL; } td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } /** * tick_oneshot_mode_active - check whether the system is in oneshot mode * * returns 1 when either nohz or highres are enabled. otherwise 0. */ int tick_oneshot_mode_active(void) { unsigned long flags; int ret; local_irq_save(flags); ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT; local_irq_restore(flags); return ret; } #ifdef CONFIG_HIGH_RES_TIMERS /** * tick_init_highres - switch to high resolution mode * * Called with interrupts disabled. */ int tick_init_highres(void) { return tick_switch_to_oneshot(hrtimer_interrupt); } #endif |
| 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UDF_SB_H #define __LINUX_UDF_SB_H #include <linux/mutex.h> #include <linux/bitops.h> #include <linux/magic.h> /* * Even UDF 2.6 media should have version <= 0x250 but apparently there are * some broken filesystems with version set to 0x260. Accommodate those. */ #define UDF_MAX_READ_VERSION 0x0260 #define UDF_MAX_WRITE_VERSION 0x0201 #define UDF_FLAG_USE_EXTENDED_FE 0 #define UDF_VERS_USE_EXTENDED_FE 0x0200 #define UDF_FLAG_USE_STREAMS 1 #define UDF_VERS_USE_STREAMS 0x0200 #define UDF_FLAG_USE_SHORT_AD 2 #define UDF_FLAG_USE_AD_IN_ICB 3 #define UDF_FLAG_USE_FILE_CTIME_EA 4 #define UDF_FLAG_STRICT 5 #define UDF_FLAG_UNDELETE 6 #define UDF_FLAG_UNHIDE 7 #define UDF_FLAG_NOVRS 8 #define UDF_FLAG_UID_FORGET 11 /* save -1 for uid to disk */ #define UDF_FLAG_GID_FORGET 12 #define UDF_FLAG_UID_SET 13 #define UDF_FLAG_GID_SET 14 #define UDF_FLAG_SESSION_SET 15 #define UDF_FLAG_LASTBLOCK_SET 16 #define UDF_FLAG_BLOCKSIZE_SET 17 #define UDF_FLAG_INCONSISTENT 18 #define UDF_FLAG_RW_INCOMPAT 19 /* Set when we find RW incompatible * feature */ #define UDF_PART_FLAG_UNALLOC_BITMAP 0x0001 #define UDF_PART_FLAG_UNALLOC_TABLE 0x0002 #define UDF_PART_FLAG_READ_ONLY 0x0010 #define UDF_PART_FLAG_WRITE_ONCE 0x0020 #define UDF_PART_FLAG_REWRITABLE 0x0040 #define UDF_PART_FLAG_OVERWRITABLE 0x0080 #define UDF_MAX_BLOCK_LOADED 8 #define UDF_TYPE1_MAP15 0x1511U #define UDF_VIRTUAL_MAP15 0x1512U #define UDF_VIRTUAL_MAP20 0x2012U #define UDF_SPARABLE_MAP15 0x1522U #define UDF_METADATA_MAP25 0x2511U #define UDF_INVALID_MODE ((umode_t)-1) #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 #define EFSCORRUPTED EUCLEAN struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; __u32 s_bitmap_file_loc; __u32 s_alloc_unit_size; __u16 s_align_unit_size; /* * Partition Reference Number of the associated physical / sparable * partition */ __u16 s_phys_partition_ref; int s_flags; struct inode *s_metadata_fe; struct inode *s_mirror_fe; struct inode *s_bitmap_fe; }; struct udf_sparing_data { __u16 s_packet_len; struct buffer_head *s_spar_map[4]; }; struct udf_virtual_data { __u32 s_num_entries; __u16 s_start_offset; }; struct udf_bitmap { __u32 s_extPosition; int s_nr_groups; struct buffer_head *s_block_bitmap[] __counted_by(s_nr_groups); }; struct udf_part_map { union { struct udf_bitmap *s_bitmap; struct inode *s_table; } s_uspace; __u32 s_partition_root; __u32 s_partition_len; __u16 s_partition_type; __u16 s_partition_num; union { struct udf_sparing_data s_sparing; struct udf_virtual_data s_virtual; struct udf_meta_data s_metadata; } s_type_specific; __u32 (*s_partition_func)(struct super_block *, __u32, __u16, __u32); __u16 s_volumeseqnum; __u16 s_partition_flags; }; #pragma pack() struct udf_sb_info { struct udf_part_map *s_partmaps; __u8 s_volume_ident[32]; /* Overall info */ __u16 s_partitions; __u16 s_partition; /* Sector headers */ __s32 s_session; __u32 s_anchor; __u32 s_last_block; struct buffer_head *s_lvid_bh; /* Default permissions */ umode_t s_umask; kgid_t s_gid; kuid_t s_uid; umode_t s_fmode; umode_t s_dmode; /* Lock protecting consistency of above permission settings */ rwlock_t s_cred_lock; /* Root Info */ struct timespec64 s_record_time; /* Fileset Info */ __u16 s_serial_number; /* highest UDF revision we have recorded to this media */ __u16 s_udfrev; /* Miscellaneous flags */ unsigned long s_flags; /* Encoding info */ struct nls_table *s_nls_map; /* VAT inode */ struct inode *s_vat_inode; struct mutex s_alloc_mutex; /* Protected by s_alloc_mutex */ unsigned int s_lvid_dirty; }; static inline struct udf_sb_info *UDF_SB(struct super_block *sb) { return sb->s_fs_info; } struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb); int udf_compute_nr_groups(struct super_block *sb, u32 partition); static inline int UDF_QUERY_FLAG(struct super_block *sb, int flag) { return test_bit(flag, &UDF_SB(sb)->s_flags); } static inline void UDF_SET_FLAG(struct super_block *sb, int flag) { set_bit(flag, &UDF_SB(sb)->s_flags); } static inline void UDF_CLEAR_FLAG(struct super_block *sb, int flag) { clear_bit(flag, &UDF_SB(sb)->s_flags); } #endif /* __LINUX_UDF_SB_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | /* * mtdram - a test mtd device * Author: Alexander Larsson <alex@cendio.se> * * Copyright (c) 1999 Alexander Larsson <alex@cendio.se> * Copyright (c) 2005 Joern Engel <joern@wh.fh-wedel.de> * * This code is GPL * */ #include <linux/module.h> #include <linux/slab.h> #include <linux/ioport.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/mtd/mtd.h> #include <linux/mtd/mtdram.h> static unsigned long total_size = CONFIG_MTDRAM_TOTAL_SIZE; static unsigned long erase_size = CONFIG_MTDRAM_ERASE_SIZE; static unsigned long writebuf_size = 64; #define MTDRAM_TOTAL_SIZE (total_size * 1024) #define MTDRAM_ERASE_SIZE (erase_size * 1024) module_param(total_size, ulong, 0); MODULE_PARM_DESC(total_size, "Total device size in KiB"); module_param(erase_size, ulong, 0); MODULE_PARM_DESC(erase_size, "Device erase block size in KiB"); module_param(writebuf_size, ulong, 0); MODULE_PARM_DESC(writebuf_size, "Device write buf size in Bytes (Default: 64)"); // We could store these in the mtd structure, but we only support 1 device.. static struct mtd_info *mtd_info; static int check_offs_len(struct mtd_info *mtd, loff_t ofs, uint64_t len) { int ret = 0; /* Start address must align on block boundary */ if (mtd_mod_by_eb(ofs, mtd)) { pr_debug("%s: unaligned address\n", __func__); ret = -EINVAL; } /* Length must align on block boundary */ if (mtd_mod_by_eb(len, mtd)) { pr_debug("%s: length not block aligned\n", __func__); ret = -EINVAL; } return ret; } static int ram_erase(struct mtd_info *mtd, struct erase_info *instr) { if (check_offs_len(mtd, instr->addr, instr->len)) return -EINVAL; memset((char *)mtd->priv + instr->addr, 0xff, instr->len); return 0; } static int ram_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, void **virt, resource_size_t *phys) { *virt = mtd->priv + from; *retlen = len; if (phys) { /* limit retlen to the number of contiguous physical pages */ unsigned long page_ofs = offset_in_page(*virt); void *addr = *virt - page_ofs; unsigned long pfn1, pfn0 = vmalloc_to_pfn(addr); *phys = __pfn_to_phys(pfn0) + page_ofs; len += page_ofs; while (len > PAGE_SIZE) { len -= PAGE_SIZE; addr += PAGE_SIZE; pfn0++; pfn1 = vmalloc_to_pfn(addr); if (pfn1 != pfn0) { *retlen = addr - *virt; break; } } } return 0; } static int ram_unpoint(struct mtd_info *mtd, loff_t from, size_t len) { return 0; } static int ram_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { memcpy(buf, mtd->priv + from, len); *retlen = len; return 0; } static int ram_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { memcpy((char *)mtd->priv + to, buf, len); *retlen = len; return 0; } static void __exit cleanup_mtdram(void) { if (mtd_info) { mtd_device_unregister(mtd_info); vfree(mtd_info->priv); kfree(mtd_info); } } int mtdram_init_device(struct mtd_info *mtd, void *mapped_address, unsigned long size, const char *name) { memset(mtd, 0, sizeof(*mtd)); /* Setup the MTD structure */ mtd->name = name; mtd->type = MTD_RAM; mtd->flags = MTD_CAP_RAM; mtd->size = size; mtd->writesize = 1; mtd->writebufsize = writebuf_size; mtd->erasesize = MTDRAM_ERASE_SIZE; mtd->priv = mapped_address; mtd->owner = THIS_MODULE; mtd->_erase = ram_erase; mtd->_point = ram_point; mtd->_unpoint = ram_unpoint; mtd->_read = ram_read; mtd->_write = ram_write; if (mtd_device_register(mtd, NULL, 0)) return -EIO; return 0; } static int __init init_mtdram(void) { void *addr; int err; if (!total_size) return -EINVAL; /* Allocate some memory */ mtd_info = kmalloc(sizeof(struct mtd_info), GFP_KERNEL); if (!mtd_info) return -ENOMEM; addr = vmalloc(MTDRAM_TOTAL_SIZE); if (!addr) { kfree(mtd_info); mtd_info = NULL; return -ENOMEM; } err = mtdram_init_device(mtd_info, addr, MTDRAM_TOTAL_SIZE, "mtdram test device"); if (err) { vfree(addr); kfree(mtd_info); mtd_info = NULL; return err; } memset(mtd_info->priv, 0xff, MTDRAM_TOTAL_SIZE); return err; } module_init(init_mtdram); module_exit(cleanup_mtdram); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alexander Larsson <alexl@redhat.com>"); MODULE_DESCRIPTION("Simulated MTD driver for testing"); |
| 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 | // 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 shrinker which evicts clean znodes from the TNC * tree when Linux VM needs more RAM. * * We do not implement any LRU lists to find oldest znodes to free because it * would add additional overhead to the file system fast paths. So the shrinker * just walks the TNC tree when searching for znodes to free. * * If the root of a TNC sub-tree is clean and old enough, then the children are * also clean and old enough. So the shrinker walks the TNC in level order and * dumps entire sub-trees. * * The age of znodes is just the time-stamp when they were last looked at. * The current shrinker first tries to evict old znodes, then young ones. * * Since the shrinker is global, it has to protect against races with FS * un-mounts, which is done by the 'ubifs_infos_lock' and 'c->umount_mutex'. */ #include "ubifs.h" /* List of all UBIFS file-system instances */ LIST_HEAD(ubifs_infos); /* * We number each shrinker run and record the number on the ubifs_info structure * so that we can easily work out which ubifs_info structures have already been * done by the current run. */ static unsigned int shrinker_run_no; /* Protects 'ubifs_infos' list */ DEFINE_SPINLOCK(ubifs_infos_lock); /* Global clean znode counter (for all mounted UBIFS instances) */ atomic_long_t ubifs_clean_zn_cnt; /** * shrink_tnc - shrink TNC tree. * @c: UBIFS file-system description object * @nr: number of znodes to free * @age: the age of znodes to free * @contention: if any contention, this is set to %1 * * This function traverses TNC tree and frees clean znodes. It does not free * clean znodes which younger then @age. Returns number of freed znodes. */ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention) { int total_freed = 0; struct ubifs_znode *znode, *zprev; time64_t time = ktime_get_seconds(); ubifs_assert(c, mutex_is_locked(&c->umount_mutex)); ubifs_assert(c, mutex_is_locked(&c->tnc_mutex)); if (!c->zroot.znode || atomic_long_read(&c->clean_zn_cnt) == 0) return 0; /* * Traverse the TNC tree in levelorder manner, so that it is possible * to destroy large sub-trees. Indeed, if a znode is old, then all its * children are older or of the same age. * * Note, we are holding 'c->tnc_mutex', so we do not have to lock the * 'c->space_lock' when _reading_ 'c->clean_zn_cnt', because it is * changed only when the 'c->tnc_mutex' is held. */ zprev = NULL; znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL); while (znode && total_freed < nr && atomic_long_read(&c->clean_zn_cnt) > 0) { int freed; /* * If the znode is clean, but it is in the 'c->cnext' list, this * means that this znode has just been written to flash as a * part of commit and was marked clean. They will be removed * from the list at end commit. We cannot change the list, * because it is not protected by any mutex (design decision to * make commit really independent and parallel to main I/O). So * we just skip these znodes. * * Note, the 'clean_zn_cnt' counters are not updated until * after the commit, so the UBIFS shrinker does not report * the znodes which are in the 'c->cnext' list as freeable. * * Also note, if the root of a sub-tree is not in 'c->cnext', * then the whole sub-tree is not in 'c->cnext' as well, so it * is safe to dump whole sub-tree. */ if (znode->cnext) { /* * Very soon these znodes will be removed from the list * and become freeable. */ *contention = 1; } else if (!ubifs_zn_dirty(znode) && abs(time - znode->time) >= age) { if (znode->parent) znode->parent->zbranch[znode->iip].znode = NULL; else c->zroot.znode = NULL; freed = ubifs_destroy_tnc_subtree(c, znode); atomic_long_sub(freed, &ubifs_clean_zn_cnt); atomic_long_sub(freed, &c->clean_zn_cnt); total_freed += freed; znode = zprev; } if (unlikely(!c->zroot.znode)) break; zprev = znode; znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode); cond_resched(); } return total_freed; } /** * shrink_tnc_trees - shrink UBIFS TNC trees. * @nr: number of znodes to free * @age: the age of znodes to free * @contention: if any contention, this is set to %1 * * This function walks the list of mounted UBIFS file-systems and frees clean * znodes which are older than @age, until at least @nr znodes are freed. * Returns the number of freed znodes. */ static int shrink_tnc_trees(int nr, int age, int *contention) { struct ubifs_info *c; struct list_head *p; unsigned int run_no; int freed = 0; spin_lock(&ubifs_infos_lock); do { run_no = ++shrinker_run_no; } while (run_no == 0); /* Iterate over all mounted UBIFS file-systems and try to shrink them */ p = ubifs_infos.next; while (p != &ubifs_infos) { c = list_entry(p, struct ubifs_info, infos_list); /* * We move the ones we do to the end of the list, so we stop * when we see one we have already done. */ if (c->shrinker_run_no == run_no) break; if (!mutex_trylock(&c->umount_mutex)) { /* Some un-mount is in progress, try next FS */ *contention = 1; p = p->next; continue; } /* * We're holding 'c->umount_mutex', so the file-system won't go * away. */ if (!mutex_trylock(&c->tnc_mutex)) { mutex_unlock(&c->umount_mutex); *contention = 1; p = p->next; continue; } spin_unlock(&ubifs_infos_lock); /* * OK, now we have TNC locked, the file-system cannot go away - * it is safe to reap the cache. */ c->shrinker_run_no = run_no; freed += shrink_tnc(c, nr, age, contention); mutex_unlock(&c->tnc_mutex); spin_lock(&ubifs_infos_lock); /* Get the next list element before we move this one */ p = p->next; /* * Move this one to the end of the list to provide some * fairness. */ list_move_tail(&c->infos_list, &ubifs_infos); mutex_unlock(&c->umount_mutex); if (freed >= nr) break; } spin_unlock(&ubifs_infos_lock); return freed; } /** * kick_a_thread - kick a background thread to start commit. * * This function kicks a background thread to start background commit. Returns * %-1 if a thread was kicked or there is another reason to assume the memory * will soon be freed or become freeable. If there are no dirty znodes, returns * %0. */ static int kick_a_thread(void) { int i; struct ubifs_info *c; /* * Iterate over all mounted UBIFS file-systems and find out if there is * already an ongoing commit operation there. If no, then iterate for * the second time and initiate background commit. */ spin_lock(&ubifs_infos_lock); for (i = 0; i < 2; i++) { list_for_each_entry(c, &ubifs_infos, infos_list) { long dirty_zn_cnt; if (!mutex_trylock(&c->umount_mutex)) { /* * Some un-mount is in progress, it will * certainly free memory, so just return. */ spin_unlock(&ubifs_infos_lock); return -1; } dirty_zn_cnt = atomic_long_read(&c->dirty_zn_cnt); if (!dirty_zn_cnt || c->cmt_state == COMMIT_BROKEN || c->ro_mount || c->ro_error) { mutex_unlock(&c->umount_mutex); continue; } if (c->cmt_state != COMMIT_RESTING) { spin_unlock(&ubifs_infos_lock); mutex_unlock(&c->umount_mutex); return -1; } if (i == 1) { list_move_tail(&c->infos_list, &ubifs_infos); spin_unlock(&ubifs_infos_lock); ubifs_request_bg_commit(c); mutex_unlock(&c->umount_mutex); return -1; } mutex_unlock(&c->umount_mutex); } } spin_unlock(&ubifs_infos_lock); return 0; } unsigned long ubifs_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); /* * Due to the way UBIFS updates the clean znode counter it may * temporarily be negative. */ return clean_zn_cnt >= 0 ? clean_zn_cnt : 1; } unsigned long ubifs_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr = sc->nr_to_scan; int contention = 0; unsigned long freed; long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt); if (!clean_zn_cnt) { /* * No clean znodes, nothing to reap. All we can do in this case * is to kick background threads to start commit, which will * probably make clean znodes which, in turn, will be freeable. * And we return -1 which means will make VM call us again * later. */ dbg_tnc("no clean znodes, kick a thread"); return kick_a_thread(); } freed = shrink_tnc_trees(nr, OLD_ZNODE_AGE, &contention); if (freed >= nr) goto out; dbg_tnc("not enough old znodes, try to free young ones"); freed += shrink_tnc_trees(nr - freed, YOUNG_ZNODE_AGE, &contention); if (freed >= nr) goto out; dbg_tnc("not enough young znodes, free all"); freed += shrink_tnc_trees(nr - freed, 0, &contention); if (!freed && contention) { dbg_tnc("freed nothing, but contention"); return SHRINK_STOP; } out: dbg_tnc("%lu znodes were freed, requested %lu", freed, nr); return freed; } |
| 10 26 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2016 Oracle. All Rights Reserved. * Author: Darrick J. Wong <darrick.wong@oracle.com> */ #ifndef __XFS_REFCOUNT_H__ #define __XFS_REFCOUNT_H__ struct xfs_trans; struct xfs_mount; struct xfs_perag; struct xfs_btree_cur; struct xfs_bmbt_irec; struct xfs_refcount_irec; struct xfs_rtgroup; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); static inline uint32_t xfs_refcount_encode_startblock( xfs_agblock_t startblock, enum xfs_refc_domain domain) { uint32_t start; /* * low level btree operations need to handle the generic btree range * query functions (which set rc_domain == -1U), so we check that the * domain is /not/ shared. */ start = startblock & ~XFS_REFC_COWFLAG; if (domain != XFS_REFC_DOMAIN_SHARED) start |= XFS_REFC_COWFLAG; return start; } enum xfs_refcount_intent_type { XFS_REFCOUNT_INCREASE = 1, XFS_REFCOUNT_DECREASE, XFS_REFCOUNT_ALLOC_COW, XFS_REFCOUNT_FREE_COW, }; #define XFS_REFCOUNT_INTENT_STRINGS \ { XFS_REFCOUNT_INCREASE, "incr" }, \ { XFS_REFCOUNT_DECREASE, "decr" }, \ { XFS_REFCOUNT_ALLOC_COW, "alloc_cow" }, \ { XFS_REFCOUNT_FREE_COW, "free_cow" } struct xfs_refcount_intent { struct list_head ri_list; struct xfs_group *ri_group; enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; bool ri_realtime; }; /* Check that the refcount is appropriate for the record domain. */ static inline bool xfs_refcount_check_domain( const struct xfs_refcount_irec *irec) { if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1) return false; if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2) return false; return true; } void xfs_refcount_increase_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); void xfs_refcount_decrease_extent(struct xfs_trans *tp, bool isrt, struct xfs_bmbt_irec *irec); int xfs_refcount_finish_one(struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); int xfs_rtrefcount_finish_one(struct xfs_trans *tp, struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur); extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur, xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_end_of_shared); void xfs_refcount_alloc_cow_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len); void xfs_refcount_free_cow_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsb, xfs_extlen_t len); int xfs_refcount_recover_cow_leftovers(struct xfs_group *xg); /* * While we're adjusting the refcounts records of an extent, we have * to keep an eye on the number of extents we're dirtying -- run too * many in a single transaction and we'll exceed the transaction's * reservation and crash the fs. Each record adds 12 bytes to the * log (plus any key updates) so we'll conservatively assume 32 bytes * per record. We must also leave space for btree splits on both ends * of the range and space for the CUD and a new CUI. * * Each EFI that we attach to the transaction is assumed to consume ~32 bytes. * This is a low estimate for an EFI tracking a single extent (16 bytes for the * EFI header, 16 for the extent, and 12 for the xlog op header), but the * estimate is acceptable if there's more than one extent being freed. * In the worst case of freeing every other block during a refcount decrease * operation, we amortize the space used for one EFI log item across 16 * extents. */ #define XFS_REFCOUNT_ITEM_OVERHEAD 32 extern int xfs_refcount_has_records(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome); union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag, const struct xfs_refcount_irec *irec); xfs_failaddr_t xfs_rtrefcount_check_irec(struct xfs_rtgroup *rtg, const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); extern struct kmem_cache *xfs_refcount_intent_cache; int __init xfs_refcount_intent_init_cache(void); void xfs_refcount_intent_destroy_cache(void); typedef int (*xfs_refcount_query_range_fn)( struct xfs_btree_cur *cur, const struct xfs_refcount_irec *rec, void *priv); int xfs_refcount_query_range(struct xfs_btree_cur *cur, const struct xfs_refcount_irec *low_rec, const struct xfs_refcount_irec *high_rec, xfs_refcount_query_range_fn fn, void *priv); #endif /* __XFS_REFCOUNT_H__ */ |
| 13 12 12 5 6 6 1 2 11 10 1 10 2 1 11 12 10 3 1 1 2 7 10 2 3 2 3 8 13 13 2 10 8 1 10 8 5 7 2 3 10 11 11 1 3 10 2 1 1 9 13 13 16 3 12 1 12 1 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 | // SPDX-License-Identifier: GPL-2.0 #include "backref.h" #include "btrfs_inode.h" #include "fiemap.h" #include "file.h" #include "file-item.h" struct btrfs_fiemap_entry { u64 offset; u64 phys; u64 len; u32 flags; }; /* * Indicate the caller of emit_fiemap_extent() that it needs to unlock the file * range from the inode's io tree, unlock the subvolume tree search path, flush * the fiemap cache and relock the file range and research the subvolume tree. * The value here is something negative that can't be confused with a valid * errno value and different from 1 because that's also a return value from * fiemap_fill_next_extent() and also it's often used to mean some btree search * did not find a key, so make it some distinct negative value. */ #define BTRFS_FIEMAP_FLUSH_CACHE (-(MAX_ERRNO + 1)) /* * Used to: * * - Cache the next entry to be emitted to the fiemap buffer, so that we can * merge extents that are contiguous and can be grouped as a single one; * * - Store extents ready to be written to the fiemap buffer in an intermediary * buffer. This intermediary buffer is to ensure that in case the fiemap * buffer is memory mapped to the fiemap target file, we don't deadlock * during btrfs_page_mkwrite(). This is because during fiemap we are locking * an extent range in order to prevent races with delalloc flushing and * ordered extent completion, which is needed in order to reliably detect * delalloc in holes and prealloc extents. And this can lead to a deadlock * if the fiemap buffer is memory mapped to the file we are running fiemap * against (a silly, useless in practice scenario, but possible) because * btrfs_page_mkwrite() will try to lock the same extent range. */ struct fiemap_cache { /* An array of ready fiemap entries. */ struct btrfs_fiemap_entry *entries; /* Number of entries in the entries array. */ int entries_size; /* Index of the next entry in the entries array to write to. */ int entries_pos; /* * Once the entries array is full, this indicates what's the offset for * the next file extent item we must search for in the inode's subvolume * tree after unlocking the extent range in the inode's io tree and * releasing the search path. */ u64 next_search_offset; /* * This matches struct fiemap_extent_info::fi_mapped_extents, we use it * to count ourselves emitted extents and stop instead of relying on * fiemap_fill_next_extent() because we buffer ready fiemap entries at * the @entries array, and we want to stop as soon as we hit the max * amount of extents to map, not just to save time but also to make the * logic at extent_fiemap() simpler. */ unsigned int extents_mapped; /* Fields for the cached extent (unsubmitted, not ready, extent). */ u64 offset; u64 phys; u64 len; u32 flags; bool cached; }; static int flush_fiemap_cache(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache) { for (int i = 0; i < cache->entries_pos; i++) { struct btrfs_fiemap_entry *entry = &cache->entries[i]; int ret; ret = fiemap_fill_next_extent(fieinfo, entry->offset, entry->phys, entry->len, entry->flags); /* * Ignore 1 (reached max entries) because we keep track of that * ourselves in emit_fiemap_extent(). */ if (ret < 0) return ret; } cache->entries_pos = 0; return 0; } /* * Helper to submit fiemap extent. * * Will try to merge current fiemap extent specified by @offset, @phys, * @len and @flags with cached one. * And only when we fails to merge, cached one will be submitted as * fiemap extent. * * Return value is the same as fiemap_fill_next_extent(). */ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache, u64 offset, u64 phys, u64 len, u32 flags) { struct btrfs_fiemap_entry *entry; u64 cache_end; /* Set at the end of extent_fiemap(). */ ASSERT((flags & FIEMAP_EXTENT_LAST) == 0); if (!cache->cached) goto assign; /* * When iterating the extents of the inode, at extent_fiemap(), we may * find an extent that starts at an offset behind the end offset of the * previous extent we processed. This happens if fiemap is called * without FIEMAP_FLAG_SYNC and there are ordered extents completing * after we had to unlock the file range, release the search path, emit * the fiemap extents stored in the buffer (cache->entries array) and * the lock the remainder of the range and re-search the btree. * * For example we are in leaf X processing its last item, which is the * file extent item for file range [512K, 1M[, and after * btrfs_next_leaf() releases the path, there's an ordered extent that * completes for the file range [768K, 2M[, and that results in trimming * the file extent item so that it now corresponds to the file range * [512K, 768K[ and a new file extent item is inserted for the file * range [768K, 2M[, which may end up as the last item of leaf X or as * the first item of the next leaf - in either case btrfs_next_leaf() * will leave us with a path pointing to the new extent item, for the * file range [768K, 2M[, since that's the first key that follows the * last one we processed. So in order not to report overlapping extents * to user space, we trim the length of the previously cached extent and * emit it. * * Upon calling btrfs_next_leaf() we may also find an extent with an * offset smaller than or equals to cache->offset, and this happens * when we had a hole or prealloc extent with several delalloc ranges in * it, but after btrfs_next_leaf() released the path, delalloc was * flushed and the resulting ordered extents were completed, so we can * now have found a file extent item for an offset that is smaller than * or equals to what we have in cache->offset. We deal with this as * described below. */ cache_end = cache->offset + cache->len; if (cache_end > offset) { if (offset == cache->offset) { /* * We cached a delalloc range (found in the io tree) for * a hole or prealloc extent and we have now found a * file extent item for the same offset. What we have * now is more recent and up to date, so discard what * we had in the cache and use what we have just found. */ goto assign; } else if (offset > cache->offset) { /* * The extent range we previously found ends after the * offset of the file extent item we found and that * offset falls somewhere in the middle of that previous * extent range. So adjust the range we previously found * to end at the offset of the file extent item we have * just found, since this extent is more up to date. * Emit that adjusted range and cache the file extent * item we have just found. This corresponds to the case * where a previously found file extent item was split * due to an ordered extent completing. */ cache->len = offset - cache->offset; goto emit; } else { const u64 range_end = offset + len; /* * The offset of the file extent item we have just found * is behind the cached offset. This means we were * processing a hole or prealloc extent for which we * have found delalloc ranges (in the io tree), so what * we have in the cache is the last delalloc range we * found while the file extent item we found can be * either for a whole delalloc range we previously * emitted or only a part of that range. * * We have two cases here: * * 1) The file extent item's range ends at or behind the * cached extent's end. In this case just ignore the * current file extent item because we don't want to * overlap with previous ranges that may have been * emitted already; * * 2) The file extent item starts behind the currently * cached extent but its end offset goes beyond the * end offset of the cached extent. We don't want to * overlap with a previous range that may have been * emitted already, so we emit the currently cached * extent and then partially store the current file * extent item's range in the cache, for the subrange * going the cached extent's end to the end of the * file extent item. */ if (range_end <= cache_end) return 0; if (!(flags & (FIEMAP_EXTENT_ENCODED | FIEMAP_EXTENT_DELALLOC))) phys += cache_end - offset; offset = cache_end; len = range_end - cache_end; goto emit; } } /* * Only merges fiemap extents if * 1) Their logical addresses are continuous * * 2) Their physical addresses are continuous * So truly compressed (physical size smaller than logical size) * extents won't get merged with each other * * 3) Share same flags */ if (cache->offset + cache->len == offset && cache->phys + cache->len == phys && cache->flags == flags) { cache->len += len; return 0; } emit: /* Not mergeable, need to submit cached one */ if (cache->entries_pos == cache->entries_size) { /* * We will need to research for the end offset of the last * stored extent and not from the current offset, because after * unlocking the range and releasing the path, if there's a hole * between that end offset and this current offset, a new extent * may have been inserted due to a new write, so we don't want * to miss it. */ entry = &cache->entries[cache->entries_size - 1]; cache->next_search_offset = entry->offset + entry->len; cache->cached = false; return BTRFS_FIEMAP_FLUSH_CACHE; } entry = &cache->entries[cache->entries_pos]; entry->offset = cache->offset; entry->phys = cache->phys; entry->len = cache->len; entry->flags = cache->flags; cache->entries_pos++; cache->extents_mapped++; if (cache->extents_mapped == fieinfo->fi_extents_max) { cache->cached = false; return 1; } assign: cache->cached = true; cache->offset = offset; cache->phys = phys; cache->len = len; cache->flags = flags; return 0; } /* * Emit last fiemap cache * * The last fiemap cache may still be cached in the following case: * 0 4k 8k * |<- Fiemap range ->| * |<------------ First extent ----------->| * * In this case, the first extent range will be cached but not emitted. * So we must emit it before ending extent_fiemap(). */ static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache) { int ret; if (!cache->cached) return 0; ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); cache->cached = false; if (ret > 0) ret = 0; return ret; } static int fiemap_next_leaf_item(struct btrfs_inode *inode, struct btrfs_path *path) { struct extent_buffer *clone = path->nodes[0]; struct btrfs_key key; int slot; int ret; path->slots[0]++; if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) return 0; /* * Add a temporary extra ref to an already cloned extent buffer to * prevent btrfs_next_leaf() freeing it, we want to reuse it to avoid * the cost of allocating a new one. */ ASSERT(test_bit(EXTENT_BUFFER_UNMAPPED, &clone->bflags)); refcount_inc(&clone->refs); ret = btrfs_next_leaf(inode->root, path); if (ret != 0) goto out; /* * Don't bother with cloning if there are no more file extent items for * our inode. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != btrfs_ino(inode) || key.type != BTRFS_EXTENT_DATA_KEY) { ret = 1; goto out; } /* * Important to preserve the start field, for the optimizations when * checking if extents are shared (see extent_fiemap()). * * We must set ->start before calling copy_extent_buffer_full(). If we * are on sub-pagesize blocksize, we use ->start to determine the offset * into the folio where our eb exists, and if we update ->start after * the fact then any subsequent reads of the eb may read from a * different offset in the folio than where we originally copied into. */ clone->start = path->nodes[0]->start; /* See the comment at fiemap_search_slot() about why we clone. */ copy_extent_buffer_full(clone, path->nodes[0]); slot = path->slots[0]; btrfs_release_path(path); path->nodes[0] = clone; path->slots[0] = slot; out: if (ret) free_extent_buffer(clone); return ret; } /* * Search for the first file extent item that starts at a given file offset or * the one that starts immediately before that offset. * Returns: 0 on success, < 0 on error, 1 if not found. */ static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path, u64 file_offset) { const u64 ino = btrfs_ino(inode); struct btrfs_root *root = inode->root; struct extent_buffer *clone; struct btrfs_key key; int slot; int ret; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = file_offset; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; if (ret > 0 && path->slots[0] > 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) path->slots[0]--; } if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret != 0) return ret; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) return 1; } /* * We clone the leaf and use it during fiemap. This is because while * using the leaf we do expensive things like checking if an extent is * shared, which can take a long time. In order to prevent blocking * other tasks for too long, we use a clone of the leaf. We have locked * the file range in the inode's io tree, so we know none of our file * extent items can change. This way we avoid blocking other tasks that * want to insert items for other inodes in the same leaf or b+tree * rebalance operations (triggered for example when someone is trying * to push items into this leaf when trying to insert an item in a * neighbour leaf). * We also need the private clone because holding a read lock on an * extent buffer of the subvolume's b+tree will make lockdep unhappy * when we check if extents are shared, as backref walking may need to * lock the same leaf we are processing. */ clone = btrfs_clone_extent_buffer(path->nodes[0]); if (!clone) return -ENOMEM; slot = path->slots[0]; btrfs_release_path(path); path->nodes[0] = clone; path->slots[0] = slot; return 0; } /* * Process a range which is a hole or a prealloc extent in the inode's subvolume * btree. If @disk_bytenr is 0, we are dealing with a hole, otherwise a prealloc * extent. The end offset (@end) is inclusive. */ static int fiemap_process_hole(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache, struct extent_state **delalloc_cached_state, struct btrfs_backref_share_check_ctx *backref_ctx, u64 disk_bytenr, u64 extent_offset, u64 extent_gen, u64 start, u64 end) { const u64 i_size = i_size_read(&inode->vfs_inode); u64 cur_offset = start; u64 last_delalloc_end = 0; u32 prealloc_flags = FIEMAP_EXTENT_UNWRITTEN; bool checked_extent_shared = false; int ret; /* * There can be no delalloc past i_size, so don't waste time looking for * it beyond i_size. */ while (cur_offset < end && cur_offset < i_size) { u64 delalloc_start; u64 delalloc_end; u64 prealloc_start; u64 prealloc_len = 0; bool delalloc; delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end, delalloc_cached_state, &delalloc_start, &delalloc_end); if (!delalloc) break; /* * If this is a prealloc extent we have to report every section * of it that has no delalloc. */ if (disk_bytenr != 0) { if (last_delalloc_end == 0) { prealloc_start = start; prealloc_len = delalloc_start - start; } else { prealloc_start = last_delalloc_end + 1; prealloc_len = delalloc_start - prealloc_start; } } if (prealloc_len > 0) { if (!checked_extent_shared && fieinfo->fi_extents_max) { ret = btrfs_is_data_extent_shared(inode, disk_bytenr, extent_gen, backref_ctx); if (ret < 0) return ret; else if (ret > 0) prealloc_flags |= FIEMAP_EXTENT_SHARED; checked_extent_shared = true; } ret = emit_fiemap_extent(fieinfo, cache, prealloc_start, disk_bytenr + extent_offset, prealloc_len, prealloc_flags); if (ret) return ret; extent_offset += prealloc_len; } ret = emit_fiemap_extent(fieinfo, cache, delalloc_start, 0, delalloc_end + 1 - delalloc_start, FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); if (ret) return ret; last_delalloc_end = delalloc_end; cur_offset = delalloc_end + 1; extent_offset += cur_offset - delalloc_start; cond_resched(); } /* * Either we found no delalloc for the whole prealloc extent or we have * a prealloc extent that spans i_size or starts at or after i_size. */ if (disk_bytenr != 0 && last_delalloc_end < end) { u64 prealloc_start; u64 prealloc_len; if (last_delalloc_end == 0) { prealloc_start = start; prealloc_len = end + 1 - start; } else { prealloc_start = last_delalloc_end + 1; prealloc_len = end + 1 - prealloc_start; } if (!checked_extent_shared && fieinfo->fi_extents_max) { ret = btrfs_is_data_extent_shared(inode, disk_bytenr, extent_gen, backref_ctx); if (ret < 0) return ret; else if (ret > 0) prealloc_flags |= FIEMAP_EXTENT_SHARED; } ret = emit_fiemap_extent(fieinfo, cache, prealloc_start, disk_bytenr + extent_offset, prealloc_len, prealloc_flags); if (ret) return ret; } return 0; } static int fiemap_find_last_extent_offset(struct btrfs_inode *inode, struct btrfs_path *path, u64 *last_extent_end_ret) { const u64 ino = btrfs_ino(inode); struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_file_extent_item *ei; struct btrfs_key key; u64 disk_bytenr; int ret; /* * Lookup the last file extent. We're not using i_size here because * there might be preallocation past i_size. */ ret = btrfs_lookup_file_extent(NULL, root, path, ino, (u64)-1, 0); /* There can't be a file extent item at offset (u64)-1 */ ASSERT(ret != 0); if (ret < 0) return ret; /* * For a non-existing key, btrfs_search_slot() always leaves us at a * slot > 0, except if the btree is empty, which is impossible because * at least it has the inode item for this inode and all the items for * the root inode 256. */ ASSERT(path->slots[0] > 0); path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) { /* No file extent items in the subvolume tree. */ *last_extent_end_ret = 0; return 0; } /* * For an inline extent, the disk_bytenr is where inline data starts at, * so first check if we have an inline extent item before checking if we * have an implicit hole (disk_bytenr == 0). */ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { *last_extent_end_ret = btrfs_file_extent_end(path); return 0; } /* * Find the last file extent item that is not a hole (when NO_HOLES is * not enabled). This should take at most 2 iterations in the worst * case: we have one hole file extent item at slot 0 of a leaf and * another hole file extent item as the last item in the previous leaf. * This is because we merge file extent items that represent holes. */ disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); while (disk_bytenr == 0) { ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); if (ret < 0) { return ret; } else if (ret > 0) { /* No file extent items that are not holes. */ *last_extent_end_ret = 0; return 0; } leaf = path->nodes[0]; ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); } *last_extent_end_ret = btrfs_file_extent_end(path); return 0; } static int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { const u64 ino = btrfs_ino(inode); struct extent_state *cached_state = NULL; struct extent_state *delalloc_cached_state = NULL; BTRFS_PATH_AUTO_FREE(path); struct fiemap_cache cache = { 0 }; struct btrfs_backref_share_check_ctx *backref_ctx; u64 last_extent_end = 0; u64 prev_extent_end; u64 range_start; u64 range_end; const u64 sectorsize = inode->root->fs_info->sectorsize; bool stopped = false; int ret; cache.entries_size = PAGE_SIZE / sizeof(struct btrfs_fiemap_entry); cache.entries = kmalloc_array(cache.entries_size, sizeof(struct btrfs_fiemap_entry), GFP_KERNEL); backref_ctx = btrfs_alloc_backref_share_check_ctx(); path = btrfs_alloc_path(); if (!cache.entries || !backref_ctx || !path) { ret = -ENOMEM; goto out; } restart: range_start = round_down(start, sectorsize); range_end = round_up(start + len, sectorsize); prev_extent_end = range_start; btrfs_lock_extent(&inode->io_tree, range_start, range_end, &cached_state); ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) goto out_unlock; btrfs_release_path(path); path->reada = READA_FORWARD; ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { goto out_unlock; } else if (ret > 0) { /* * No file extent item found, but we may have delalloc between * the current offset and i_size. So check for that. */ ret = 0; goto check_eof_delalloc; } while (prev_extent_end < range_end) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_file_extent_item *ei; struct btrfs_key key; u64 extent_end; u64 extent_len; u64 extent_offset = 0; u64 extent_gen; u64 disk_bytenr = 0; u64 flags = 0; int extent_type; u8 compression; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; extent_end = btrfs_file_extent_end(path); /* * The first iteration can leave us at an extent item that ends * before our range's start. Move to the next item. */ if (extent_end <= range_start) goto next_item; backref_ctx->curr_leaf_bytenr = leaf->start; /* We have in implicit hole (NO_HOLES feature enabled). */ if (prev_extent_end < key.offset) { const u64 hole_end = min(key.offset, range_end) - 1; ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, prev_extent_end, hole_end); if (ret < 0) { goto out_unlock; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; break; } /* We've reached the end of the fiemap range, stop. */ if (key.offset >= range_end) { stopped = true; break; } } extent_len = extent_end - key.offset; ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); compression = btrfs_file_extent_compression(leaf, ei); extent_type = btrfs_file_extent_type(leaf, ei); extent_gen = btrfs_file_extent_generation(leaf, ei); if (extent_type != BTRFS_FILE_EXTENT_INLINE) { disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); if (compression == BTRFS_COMPRESS_NONE) extent_offset = btrfs_file_extent_offset(leaf, ei); } if (compression != BTRFS_COMPRESS_NONE) flags |= FIEMAP_EXTENT_ENCODED; if (extent_type == BTRFS_FILE_EXTENT_INLINE) { flags |= FIEMAP_EXTENT_DATA_INLINE; flags |= FIEMAP_EXTENT_NOT_ALIGNED; ret = emit_fiemap_extent(fieinfo, &cache, key.offset, 0, extent_len, flags); } else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, disk_bytenr, extent_offset, extent_gen, key.offset, extent_end - 1); } else if (disk_bytenr == 0) { /* We have an explicit hole. */ ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, key.offset, extent_end - 1); } else { /* We have a regular extent. */ if (fieinfo->fi_extents_max) { ret = btrfs_is_data_extent_shared(inode, disk_bytenr, extent_gen, backref_ctx); if (ret < 0) goto out_unlock; else if (ret > 0) flags |= FIEMAP_EXTENT_SHARED; } ret = emit_fiemap_extent(fieinfo, &cache, key.offset, disk_bytenr + extent_offset, extent_len, flags); } if (ret < 0) { goto out_unlock; } else if (ret > 0) { /* emit_fiemap_extent() told us to stop. */ stopped = true; break; } prev_extent_end = extent_end; next_item: if (fatal_signal_pending(current)) { ret = -EINTR; goto out_unlock; } ret = fiemap_next_leaf_item(inode, path); if (ret < 0) { goto out_unlock; } else if (ret > 0) { /* No more file extent items for this inode. */ break; } cond_resched(); } check_eof_delalloc: if (!stopped && prev_extent_end < range_end) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) goto out_unlock; prev_extent_end = range_end; } if (cache.cached && cache.offset + cache.len >= last_extent_end) { const u64 i_size = i_size_read(&inode->vfs_inode); if (prev_extent_end < i_size) { u64 delalloc_start; u64 delalloc_end; bool delalloc; delalloc = btrfs_find_delalloc_in_range(inode, prev_extent_end, i_size - 1, &delalloc_cached_state, &delalloc_start, &delalloc_end); if (!delalloc) cache.flags |= FIEMAP_EXTENT_LAST; } else { cache.flags |= FIEMAP_EXTENT_LAST; } } out_unlock: btrfs_unlock_extent(&inode->io_tree, range_start, range_end, &cached_state); if (ret == BTRFS_FIEMAP_FLUSH_CACHE) { btrfs_release_path(path); ret = flush_fiemap_cache(fieinfo, &cache); if (ret) goto out; len -= cache.next_search_offset - start; start = cache.next_search_offset; goto restart; } else if (ret < 0) { goto out; } /* * Must free the path before emitting to the fiemap buffer because we * may have a non-cloned leaf and if the fiemap buffer is memory mapped * to a file, a write into it (through btrfs_page_mkwrite()) may trigger * waiting for an ordered extent that in order to complete needs to * modify that leaf, therefore leading to a deadlock. */ btrfs_free_path(path); path = NULL; ret = flush_fiemap_cache(fieinfo, &cache); if (ret) goto out; ret = emit_last_fiemap_cache(fieinfo, &cache); out: btrfs_free_extent_state(delalloc_cached_state); kfree(cache.entries); btrfs_free_backref_share_ctx(backref_ctx); return ret; } int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { struct btrfs_inode *btrfs_inode = BTRFS_I(inode); int ret; ret = fiemap_prep(inode, fieinfo, start, &len, 0); if (ret) return ret; /* * fiemap_prep() called filemap_write_and_wait() for the whole possible * file range (0 to LLONG_MAX), but that is not enough if we have * compression enabled. The first filemap_fdatawrite_range() only kicks * in the compression of data (in an async thread) and will return * before the compression is done and writeback is started. A second * filemap_fdatawrite_range() is needed to wait for the compression to * complete and writeback to start. We also need to wait for ordered * extents to complete, because our fiemap implementation uses mainly * file extent items to list the extents, searching for extent maps * only for file ranges with holes or prealloc extents to figure out * if we have delalloc in those ranges. */ if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) { ret = btrfs_wait_ordered_range(btrfs_inode, 0, LLONG_MAX); if (ret) return ret; } btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED); /* * We did an initial flush to avoid holding the inode's lock while * triggering writeback and waiting for the completion of IO and ordered * extents. Now after we locked the inode we do it again, because it's * possible a new write may have happened in between those two steps. */ if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) { ret = btrfs_wait_ordered_range(btrfs_inode, 0, LLONG_MAX); if (ret) { btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); return ret; } } ret = extent_fiemap(btrfs_inode, fieinfo, start, len); btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); return ret; } |
| 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 | /* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ /* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * 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 General Public License for more details. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: * Copyright (c) 2008, Swedish Institute of Computer Science. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the Institute nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <linux/if_arp.h> #include <net/ipv6.h> #include <net/netdev_lock.h> #include "6lowpan_i.h" static int open_count; static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; static int lowpan_dev_init(struct net_device *ldev) { netdev_lockdep_set_classes(ldev); return 0; } static int lowpan_open(struct net_device *dev) { if (!open_count) lowpan_rx_init(); open_count++; return 0; } static int lowpan_stop(struct net_device *dev) { open_count--; if (!open_count) lowpan_rx_exit(); return 0; } static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) { struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n)); /* default no short_addr is available for a neighbour */ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); return 0; } static int lowpan_get_iflink(const struct net_device *dev) { return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) { memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; ldev->netns_immutable = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; } return 0; } static int lowpan_newlink(struct net_device *ldev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **tb = params->tb; struct net_device *wdev; int ret; ASSERT_RTNL(); pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; if (params->link_net && !net_eq(params->link_net, dev_net(ldev))) return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; if (wdev->type != ARPHRD_IEEE802154) { dev_put(wdev); return -EINVAL; } if (wdev->ieee802154_ptr->lowpan_dev) { dev_put(wdev); return -EBUSY; } lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 * header. */ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh); ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; } wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { struct net_device *wdev = lowpan_802154_dev(ldev)->wdev; ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; lowpan_unregister_netdevice(ldev); dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_802154_dev)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, .validate = lowpan_validate, }; static inline int __init lowpan_netlink_init(void) { return rtnl_link_register(&lowpan_link_ops); } static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev; if (ndev->type != ARPHRD_IEEE802154) return NOTIFY_DONE; wpan_dev = ndev->ieee802154_ptr; if (!wpan_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: /* Check if wpan interface is unregistered that we * also delete possible lowpan interfaces which belongs * to the wpan interface. */ if (wpan_dev->lowpan_dev) lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_dev_notifier = { .notifier_call = lowpan_device_event, }; static int __init lowpan_init_module(void) { int err = 0; err = lowpan_net_frag_init(); if (err < 0) goto out; err = lowpan_netlink_init(); if (err < 0) goto out_frag; err = register_netdevice_notifier(&lowpan_dev_notifier); if (err < 0) goto out_pack; return 0; out_pack: lowpan_netlink_fini(); out_frag: lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { lowpan_netlink_fini(); lowpan_net_frag_exit(); unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); MODULE_DESCRIPTION("IPv6 over Low power Wireless Personal Area Network IEEE 802.15.4 core"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); |
| 9107 9138 9183 9679 9668 9675 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_CONTEXT_H #define __X86_KERNEL_FPU_CONTEXT_H #include <asm/fpu/xstate.h> #include <asm/trace/fpu.h> /* Functions related to FPU context tracking */ /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } static inline void fpregs_deactivate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* Internal helper for switch_fpu_return() and signal frame setup */ static inline void fpregs_restore_userregs(void) { struct fpu *fpu = x86_task_fpu(current); int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { /* * This restores _all_ xstate which has not been * established yet. * * If PKRU is enabled, then the PKRU value is already * correct because it was either set in switch_to() or in * flush_thread(). So it is excluded because it might be * not up to date in current->thread.fpu->xsave state. * * XFD state is handled in restore_fpregs_from_fpstate(). */ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } #endif |
| 24 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2009 IBM Corporation * Author: Mimi Zohar <zohar@us.ibm.com> */ #ifndef _LINUX_INTEGRITY_H #define _LINUX_INTEGRITY_H #include <linux/fs.h> #include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_PASS_IMMUTABLE, INTEGRITY_FAIL, INTEGRITY_FAIL_IMMUTABLE, INTEGRITY_NOLABEL, INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; #ifdef CONFIG_INTEGRITY extern void __init integrity_load_keys(void); #else static inline void integrity_load_keys(void) { } #endif /* CONFIG_INTEGRITY */ /* An inode's attributes for detection of changes */ struct integrity_inode_attributes { u64 version; /* track inode changes */ unsigned long ino; dev_t dev; }; /* * On stacked filesystems the i_version alone is not enough to detect file data * or metadata change. Additional metadata is required. */ static inline void integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, u64 i_version, const struct inode *inode) { attrs->version = i_version; attrs->dev = inode->i_sb->s_dev; attrs->ino = inode->i_ino; } /* * On stacked filesystems detect whether the inode or its content has changed. */ static inline bool integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, const struct inode *inode) { return (inode->i_sb->s_dev != attrs->dev || inode->i_ino != attrs->ino || !inode_eq_iversion(inode, attrs->version)); } #endif /* _LINUX_INTEGRITY_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic parts * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/llc.h> #include <net/llc.h> #include <net/stp.h> #include <net/switchdev.h> #include "br_private.h" /* * Handle changes in state of network devices enslaved to a bridge. * * Note: don't care about up/down if bridge itself is down, because * port state is checked when bridge is brought up. */ static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; bool notified = false; bool changed_addr; int err; if (netif_is_bridge_master(dev)) { struct net_bridge *br = netdev_priv(dev); if (event == NETDEV_REGISTER) br_fdb_change_mac_address(br, dev->dev_addr); err = br_vlan_bridge_event(dev, event, ptr); if (err) return notifier_from_errno(err); if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ err = br_sysfs_addbr(dev); if (err) return notifier_from_errno(err); return NOTIFY_DONE; } } if (is_vlan_dev(dev)) { struct net_device *real_dev = vlan_dev_real_dev(dev); if (netif_is_bridge_master(real_dev)) br_vlan_vlan_upper_event(real_dev, dev, event); } /* not a port of a bridge */ p = br_port_get_rtnl(dev); if (!p) return NOTIFY_DONE; br = p->br; switch (event) { case NETDEV_CHANGEMTU: br_mtu_auto_adjust(br); break; case NETDEV_PRE_CHANGEADDR: if (br->dev->addr_assign_type == NET_ADDR_SET) break; prechaddr_info = ptr; err = netif_pre_changeaddr_notify(br->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); break; case NETDEV_CHANGEADDR: spin_lock_bh(&br->lock); br_fdb_changeaddr(p, dev->dev_addr); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); break; case NETDEV_CHANGE: br_port_carrier_check(p, ¬ified); break; case NETDEV_FEAT_CHANGE: netdev_update_features(br->dev); break; case NETDEV_DOWN: spin_lock_bh(&br->lock); if (br->dev->flags & IFF_UP) { br_stp_disable_port(p); notified = true; } spin_unlock_bh(&br->lock); break; case NETDEV_UP: if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); notified = true; spin_unlock_bh(&br->lock); } break; case NETDEV_UNREGISTER: br_del_if(br, dev); break; case NETDEV_CHANGENAME: err = br_sysfs_renameif(p); if (err) return notifier_from_errno(err); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, br->dev); break; } if (event != NETDEV_UNREGISTER) br_vlan_port_event(p, event); /* Events that may cause spanning tree to refresh */ if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP || event == NETDEV_CHANGE || event == NETDEV_DOWN)) br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; } static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; /* called with RTNL or RCU */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; p = br_port_get_rtnl_rcu(dev); if (!p) goto out; br = p->br; switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid, fdb_info->locked, false); if (err) { err = notifier_from_errno(err); break; } br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid, false); if (err) err = notifier_from_errno(err); break; case SWITCHDEV_FDB_OFFLOADED: fdb_info = ptr; br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_FLUSH_TO_BRIDGE: fdb_info = ptr; /* Don't delete static entries */ br_fdb_delete_by_port(br, p, fdb_info->vid, 0); break; } out: return err; } static struct notifier_block br_switchdev_notifier = { .notifier_call = br_switchdev_event, }; /* called under rtnl_mutex */ static int br_switchdev_blocking_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_brport_info *brport_info; const struct switchdev_brport *b; struct net_bridge_port *p; int err = NOTIFY_DONE; p = br_port_get_rtnl(dev); if (!p) goto out; switch (event) { case SWITCHDEV_BRPORT_OFFLOADED: brport_info = ptr; b = &brport_info->brport; err = br_switchdev_port_offload(p, b->dev, b->ctx, b->atomic_nb, b->blocking_nb, b->tx_fwd_offload, extack); err = notifier_from_errno(err); break; case SWITCHDEV_BRPORT_UNOFFLOADED: brport_info = ptr; b = &brport_info->brport; br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, b->blocking_nb); break; case SWITCHDEV_BRPORT_REPLAY: brport_info = ptr; b = &brport_info->brport; err = br_switchdev_port_replay(p, b->dev, b->ctx, b->atomic_nb, b->blocking_nb, extack); err = notifier_from_errno(err); break; } out: return err; } static struct notifier_block br_switchdev_blocking_notifier = { .notifier_call = br_switchdev_blocking_event, }; static int br_toggle_fdb_local_vlan_0(struct net_bridge *br, bool on, struct netlink_ext_ack *extack) { int err; if (br_opt_get(br, BROPT_FDB_LOCAL_VLAN_0) == on) return 0; err = br_fdb_toggle_local_vlan_0(br, on, extack); if (err) return err; br_opt_toggle(br, BROPT_FDB_LOCAL_VLAN_0, on); return 0; } /* br_boolopt_toggle - change user-controlled boolean option * * @br: bridge device * @opt: id of the option to change * @on: new option value * @extack: extack for error messages * * Changes the value of the respective boolean option to @on taking care of * any internal option value mapping and configuration. */ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, struct netlink_ext_ack *extack) { int err = 0; switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: br_opt_toggle(br, BROPT_NO_LL_LEARN, on); break; case BR_BOOLOPT_MCAST_VLAN_SNOOPING: err = br_multicast_toggle_vlan_snooping(br, on, extack); break; case BR_BOOLOPT_MST_ENABLE: err = br_mst_set_enabled(br, on, extack); break; case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION: br_opt_toggle(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION, on); break; case BR_BOOLOPT_FDB_LOCAL_VLAN_0: err = br_toggle_fdb_local_vlan_0(br, on, extack); break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return err; } int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) { switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: return br_opt_get(br, BROPT_NO_LL_LEARN); case BR_BOOLOPT_MCAST_VLAN_SNOOPING: return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); case BR_BOOLOPT_MST_ENABLE: return br_opt_get(br, BROPT_MST_ENABLED); case BR_BOOLOPT_MDB_OFFLOAD_FAIL_NOTIFICATION: return br_opt_get(br, BROPT_MDB_OFFLOAD_FAIL_NOTIFICATION); case BR_BOOLOPT_FDB_LOCAL_VLAN_0: return br_opt_get(br, BROPT_FDB_LOCAL_VLAN_0); default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return 0; } int br_boolopt_multi_toggle(struct net_bridge *br, struct br_boolopt_multi *bm, struct netlink_ext_ack *extack) { unsigned long bitmap = bm->optmask; int err = 0; int opt_id; opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX); if (opt_id != BITS_PER_LONG) { NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d", opt_id); return -EINVAL; } for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); err = br_boolopt_toggle(br, opt_id, on, extack); if (err) { br_debug(br, "boolopt multi-toggle error: option: %d current: %d new: %d error: %d\n", opt_id, br_boolopt_get(br, opt_id), on, err); break; } } return err; } void br_boolopt_multi_get(const struct net_bridge *br, struct br_boolopt_multi *bm) { u32 optval = 0; int opt_id; for (opt_id = 0; opt_id < BR_BOOLOPT_MAX; opt_id++) optval |= (br_boolopt_get(br, opt_id) << opt_id); bm->optval = optval; bm->optmask = GENMASK((BR_BOOLOPT_MAX - 1), 0); } /* private bridge options, controlled by the kernel */ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on) { bool cur = !!br_opt_get(br, opt); br_debug(br, "toggle option: %d state: %d -> %d\n", opt, cur, on); if (cur == on) return; if (on) set_bit(opt, &br->options); else clear_bit(opt, &br->options); } static void __net_exit br_net_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { struct net_device *dev; ASSERT_RTNL_NET(net); for_each_netdev(net, dev) if (netif_is_bridge_master(dev)) br_dev_delete(dev, dev_to_kill); } static struct pernet_operations br_net_ops = { .exit_rtnl = br_net_exit_rtnl, }; static const struct stp_proto br_stp_proto = { .rcv = br_stp_rcv, }; static int __init br_init(void) { int err; BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { pr_err("bridge: can't register sap for STP\n"); return err; } err = br_fdb_init(); if (err) goto err_out; err = register_pernet_subsys(&br_net_ops); if (err) goto err_out1; err = br_nf_core_init(); if (err) goto err_out2; err = register_netdevice_notifier(&br_device_notifier); if (err) goto err_out3; err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); if (err) goto err_out5; err = br_netlink_init(); if (err) goto err_out6; brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; #endif #if IS_MODULE(CONFIG_BRIDGE_NETFILTER) pr_info("bridge: filtering via arp/ip/ip6tables is no longer available " "by default. Update your scripts to load br_netfilter if you " "need this.\n"); #endif return 0; err_out6: unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); err_out5: unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: br_nf_core_fini(); err_out2: unregister_pernet_subsys(&br_net_ops); err_out1: br_fdb_fini(); err_out: stp_proto_unregister(&br_stp_proto); return err; } static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_nf_core_fini(); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = NULL; #endif br_fdb_fini(); } module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); MODULE_ALIAS_RTNL_LINK("bridge"); MODULE_DESCRIPTION("Ethernet bridge driver"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 418 216 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RATELIMIT_H #define _LINUX_RATELIMIT_H #include <linux/ratelimit_types.h> #include <linux/sched.h> #include <linux/spinlock.h> static inline void ratelimit_state_init(struct ratelimit_state *rs, int interval, int burst) { memset(rs, 0, sizeof(*rs)); raw_spin_lock_init(&rs->lock); rs->interval = interval; rs->burst = burst; } static inline void ratelimit_default_init(struct ratelimit_state *rs) { return ratelimit_state_init(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); } static inline void ratelimit_state_inc_miss(struct ratelimit_state *rs) { atomic_inc(&rs->missed); } static inline int ratelimit_state_get_miss(struct ratelimit_state *rs) { return atomic_read(&rs->missed); } static inline int ratelimit_state_reset_miss(struct ratelimit_state *rs) { return atomic_xchg_relaxed(&rs->missed, 0); } static inline void ratelimit_state_reset_interval(struct ratelimit_state *rs, int interval_init) { unsigned long flags; raw_spin_lock_irqsave(&rs->lock, flags); rs->interval = interval_init; rs->flags &= ~RATELIMIT_INITIALIZED; atomic_set(&rs->rs_n_left, rs->burst); ratelimit_state_reset_miss(rs); raw_spin_unlock_irqrestore(&rs->lock, flags); } static inline void ratelimit_state_exit(struct ratelimit_state *rs) { int m; if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) return; m = ratelimit_state_reset_miss(rs); if (m) pr_warn("%s: %d output lines suppressed due to ratelimiting\n", current->comm, m); } static inline void ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags) { rs->flags = flags; } extern struct ratelimit_state printk_ratelimit_state; #ifdef CONFIG_PRINTK #define WARN_ON_RATELIMIT(condition, state) ({ \ bool __rtn_cond = !!(condition); \ WARN_ON(__rtn_cond && __ratelimit(state)); \ __rtn_cond; \ }) #define WARN_RATELIMIT(condition, format, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ int rtn = !!(condition); \ \ if (unlikely(rtn && __ratelimit(&_rs))) \ WARN(rtn, format, ##__VA_ARGS__); \ \ rtn; \ }) #else #define WARN_ON_RATELIMIT(condition, state) \ WARN_ON(condition) #define WARN_RATELIMIT(condition, format, ...) \ ({ \ int rtn = WARN(condition, format, ##__VA_ARGS__); \ rtn; \ }) #endif #endif /* _LINUX_RATELIMIT_H */ |
| 415 236 6534 2763 498 2609 235 1 1 1 2 251 143 377 843 25 861 | 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 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/math.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct file; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } #define QSTR_LEN(n,l) (struct qstr)QSTR_INIT(n,l) #define QSTR(n) QSTR_LEN(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else # define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif #define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) union shortname_store { unsigned char string[DNAME_INLINE_LEN]; unsigned long words[DNAME_INLINE_WORDS]; }; #define d_lock d_lockref.lock #define d_iname d_shortname.string struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ union { struct qstr __d_name; /* for use ONLY in fs/dcache.c */ const struct qstr d_name; }; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ union shortname_store d_shortname; /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ /* --- cacheline 2 boundary (128 bytes) --- */ struct lockref d_lockref; /* per-dentry lock and refcount * keep separate from RCU lookup area if * possible! */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct hlist_node d_sib; /* child of parent list */ struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ union { struct hlist_node d_alias; /* inode alias list */ struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; }; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; enum d_real_type { D_REAL_DATA, D_REAL_METADATA, }; struct dentry_operations { int (*d_revalidate)(struct inode *, const struct qstr *, struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); bool (*d_unalias_trylock)(const struct dentry *); void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ enum dentry_flags { DCACHE_OP_HASH = BIT(0), DCACHE_OP_COMPARE = BIT(1), DCACHE_OP_REVALIDATE = BIT(2), DCACHE_OP_DELETE = BIT(3), DCACHE_OP_PRUNE = BIT(4), /* * This dentry is possibly not currently connected to the dcache tree, * in which case its parent will either be itself, or will have this * flag as well. nfsd will not use a dentry with this bit set, but will * first endeavour to clear the bit either by discovering that it is * connected, or by performing lookup operations. Any filesystem which * supports nfsd_operations MUST have a lookup function which, if it * finds a directory inode with a DCACHE_DISCONNECTED dentry, will * d_move that dentry into place and return that dentry rather than the * passed one, typically using d_splice_alias. */ DCACHE_DISCONNECTED = BIT(5), DCACHE_REFERENCED = BIT(6), /* Recently used, don't discard. */ DCACHE_DONTCACHE = BIT(7), /* Purge from memory on final dput() */ DCACHE_CANT_MOUNT = BIT(8), DCACHE_GENOCIDE = BIT(9), DCACHE_SHRINK_LIST = BIT(10), DCACHE_OP_WEAK_REVALIDATE = BIT(11), /* * this dentry has been "silly renamed" and has to be deleted on the * last dput() */ DCACHE_NFSFS_RENAMED = BIT(12), DCACHE_FSNOTIFY_PARENT_WATCHED = BIT(13), /* Parent inode is watched by some fsnotify listener */ DCACHE_DENTRY_KILLED = BIT(14), DCACHE_MOUNTED = BIT(15), /* is a mountpoint */ DCACHE_NEED_AUTOMOUNT = BIT(16), /* handle automount on this dir */ DCACHE_MANAGE_TRANSIT = BIT(17), /* manage transit from this dirent */ DCACHE_LRU_LIST = BIT(18), DCACHE_ENTRY_TYPE = (7 << 19), /* bits 19..21 are for storing type: */ DCACHE_MISS_TYPE = (0 << 19), /* Negative dentry */ DCACHE_WHITEOUT_TYPE = (1 << 19), /* Whiteout dentry (stop pathwalk) */ DCACHE_DIRECTORY_TYPE = (2 << 19), /* Normal directory */ DCACHE_AUTODIR_TYPE = (3 << 19), /* Lookupless directory (presumed automount) */ DCACHE_REGULAR_TYPE = (4 << 19), /* Regular file type */ DCACHE_SPECIAL_TYPE = (5 << 19), /* Other file type */ DCACHE_SYMLINK_TYPE = (6 << 19), /* Symlink */ DCACHE_NOKEY_NAME = BIT(22), /* Encrypted name encoded without key */ DCACHE_OP_REAL = BIT(23), DCACHE_PAR_LOOKUP = BIT(24), /* being looked up (with parent locked shared) */ DCACHE_DENTRY_CURSOR = BIT(25), DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */ }; #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); /* weird procfs mess; *NOT* exported */ extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *, const struct dentry_operations *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); extern struct dentry *d_find_alias_rcu(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } ino_t d_parent_ino(struct dentry *dentry); /* * helper function for dentry_operations.d_dname() members */ extern __printf(3, 4) char *dynamic_dname(char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(const struct dentry *, char *, int); extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** * dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a live dentry, increment the reference count and return the dentry. * Caller must hold @dentry->d_lock. Making sure that dentry is alive is * caller's resonsibility. There are many conditions sufficient to guarantee * that; e.g. anything with non-negative refcount is alive, so's anything * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; return dentry; } /** * dget - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. Conversely, a dentry with * no references can disappear for any number of reasons, starting * with memory pressure. In other words, that primitive is * used to clone an existing reference; using it on something with * zero refcount is a bug. * * NOTE: it will spin if @dentry->d_lock is held. From the deadlock * avoidance point of view it is equivalent to spin_lock()/increment * refcount/spin_unlock(), so calling it under @dentry->d_lock is * always a bug; so's calling it under ->d_lock on any of its descendents. * */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_unhash_wake(struct dentry *dentry); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) __d_lookup_unhash_wake(dentry); } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } unsigned long vfs_pressure_ratio(unsigned long val); /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, type); else return dentry; } /** * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { struct qstr name; union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); static inline struct dentry *d_first_child(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); } static inline struct dentry *d_next_sibling(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); } void set_default_d_op(struct super_block *, const struct dentry_operations *); #endif /* __LINUX_DCACHE_H */ |
| 4 1 1 1 2 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_event.h" #include "seq_oss_timer.h" #include <sound/seq_oss_legacy.h> #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include <linux/nospec.h> /* * prototypes */ static int extended_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev); static int chn_voice_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int chn_common_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int timing_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int local_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int old_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev); static int note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev); static int note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev); static int set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev); static int set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev); static int set_echo_event(struct seq_oss_devinfo *dp, union evrec *rec, struct snd_seq_event *ev); /* * convert an OSS event to ALSA event * return 0 : enqueued * non-zero : invalid - ignored */ int snd_seq_oss_process_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->s.code) { case SEQ_EXTENDED: return extended_event(dp, q, ev); case EV_CHN_VOICE: return chn_voice_event(dp, q, ev); case EV_CHN_COMMON: return chn_common_event(dp, q, ev); case EV_TIMING: return timing_event(dp, q, ev); case EV_SEQ_LOCAL: return local_event(dp, q, ev); case EV_SYSEX: return snd_seq_oss_synth_sysex(dp, q->x.dev, q->x.buf, ev); case SEQ_MIDIPUTC: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; /* put a midi byte */ if (! is_write_mode(dp->file_mode)) break; if (snd_seq_oss_midi_open(dp, q->s.dev, SNDRV_SEQ_OSS_FILE_WRITE)) break; if (snd_seq_oss_midi_filemode(dp, q->s.dev) & SNDRV_SEQ_OSS_FILE_WRITE) return snd_seq_oss_midi_putc(dp, q->s.dev, q->s.parm1, ev); break; case SEQ_ECHO: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return set_echo_event(dp, q, ev); case SEQ_PRIVATE: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return snd_seq_oss_synth_raw_event(dp, q->c[1], q->c, ev); default: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return old_event(dp, q, ev); } return -EINVAL; } /* old type events: mode1 only */ static int old_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->s.code) { case SEQ_NOTEOFF: return note_off_event(dp, 0, q->n.chn, q->n.note, q->n.vel, ev); case SEQ_NOTEON: return note_on_event(dp, 0, q->n.chn, q->n.note, q->n.vel, ev); case SEQ_WAIT: /* skip */ break; case SEQ_PGMCHANGE: return set_control_event(dp, 0, SNDRV_SEQ_EVENT_PGMCHANGE, q->n.chn, 0, q->n.note, ev); case SEQ_SYNCTIMER: return snd_seq_oss_timer_reset(dp->timer); } return -EINVAL; } /* 8bytes extended event: mode1 only */ static int extended_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { int val; switch (q->e.cmd) { case SEQ_NOTEOFF: return note_off_event(dp, q->e.dev, q->e.chn, q->e.p1, q->e.p2, ev); case SEQ_NOTEON: return note_on_event(dp, q->e.dev, q->e.chn, q->e.p1, q->e.p2, ev); case SEQ_PGMCHANGE: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_PGMCHANGE, q->e.chn, 0, q->e.p1, ev); case SEQ_AFTERTOUCH: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CHANPRESS, q->e.chn, 0, q->e.p1, ev); case SEQ_BALANCE: /* convert -128:127 to 0:127 */ val = (char)q->e.p1; val = (val + 128) / 2; return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CONTROLLER, q->e.chn, CTL_PAN, val, ev); case SEQ_CONTROLLER: val = ((short)q->e.p3 << 8) | (short)q->e.p2; switch (q->e.p1) { case CTRL_PITCH_BENDER: /* SEQ1 V2 control */ /* -0x2000:0x1fff */ return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_PITCHBEND, q->e.chn, 0, val, ev); case CTRL_PITCH_BENDER_RANGE: /* conversion: 100/semitone -> 128/semitone */ return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_REGPARAM, q->e.chn, 0, val*128/100, ev); default: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CONTROL14, q->e.chn, q->e.p1, val, ev); } case SEQ_VOLMODE: return snd_seq_oss_synth_raw_event(dp, q->e.dev, q->c, ev); } return -EINVAL; } /* channel voice events: mode1 and 2 */ static int chn_voice_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { if (q->v.chn >= 32) return -EINVAL; switch (q->v.cmd) { case MIDI_NOTEON: return note_on_event(dp, q->v.dev, q->v.chn, q->v.note, q->v.parm, ev); case MIDI_NOTEOFF: return note_off_event(dp, q->v.dev, q->v.chn, q->v.note, q->v.parm, ev); case MIDI_KEY_PRESSURE: return set_note_event(dp, q->v.dev, SNDRV_SEQ_EVENT_KEYPRESS, q->v.chn, q->v.note, q->v.parm, ev); } return -EINVAL; } /* channel common events: mode1 and 2 */ static int chn_common_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { if (q->l.chn >= 32) return -EINVAL; switch (q->l.cmd) { case MIDI_PGM_CHANGE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_PGMCHANGE, q->l.chn, 0, q->l.p1, ev); case MIDI_CTL_CHANGE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_CONTROLLER, q->l.chn, q->l.p1, q->l.val, ev); case MIDI_PITCH_BEND: /* conversion: 0:0x3fff -> -0x2000:0x1fff */ return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_PITCHBEND, q->l.chn, 0, q->l.val - 8192, ev); case MIDI_CHN_PRESSURE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_CHANPRESS, q->l.chn, 0, q->l.val, ev); } return -EINVAL; } /* timer events: mode1 and mode2 */ static int timing_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->t.cmd) { case TMR_ECHO: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return set_echo_event(dp, q, ev); else { union evrec tmp; memset(&tmp, 0, sizeof(tmp)); /* XXX: only for little-endian! */ tmp.echo = (q->t.time << 8) | SEQ_ECHO; return set_echo_event(dp, &tmp, ev); } case TMR_STOP: if (dp->seq_mode) return snd_seq_oss_timer_stop(dp->timer); return 0; case TMR_CONTINUE: if (dp->seq_mode) return snd_seq_oss_timer_continue(dp->timer); return 0; case TMR_TEMPO: if (dp->seq_mode) return snd_seq_oss_timer_tempo(dp->timer, q->t.time); return 0; } return -EINVAL; } /* local events: mode1 and 2 */ static int local_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { return -EINVAL; } /* * process note-on event for OSS synth * three different modes are available: * - SNDRV_SEQ_OSS_PROCESS_EVENTS (for one-voice per channel mode) * Accept note 255 as volume change. * - SNDRV_SEQ_OSS_PASS_EVENTS * Pass all events to lowlevel driver anyway * - SNDRV_SEQ_OSS_PROCESS_KEYPRESS (mostly for Emu8000) * Use key-pressure if note >= 128 */ static int note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info) return -ENXIO; switch (info->arg.event_passing) { case SNDRV_SEQ_OSS_PROCESS_EVENTS: if (! info->ch || ch < 0 || ch >= info->nr_voices) { /* pass directly */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } ch = array_index_nospec(ch, info->nr_voices); if (note == 255 && info->ch[ch].note >= 0) { /* volume control */ int type; if (info->ch[ch].vel) /* sample already started -- volume change */ type = SNDRV_SEQ_EVENT_KEYPRESS; else /* sample not started -- start now */ type = SNDRV_SEQ_EVENT_NOTEON; info->ch[ch].vel = vel; return set_note_event(dp, dev, type, ch, info->ch[ch].note, vel, ev); } else if (note >= 128) return -EINVAL; /* invalid */ if (note != info->ch[ch].note && info->ch[ch].note >= 0) /* note changed - note off at beginning */ set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, info->ch[ch].note, 0, ev); /* set current status */ info->ch[ch].note = note; info->ch[ch].vel = vel; if (vel) /* non-zero velocity - start the note now */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); return -EINVAL; case SNDRV_SEQ_OSS_PASS_EVENTS: /* pass the event anyway */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); case SNDRV_SEQ_OSS_PROCESS_KEYPRESS: if (note >= 128) /* key pressure: shifted by 128 */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_KEYPRESS, ch, note - 128, vel, ev); else /* normal note-on event */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } return -EINVAL; } /* * process note-off event for OSS synth */ static int note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info) return -ENXIO; switch (info->arg.event_passing) { case SNDRV_SEQ_OSS_PROCESS_EVENTS: if (! info->ch || ch < 0 || ch >= info->nr_voices) { /* pass directly */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } ch = array_index_nospec(ch, info->nr_voices); if (info->ch[ch].note >= 0) { note = info->ch[ch].note; info->ch[ch].vel = 0; info->ch[ch].note = -1; return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, note, vel, ev); } return -EINVAL; /* invalid */ case SNDRV_SEQ_OSS_PASS_EVENTS: case SNDRV_SEQ_OSS_PROCESS_KEYPRESS: /* pass the event anyway */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, note, vel, ev); } return -EINVAL; } /* * create a note event */ static int set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev) { if (!snd_seq_oss_synth_info(dp, dev)) return -ENXIO; ev->type = type; snd_seq_oss_synth_addr(dp, dev, ev); ev->data.note.channel = ch; ev->data.note.note = note; ev->data.note.velocity = vel; return 0; } /* * create a control event */ static int set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev) { if (!snd_seq_oss_synth_info(dp, dev)) return -ENXIO; ev->type = type; snd_seq_oss_synth_addr(dp, dev, ev); ev->data.control.channel = ch; ev->data.control.param = param; ev->data.control.value = val; return 0; } /* * create an echo event */ static int set_echo_event(struct seq_oss_devinfo *dp, union evrec *rec, struct snd_seq_event *ev) { ev->type = SNDRV_SEQ_EVENT_ECHO; /* echo back to itself */ snd_seq_oss_fill_addr(dp, ev, dp->addr.client, dp->addr.port); memcpy(&ev->data, rec, LONG_EVENT_SIZE); return 0; } /* * event input callback from ALSA sequencer: * the echo event is processed here. */ int snd_seq_oss_event_input(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private_data; union evrec *rec; if (ev->type != SNDRV_SEQ_EVENT_ECHO) return snd_seq_oss_midi_input(ev, direct, private_data); if (ev->source.client != dp->cseq) return 0; /* ignored */ rec = (union evrec*)&ev->data; if (rec->s.code == SEQ_SYNCTIMER) { /* sync echo back */ snd_seq_oss_writeq_wakeup(dp->writeq, rec->t.time); } else { /* echo back event */ if (dp->readq == NULL) return 0; snd_seq_oss_readq_put_event(dp->readq, rec); } return 0; } |
| 3 3 3 3 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 3 2 2 2 3 3 3 3 2 2 2 1 1 1 1 1 2 2 1 2 2 1 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/power/snapshot.c * * This file provides system snapshot/restore functionality for swsusp. * * Copyright (C) 1998-2005 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> */ #define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/version.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/suspend.h> #include <linux/delay.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/kernel.h> #include <linux/pm.h> #include <linux/device.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/nmi.h> #include <linux/syscalls.h> #include <linux/console.h> #include <linux/highmem.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/set_memory.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/io.h> #include "power.h" #if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_ARCH_HAS_SET_MEMORY) static bool hibernate_restore_protection; static bool hibernate_restore_protection_active; void enable_restore_image_protection(void) { hibernate_restore_protection = true; } static inline void hibernate_restore_protection_begin(void) { hibernate_restore_protection_active = hibernate_restore_protection; } static inline void hibernate_restore_protection_end(void) { hibernate_restore_protection_active = false; } static inline int __must_check hibernate_restore_protect_page(void *page_address) { if (hibernate_restore_protection_active) return set_memory_ro((unsigned long)page_address, 1); return 0; } static inline int hibernate_restore_unprotect_page(void *page_address) { if (hibernate_restore_protection_active) return set_memory_rw((unsigned long)page_address, 1); return 0; } #else static inline void hibernate_restore_protection_begin(void) {} static inline void hibernate_restore_protection_end(void) {} static inline int __must_check hibernate_restore_protect_page(void *page_address) {return 0; } static inline int hibernate_restore_unprotect_page(void *page_address) {return 0; } #endif /* CONFIG_STRICT_KERNEL_RWX && CONFIG_ARCH_HAS_SET_MEMORY */ /* * The calls to set_direct_map_*() should not fail because remapping a page * here means that we only update protection bits in an existing PTE. * It is still worth to have a warning here if something changes and this * will no longer be the case. */ static inline void hibernate_map_page(struct page *page) { if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { int ret = set_direct_map_default_noflush(page); if (ret) pr_warn_once("Failed to remap page\n"); } else { debug_pagealloc_map_pages(page, 1); } } static inline void hibernate_unmap_page(struct page *page) { if (IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { unsigned long addr = (unsigned long)page_address(page); int ret = set_direct_map_invalid_noflush(page); if (ret) pr_warn_once("Failed to remap page\n"); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); } else { debug_pagealloc_unmap_pages(page, 1); } } static int swsusp_page_is_free(struct page *); static void swsusp_set_page_forbidden(struct page *); static void swsusp_unset_page_forbidden(struct page *); /* * Number of bytes to reserve for memory allocations made by device drivers * from their ->freeze() and ->freeze_noirq() callbacks so that they don't * cause image creation to fail (tunable via /sys/power/reserved_size). */ unsigned long reserved_size; void __init hibernate_reserved_size_init(void) { reserved_size = SPARE_PAGES * PAGE_SIZE; } /* * Preferred image size in bytes (tunable via /sys/power/image_size). * When it is set to N, swsusp will do its best to ensure the image * size will not exceed N bytes, but if that is impossible, it will * try to create the smallest image possible. */ unsigned long image_size; void __init hibernate_image_size_init(void) { image_size = ((totalram_pages() * 2) / 5) * PAGE_SIZE; } /* * List of PBEs needed for restoring the pages that were allocated before * the suspend and included in the suspend image, but have also been * allocated by the "resume" kernel, so their contents cannot be written * directly to their "original" page frames. */ struct pbe *restore_pblist; /* struct linked_page is used to build chains of pages */ #define LINKED_PAGE_DATA_SIZE (PAGE_SIZE - sizeof(void *)) struct linked_page { struct linked_page *next; char data[LINKED_PAGE_DATA_SIZE]; } __packed; /* * List of "safe" pages (ie. pages that were not used by the image kernel * before hibernation) that may be used as temporary storage for image kernel * memory contents. */ static struct linked_page *safe_pages_list; /* Pointer to an auxiliary buffer (1 page) */ static void *buffer; #define PG_ANY 0 #define PG_SAFE 1 #define PG_UNSAFE_CLEAR 1 #define PG_UNSAFE_KEEP 0 static unsigned int allocated_unsafe_pages; /** * get_image_page - Allocate a page for a hibernation image. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages that were not used before hibernation (restore only) * * During image restoration, for storing the PBE list and the image data, we can * only use memory pages that do not conflict with the pages used before * hibernation. The "unsafe" pages have PageNosaveFree set and we count them * using allocated_unsafe_pages. * * Each allocated image page is marked as PageNosave and PageNosaveFree so that * swsusp_free() can release it. */ static void *get_image_page(gfp_t gfp_mask, int safe_needed) { void *res; res = (void *)get_zeroed_page(gfp_mask); if (safe_needed) while (res && swsusp_page_is_free(virt_to_page(res))) { /* The page is unsafe, mark it for swsusp_free() */ swsusp_set_page_forbidden(virt_to_page(res)); allocated_unsafe_pages++; res = (void *)get_zeroed_page(gfp_mask); } if (res) { swsusp_set_page_forbidden(virt_to_page(res)); swsusp_set_page_free(virt_to_page(res)); } return res; } static void *__get_safe_page(gfp_t gfp_mask) { if (safe_pages_list) { void *ret = safe_pages_list; safe_pages_list = safe_pages_list->next; memset(ret, 0, PAGE_SIZE); return ret; } return get_image_page(gfp_mask, PG_SAFE); } unsigned long get_safe_page(gfp_t gfp_mask) { return (unsigned long)__get_safe_page(gfp_mask); } static struct page *alloc_image_page(gfp_t gfp_mask) { struct page *page; page = alloc_page(gfp_mask); if (page) { swsusp_set_page_forbidden(page); swsusp_set_page_free(page); } return page; } static void recycle_safe_page(void *page_address) { struct linked_page *lp = page_address; lp->next = safe_pages_list; safe_pages_list = lp; } /** * free_image_page - Free a page allocated for hibernation image. * @addr: Address of the page to free. * @clear_nosave_free: If set, clear the PageNosaveFree bit for the page. * * The page to free should have been allocated by get_image_page() (page flags * set by it are affected). */ static inline void free_image_page(void *addr, int clear_nosave_free) { struct page *page; BUG_ON(!virt_addr_valid(addr)); page = virt_to_page(addr); swsusp_unset_page_forbidden(page); if (clear_nosave_free) swsusp_unset_page_free(page); __free_page(page); } static inline void free_list_of_pages(struct linked_page *list, int clear_page_nosave) { while (list) { struct linked_page *lp = list->next; free_image_page(list, clear_page_nosave); list = lp; } } /* * struct chain_allocator is used for allocating small objects out of * a linked list of pages called 'the chain'. * * The chain grows each time when there is no room for a new object in * the current page. The allocated objects cannot be freed individually. * It is only possible to free them all at once, by freeing the entire * chain. * * NOTE: The chain allocator may be inefficient if the allocated objects * are not much smaller than PAGE_SIZE. */ struct chain_allocator { struct linked_page *chain; /* the chain */ unsigned int used_space; /* total size of objects allocated out of the current page */ gfp_t gfp_mask; /* mask for allocating pages */ int safe_needed; /* if set, only "safe" pages are allocated */ }; static void chain_init(struct chain_allocator *ca, gfp_t gfp_mask, int safe_needed) { ca->chain = NULL; ca->used_space = LINKED_PAGE_DATA_SIZE; ca->gfp_mask = gfp_mask; ca->safe_needed = safe_needed; } static void *chain_alloc(struct chain_allocator *ca, unsigned int size) { void *ret; if (LINKED_PAGE_DATA_SIZE - ca->used_space < size) { struct linked_page *lp; lp = ca->safe_needed ? __get_safe_page(ca->gfp_mask) : get_image_page(ca->gfp_mask, PG_ANY); if (!lp) return NULL; lp->next = ca->chain; ca->chain = lp; ca->used_space = 0; } ret = ca->chain->data + ca->used_space; ca->used_space += size; return ret; } /* * Data types related to memory bitmaps. * * Memory bitmap is a structure consisting of many linked lists of * objects. The main list's elements are of type struct zone_bitmap * and each of them corresponds to one zone. For each zone bitmap * object there is a list of objects of type struct bm_block that * represent each blocks of bitmap in which information is stored. * * struct memory_bitmap contains a pointer to the main list of zone * bitmap objects, a struct bm_position used for browsing the bitmap, * and a pointer to the list of pages used for allocating all of the * zone bitmap objects and bitmap block objects. * * NOTE: It has to be possible to lay out the bitmap in memory * using only allocations of order 0. Additionally, the bitmap is * designed to work with arbitrary number of zones (this is over the * top for now, but let's avoid making unnecessary assumptions ;-). * * struct zone_bitmap contains a pointer to a list of bitmap block * objects and a pointer to the bitmap block object that has been * most recently used for setting bits. Additionally, it contains the * PFNs that correspond to the start and end of the represented zone. * * struct bm_block contains a pointer to the memory page in which * information is stored (in the form of a block of bitmap) * It also contains the pfns that correspond to the start and end of * the represented memory area. * * The memory bitmap is organized as a radix tree to guarantee fast random * access to the bits. There is one radix tree for each zone (as returned * from create_mem_extents). * * One radix tree is represented by one struct mem_zone_bm_rtree. There are * two linked lists for the nodes of the tree, one for the inner nodes and * one for the leaf nodes. The linked leaf nodes are used for fast linear * access of the memory bitmap. * * The struct rtree_node represents one node of the radix tree. */ #define BM_END_OF_MAP (~0UL) #define BM_BITS_PER_BLOCK (PAGE_SIZE * BITS_PER_BYTE) #define BM_BLOCK_SHIFT (PAGE_SHIFT + 3) #define BM_BLOCK_MASK ((1UL << BM_BLOCK_SHIFT) - 1) /* * struct rtree_node is a wrapper struct to link the nodes * of the rtree together for easy linear iteration over * bits and easy freeing */ struct rtree_node { struct list_head list; unsigned long *data; }; /* * struct mem_zone_bm_rtree represents a bitmap used for one * populated memory zone. */ struct mem_zone_bm_rtree { struct list_head list; /* Link Zones together */ struct list_head nodes; /* Radix Tree inner nodes */ struct list_head leaves; /* Radix Tree leaves */ unsigned long start_pfn; /* Zone start page frame */ unsigned long end_pfn; /* Zone end page frame + 1 */ struct rtree_node *rtree; /* Radix Tree Root */ int levels; /* Number of Radix Tree Levels */ unsigned int blocks; /* Number of Bitmap Blocks */ }; /* struct bm_position is used for browsing memory bitmaps */ struct bm_position { struct mem_zone_bm_rtree *zone; struct rtree_node *node; unsigned long node_pfn; unsigned long cur_pfn; int node_bit; }; struct memory_bitmap { struct list_head zones; struct linked_page *p_list; /* list of pages used to store zone bitmap objects and bitmap block objects */ struct bm_position cur; /* most recently used bit position */ }; /* Functions that operate on memory bitmaps */ #define BM_ENTRIES_PER_LEVEL (PAGE_SIZE / sizeof(unsigned long)) #if BITS_PER_LONG == 32 #define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 2) #else #define BM_RTREE_LEVEL_SHIFT (PAGE_SHIFT - 3) #endif #define BM_RTREE_LEVEL_MASK ((1UL << BM_RTREE_LEVEL_SHIFT) - 1) /** * alloc_rtree_node - Allocate a new node and add it to the radix tree. * @gfp_mask: GFP mask for the allocation. * @safe_needed: Get pages not used before hibernation (restore only) * @ca: Pointer to a linked list of pages ("a chain") to allocate from * @list: Radix Tree node to add. * * This function is used to allocate inner nodes as well as the * leave nodes of the radix tree. It also adds the node to the * corresponding linked list passed in by the *list parameter. */ static struct rtree_node *alloc_rtree_node(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, struct list_head *list) { struct rtree_node *node; node = chain_alloc(ca, sizeof(struct rtree_node)); if (!node) return NULL; node->data = get_image_page(gfp_mask, safe_needed); if (!node->data) return NULL; list_add_tail(&node->list, list); return node; } /** * add_rtree_block - Add a new leave node to the radix tree. * * The leave nodes need to be allocated in order to keep the leaves * linked list in order. This is guaranteed by the zone->blocks * counter. */ static int add_rtree_block(struct mem_zone_bm_rtree *zone, gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca) { struct rtree_node *node, *block, **dst; unsigned int levels_needed, block_nr; int i; block_nr = zone->blocks; levels_needed = 0; /* How many levels do we need for this block nr? */ while (block_nr) { levels_needed += 1; block_nr >>= BM_RTREE_LEVEL_SHIFT; } /* Make sure the rtree has enough levels */ for (i = zone->levels; i < levels_needed; i++) { node = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->nodes); if (!node) return -ENOMEM; node->data[0] = (unsigned long)zone->rtree; zone->rtree = node; zone->levels += 1; } /* Allocate new block */ block = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->leaves); if (!block) return -ENOMEM; /* Now walk the rtree to insert the block */ node = zone->rtree; dst = &zone->rtree; block_nr = zone->blocks; for (i = zone->levels; i > 0; i--) { int index; if (!node) { node = alloc_rtree_node(gfp_mask, safe_needed, ca, &zone->nodes); if (!node) return -ENOMEM; *dst = node; } index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); index &= BM_RTREE_LEVEL_MASK; dst = (struct rtree_node **)&((*dst)->data[index]); node = *dst; } zone->blocks += 1; *dst = block; return 0; } static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free); /** * create_zone_bm_rtree - Create a radix tree for one zone. * * Allocated the mem_zone_bm_rtree structure and initializes it. * This function also allocated and builds the radix tree for the * zone. */ static struct mem_zone_bm_rtree *create_zone_bm_rtree(gfp_t gfp_mask, int safe_needed, struct chain_allocator *ca, unsigned long start, unsigned long end) { struct mem_zone_bm_rtree *zone; unsigned int i, nr_blocks; unsigned long pages; pages = end - start; zone = chain_alloc(ca, sizeof(struct mem_zone_bm_rtree)); if (!zone) return NULL; INIT_LIST_HEAD(&zone->nodes); INIT_LIST_HEAD(&zone->leaves); zone->start_pfn = start; zone->end_pfn = end; nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK); for (i = 0; i < nr_blocks; i++) { if (add_rtree_block(zone, gfp_mask, safe_needed, ca)) { free_zone_bm_rtree(zone, PG_UNSAFE_CLEAR); return NULL; } } return zone; } /** * free_zone_bm_rtree - Free the memory of the radix tree. * * Free all node pages of the radix tree. The mem_zone_bm_rtree * structure itself is not freed here nor are the rtree_node * structs. */ static void free_zone_bm_rtree(struct mem_zone_bm_rtree *zone, int clear_nosave_free) { struct rtree_node *node; list_for_each_entry(node, &zone->nodes, list) free_image_page(node->data, clear_nosave_free); list_for_each_entry(node, &zone->leaves, list) free_image_page(node->data, clear_nosave_free); } static void memory_bm_position_reset(struct memory_bitmap *bm) { bm->cur.zone = list_entry(bm->zones.next, struct mem_zone_bm_rtree, list); bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; bm->cur.cur_pfn = BM_END_OF_MAP; bm->cur.node_bit = 0; } static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free); struct mem_extent { struct list_head hook; unsigned long start; unsigned long end; }; /** * free_mem_extents - Free a list of memory extents. * @list: List of extents to free. */ static void free_mem_extents(struct list_head *list) { struct mem_extent *ext, *aux; list_for_each_entry_safe(ext, aux, list, hook) { list_del(&ext->hook); kfree(ext); } } /** * create_mem_extents - Create a list of memory extents. * @list: List to put the extents into. * @gfp_mask: Mask to use for memory allocations. * * The extents represent contiguous ranges of PFNs. */ static int create_mem_extents(struct list_head *list, gfp_t gfp_mask) { struct zone *zone; INIT_LIST_HEAD(list); for_each_populated_zone(zone) { unsigned long zone_start, zone_end; struct mem_extent *ext, *cur, *aux; zone_start = zone->zone_start_pfn; zone_end = zone_end_pfn(zone); list_for_each_entry(ext, list, hook) if (zone_start <= ext->end) break; if (&ext->hook == list || zone_end < ext->start) { /* New extent is necessary */ struct mem_extent *new_ext; new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask); if (!new_ext) { free_mem_extents(list); return -ENOMEM; } new_ext->start = zone_start; new_ext->end = zone_end; list_add_tail(&new_ext->hook, &ext->hook); continue; } /* Merge this zone's range of PFNs with the existing one */ if (zone_start < ext->start) ext->start = zone_start; if (zone_end > ext->end) ext->end = zone_end; /* More merging may be possible */ cur = ext; list_for_each_entry_safe_continue(cur, aux, list, hook) { if (zone_end < cur->start) break; if (zone_end < cur->end) ext->end = cur->end; list_del(&cur->hook); kfree(cur); } } return 0; } /** * memory_bm_create - Allocate memory for a memory bitmap. */ static int memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed) { struct chain_allocator ca; struct list_head mem_extents; struct mem_extent *ext; int error; chain_init(&ca, gfp_mask, safe_needed); INIT_LIST_HEAD(&bm->zones); error = create_mem_extents(&mem_extents, gfp_mask); if (error) return error; list_for_each_entry(ext, &mem_extents, hook) { struct mem_zone_bm_rtree *zone; zone = create_zone_bm_rtree(gfp_mask, safe_needed, &ca, ext->start, ext->end); if (!zone) { error = -ENOMEM; goto Error; } list_add_tail(&zone->list, &bm->zones); } bm->p_list = ca.chain; memory_bm_position_reset(bm); Exit: free_mem_extents(&mem_extents); return error; Error: bm->p_list = ca.chain; memory_bm_free(bm, PG_UNSAFE_CLEAR); goto Exit; } /** * memory_bm_free - Free memory occupied by the memory bitmap. * @bm: Memory bitmap. */ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free) { struct mem_zone_bm_rtree *zone; list_for_each_entry(zone, &bm->zones, list) free_zone_bm_rtree(zone, clear_nosave_free); free_list_of_pages(bm->p_list, clear_nosave_free); INIT_LIST_HEAD(&bm->zones); } /** * memory_bm_find_bit - Find the bit for a given PFN in a memory bitmap. * * Find the bit in memory bitmap @bm that corresponds to the given PFN. * The cur.zone, cur.block and cur.node_pfn members of @bm are updated. * * Walk the radix tree to find the page containing the bit that represents @pfn * and return the position of the bit in @addr and @bit_nr. */ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn, void **addr, unsigned int *bit_nr) { struct mem_zone_bm_rtree *curr, *zone; struct rtree_node *node; int i, block_nr; zone = bm->cur.zone; if (pfn >= zone->start_pfn && pfn < zone->end_pfn) goto zone_found; zone = NULL; /* Find the right zone */ list_for_each_entry(curr, &bm->zones, list) { if (pfn >= curr->start_pfn && pfn < curr->end_pfn) { zone = curr; break; } } if (!zone) return -EFAULT; zone_found: /* * We have found the zone. Now walk the radix tree to find the leaf node * for our PFN. */ /* * If the zone we wish to scan is the current zone and the * pfn falls into the current node then we do not need to walk * the tree. */ node = bm->cur.node; if (zone == bm->cur.zone && ((pfn - zone->start_pfn) & ~BM_BLOCK_MASK) == bm->cur.node_pfn) goto node_found; node = zone->rtree; block_nr = (pfn - zone->start_pfn) >> BM_BLOCK_SHIFT; for (i = zone->levels; i > 0; i--) { int index; index = block_nr >> ((i - 1) * BM_RTREE_LEVEL_SHIFT); index &= BM_RTREE_LEVEL_MASK; BUG_ON(node->data[index] == 0); node = (struct rtree_node *)node->data[index]; } node_found: /* Update last position */ bm->cur.zone = zone; bm->cur.node = node; bm->cur.node_pfn = (pfn - zone->start_pfn) & ~BM_BLOCK_MASK; bm->cur.cur_pfn = pfn; /* Set return values */ *addr = node->data; *bit_nr = (pfn - zone->start_pfn) & BM_BLOCK_MASK; return 0; } static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); set_bit(bit, addr); } static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); if (!error) set_bit(bit, addr); return error; } static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); clear_bit(bit, addr); } static void memory_bm_clear_current(struct memory_bitmap *bm) { int bit; bit = max(bm->cur.node_bit - 1, 0); clear_bit(bit, bm->cur.node->data); } static unsigned long memory_bm_get_current(struct memory_bitmap *bm) { return bm->cur.cur_pfn; } static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; int error; error = memory_bm_find_bit(bm, pfn, &addr, &bit); BUG_ON(error); return test_bit(bit, addr); } static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) { void *addr; unsigned int bit; return !memory_bm_find_bit(bm, pfn, &addr, &bit); } /* * rtree_next_node - Jump to the next leaf node. * * Set the position to the beginning of the next node in the * memory bitmap. This is either the next node in the current * zone's radix tree or the first node in the radix tree of the * next zone. * * Return true if there is a next node, false otherwise. */ static bool rtree_next_node(struct memory_bitmap *bm) { if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) { bm->cur.node = list_entry(bm->cur.node->list.next, struct rtree_node, list); bm->cur.node_pfn += BM_BITS_PER_BLOCK; bm->cur.node_bit = 0; touch_softlockup_watchdog(); return true; } /* No more nodes, goto next zone */ if (!list_is_last(&bm->cur.zone->list, &bm->zones)) { bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list); bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; bm->cur.node_bit = 0; return true; } /* No more zones */ return false; } /** * memory_bm_next_pfn - Find the next set bit in a memory bitmap. * @bm: Memory bitmap. * * Starting from the last returned position this function searches for the next * set bit in @bm and returns the PFN represented by it. If no more bits are * set, BM_END_OF_MAP is returned. * * It is required to run memory_bm_position_reset() before the first call to * this function for the given memory bitmap. */ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm) { unsigned long bits, pfn, pages; int bit; do { pages = bm->cur.zone->end_pfn - bm->cur.zone->start_pfn; bits = min(pages - bm->cur.node_pfn, BM_BITS_PER_BLOCK); bit = find_next_bit(bm->cur.node->data, bits, bm->cur.node_bit); if (bit < bits) { pfn = bm->cur.zone->start_pfn + bm->cur.node_pfn + bit; bm->cur.node_bit = bit + 1; bm->cur.cur_pfn = pfn; return pfn; } } while (rtree_next_node(bm)); bm->cur.cur_pfn = BM_END_OF_MAP; return BM_END_OF_MAP; } /* * This structure represents a range of page frames the contents of which * should not be saved during hibernation. */ struct nosave_region { struct list_head list; unsigned long start_pfn; unsigned long end_pfn; }; static LIST_HEAD(nosave_regions); static void recycle_zone_bm_rtree(struct mem_zone_bm_rtree *zone) { struct rtree_node *node; list_for_each_entry(node, &zone->nodes, list) recycle_safe_page(node->data); list_for_each_entry(node, &zone->leaves, list) recycle_safe_page(node->data); } static void memory_bm_recycle(struct memory_bitmap *bm) { struct mem_zone_bm_rtree *zone; struct linked_page *p_list; list_for_each_entry(zone, &bm->zones, list) recycle_zone_bm_rtree(zone); p_list = bm->p_list; while (p_list) { struct linked_page *lp = p_list; p_list = lp->next; recycle_safe_page(lp); } } /** * register_nosave_region - Register a region of unsaveable memory. * * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; if (start_pfn >= end_pfn) return; if (!list_empty(&nosave_regions)) { /* Try to extend the previous region (they should be sorted) */ region = list_entry(nosave_regions.prev, struct nosave_region, list); if (region->end_pfn == start_pfn) { region->end_pfn = end_pfn; goto Report; } } /* This allocation cannot fail */ region = memblock_alloc_or_panic(sizeof(struct nosave_region), SMP_CACHE_BYTES); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); Report: pr_info("Registered nosave memory: [mem %#010llx-%#010llx]\n", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1); } /* * Set bits in this map correspond to the page frames the contents of which * should not be saved during the suspend. */ static struct memory_bitmap *forbidden_pages_map; /* Set bits in this map correspond to free page frames. */ static struct memory_bitmap *free_pages_map; /* * Each page frame allocated for creating the image is marked by setting the * corresponding bits in forbidden_pages_map and free_pages_map simultaneously */ void swsusp_set_page_free(struct page *page) { if (free_pages_map) memory_bm_set_bit(free_pages_map, page_to_pfn(page)); } static int swsusp_page_is_free(struct page *page) { return free_pages_map ? memory_bm_test_bit(free_pages_map, page_to_pfn(page)) : 0; } void swsusp_unset_page_free(struct page *page) { if (free_pages_map) memory_bm_clear_bit(free_pages_map, page_to_pfn(page)); } static void swsusp_set_page_forbidden(struct page *page) { if (forbidden_pages_map) memory_bm_set_bit(forbidden_pages_map, page_to_pfn(page)); } int swsusp_page_is_forbidden(struct page *page) { return forbidden_pages_map ? memory_bm_test_bit(forbidden_pages_map, page_to_pfn(page)) : 0; } static void swsusp_unset_page_forbidden(struct page *page) { if (forbidden_pages_map) memory_bm_clear_bit(forbidden_pages_map, page_to_pfn(page)); } /** * mark_nosave_pages - Mark pages that should not be saved. * @bm: Memory bitmap. * * Set the bits in @bm that correspond to the page frames the contents of which * should not be saved. */ static void mark_nosave_pages(struct memory_bitmap *bm) { struct nosave_region *region; if (list_empty(&nosave_regions)) return; list_for_each_entry(region, &nosave_regions, list) { unsigned long pfn; pr_debug("Marking nosave pages: [mem %#010llx-%#010llx]\n", (unsigned long long) region->start_pfn << PAGE_SHIFT, ((unsigned long long) region->end_pfn << PAGE_SHIFT) - 1); for_each_valid_pfn(pfn, region->start_pfn, region->end_pfn) { /* * It is safe to ignore the result of * mem_bm_set_bit_check() here, since we won't * touch the PFNs for which the error is * returned anyway. */ mem_bm_set_bit_check(bm, pfn); } } } /** * create_basic_memory_bitmaps - Create bitmaps to hold basic page information. * * Create bitmaps needed for marking page frames that should not be saved and * free page frames. The forbidden_pages_map and free_pages_map pointers are * only modified if everything goes well, because we don't want the bits to be * touched before both bitmaps are set up. */ int create_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; int error; if (forbidden_pages_map && free_pages_map) return 0; else BUG_ON(forbidden_pages_map || free_pages_map); bm1 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm1) return -ENOMEM; error = memory_bm_create(bm1, GFP_KERNEL, PG_ANY); if (error) goto Free_first_object; bm2 = kzalloc(sizeof(struct memory_bitmap), GFP_KERNEL); if (!bm2) goto Free_first_bitmap; error = memory_bm_create(bm2, GFP_KERNEL, PG_ANY); if (error) goto Free_second_object; forbidden_pages_map = bm1; free_pages_map = bm2; mark_nosave_pages(forbidden_pages_map); pr_debug("Basic memory bitmaps created\n"); return 0; Free_second_object: kfree(bm2); Free_first_bitmap: memory_bm_free(bm1, PG_UNSAFE_CLEAR); Free_first_object: kfree(bm1); return -ENOMEM; } /** * free_basic_memory_bitmaps - Free memory bitmaps holding basic information. * * Free memory bitmaps allocated by create_basic_memory_bitmaps(). The * auxiliary pointers are necessary so that the bitmaps themselves are not * referred to while they are being freed. */ void free_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; if (WARN_ON(!(forbidden_pages_map && free_pages_map))) return; bm1 = forbidden_pages_map; bm2 = free_pages_map; forbidden_pages_map = NULL; free_pages_map = NULL; memory_bm_free(bm1, PG_UNSAFE_CLEAR); kfree(bm1); memory_bm_free(bm2, PG_UNSAFE_CLEAR); kfree(bm2); pr_debug("Basic memory bitmaps freed\n"); } static void clear_or_poison_free_page(struct page *page) { if (page_poisoning_enabled_static()) __kernel_poison_pages(page, 1); else if (want_init_on_free()) clear_highpage(page); } void clear_or_poison_free_pages(void) { struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; if (page_poisoning_enabled() || want_init_on_free()) { memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); while (pfn != BM_END_OF_MAP) { if (pfn_valid(pfn)) clear_or_poison_free_page(pfn_to_page(pfn)); pfn = memory_bm_next_pfn(bm); } memory_bm_position_reset(bm); pr_info("free pages cleared after restore\n"); } } /** * snapshot_additional_pages - Estimate the number of extra pages needed. * @zone: Memory zone to carry out the computation for. * * Estimate the number of additional pages needed for setting up a hibernation * image data structures for @zone (usually, the returned value is greater than * the exact number). */ unsigned int snapshot_additional_pages(struct zone *zone) { unsigned int rtree, nodes; rtree = nodes = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); rtree += DIV_ROUND_UP(rtree * sizeof(struct rtree_node), LINKED_PAGE_DATA_SIZE); while (nodes > 1) { nodes = DIV_ROUND_UP(nodes, BM_ENTRIES_PER_LEVEL); rtree += nodes; } return 2 * rtree; } /* * Touch the watchdog for every WD_PAGE_COUNT pages. */ #define WD_PAGE_COUNT (128*1024) static void mark_free_pages(struct zone *zone) { unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT; unsigned long flags; unsigned int order, t; struct page *page; if (zone_is_empty(zone)) return; spin_lock_irqsave(&zone->lock, flags); max_zone_pfn = zone_end_pfn(zone); for_each_valid_pfn(pfn, zone->zone_start_pfn, max_zone_pfn) { page = pfn_to_page(pfn); if (!--page_count) { touch_nmi_watchdog(); page_count = WD_PAGE_COUNT; } if (page_zone(page) != zone) continue; if (!swsusp_page_is_forbidden(page)) swsusp_unset_page_free(page); } for_each_migratetype_order(order, t) { list_for_each_entry(page, &zone->free_area[order].free_list[t], buddy_list) { unsigned long i; pfn = page_to_pfn(page); for (i = 0; i < (1UL << order); i++) { if (!--page_count) { touch_nmi_watchdog(); page_count = WD_PAGE_COUNT; } swsusp_set_page_free(pfn_to_page(pfn + i)); } } } spin_unlock_irqrestore(&zone->lock, flags); } #ifdef CONFIG_HIGHMEM /** * count_free_highmem_pages - Compute the total number of free highmem pages. * * The returned number is system-wide. */ static unsigned int count_free_highmem_pages(void) { struct zone *zone; unsigned int cnt = 0; for_each_populated_zone(zone) if (is_highmem(zone)) cnt += zone_page_state(zone, NR_FREE_PAGES); return cnt; } /** * saveable_highmem_page - Check if a highmem page is saveable. * * Determine whether a highmem page should be included in a hibernation image. * * We should save the page if it isn't Nosave or NosaveFree, or Reserved, * and it isn't part of a free chunk of pages. */ static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_online_page(pfn); if (!page || page_zone(page) != zone) return NULL; BUG_ON(!PageHighMem(page)); if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL; if (PageReserved(page) || PageOffline(page)) return NULL; if (page_is_guard(page)) return NULL; return page; } /** * count_highmem_pages - Compute the total number of saveable highmem pages. */ static unsigned int count_highmem_pages(void) { struct zone *zone; unsigned int n = 0; for_each_populated_zone(zone) { unsigned long pfn, max_zone_pfn; if (!is_highmem(zone)) continue; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (saveable_highmem_page(zone, pfn)) n++; } return n; } #endif /* CONFIG_HIGHMEM */ /** * saveable_page - Check if the given page is saveable. * * Determine whether a non-highmem page should be included in a hibernation * image. * * We should save the page if it isn't Nosave, and is not in the range * of pages statically defined as 'unsaveable', and it isn't part of * a free chunk of pages. */ static struct page *saveable_page(struct zone *zone, unsigned long pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_online_page(pfn); if (!page || page_zone(page) != zone) return NULL; BUG_ON(PageHighMem(page)); if (swsusp_page_is_forbidden(page) || swsusp_page_is_free(page)) return NULL; if (PageOffline(page)) return NULL; if (PageReserved(page) && (!kernel_page_present(page) || pfn_is_nosave(pfn))) return NULL; if (page_is_guard(page)) return NULL; return page; } /** * count_data_pages - Compute the total number of saveable non-highmem pages. */ static unsigned int count_data_pages(void) { struct zone *zone; unsigned long pfn, max_zone_pfn; unsigned int n = 0; for_each_populated_zone(zone) { if (is_highmem(zone)) continue; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (saveable_page(zone, pfn)) n++; } return n; } /* * This is needed, because copy_page and memcpy are not usable for copying * task structs. Returns true if the page was filled with only zeros, * otherwise false. */ static inline bool do_copy_page(long *dst, long *src) { long z = 0; int n; for (n = PAGE_SIZE / sizeof(long); n; n--) { z |= *src; *dst++ = *src++; } return !z; } /** * safe_copy_page - Copy a page in a safe way. * * Check if the page we are going to copy is marked as present in the kernel * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present() * always returns 'true'. Returns true if the page was entirely composed of * zeros, otherwise it will return false. */ static bool safe_copy_page(void *dst, struct page *s_page) { bool zeros_only; if (kernel_page_present(s_page)) { zeros_only = do_copy_page(dst, page_address(s_page)); } else { hibernate_map_page(s_page); zeros_only = do_copy_page(dst, page_address(s_page)); hibernate_unmap_page(s_page); } return zeros_only; } #ifdef CONFIG_HIGHMEM static inline struct page *page_is_saveable(struct zone *zone, unsigned long pfn) { return is_highmem(zone) ? saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn); } static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) { struct page *s_page, *d_page; void *src, *dst; bool zeros_only; s_page = pfn_to_page(src_pfn); d_page = pfn_to_page(dst_pfn); if (PageHighMem(s_page)) { src = kmap_local_page(s_page); dst = kmap_local_page(d_page); zeros_only = do_copy_page(dst, src); kunmap_local(dst); kunmap_local(src); } else { if (PageHighMem(d_page)) { /* * The page pointed to by src may contain some kernel * data modified by kmap_atomic() */ zeros_only = safe_copy_page(buffer, s_page); dst = kmap_local_page(d_page); copy_page(dst, buffer); kunmap_local(dst); } else { zeros_only = safe_copy_page(page_address(d_page), s_page); } } return zeros_only; } #else #define page_is_saveable(zone, pfn) saveable_page(zone, pfn) static inline int copy_data_page(unsigned long dst_pfn, unsigned long src_pfn) { return safe_copy_page(page_address(pfn_to_page(dst_pfn)), pfn_to_page(src_pfn)); } #endif /* CONFIG_HIGHMEM */ /* * Copy data pages will copy all pages into pages pulled from the copy_bm. * If a page was entirely filled with zeros it will be marked in the zero_bm. * * Returns the number of pages copied. */ static unsigned long copy_data_pages(struct memory_bitmap *copy_bm, struct memory_bitmap *orig_bm, struct memory_bitmap *zero_bm) { unsigned long copied_pages = 0; struct zone *zone; unsigned long pfn, copy_pfn; for_each_populated_zone(zone) { unsigned long max_zone_pfn; mark_free_pages(zone); max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) if (page_is_saveable(zone, pfn)) memory_bm_set_bit(orig_bm, pfn); } memory_bm_position_reset(orig_bm); memory_bm_position_reset(copy_bm); copy_pfn = memory_bm_next_pfn(copy_bm); for (;;) { pfn = memory_bm_next_pfn(orig_bm); if (unlikely(pfn == BM_END_OF_MAP)) break; if (copy_data_page(copy_pfn, pfn)) { memory_bm_set_bit(zero_bm, pfn); /* Use this copy_pfn for a page that is not full of zeros */ continue; } copied_pages++; copy_pfn = memory_bm_next_pfn(copy_bm); } return copied_pages; } /* Total number of image pages */ static unsigned int nr_copy_pages; /* Number of pages needed for saving the original pfns of the image pages */ static unsigned int nr_meta_pages; /* Number of zero pages */ static unsigned int nr_zero_pages; /* * Numbers of normal and highmem page frames allocated for hibernation image * before suspending devices. */ static unsigned int alloc_normal, alloc_highmem; /* * Memory bitmap used for marking saveable pages (during hibernation) or * hibernation image pages (during restore) */ static struct memory_bitmap orig_bm; /* * Memory bitmap used during hibernation for marking allocated page frames that * will contain copies of saveable pages. During restore it is initially used * for marking hibernation image pages, but then the set bits from it are * duplicated in @orig_bm and it is released. On highmem systems it is next * used for marking "safe" highmem pages, but it has to be reinitialized for * this purpose. */ static struct memory_bitmap copy_bm; /* Memory bitmap which tracks which saveable pages were zero filled. */ static struct memory_bitmap zero_bm; /** * swsusp_free - Free pages allocated for hibernation image. * * Image pages are allocated before snapshot creation, so they need to be * released after resume. */ void swsusp_free(void) { unsigned long fb_pfn, fr_pfn; if (!forbidden_pages_map || !free_pages_map) goto out; memory_bm_position_reset(forbidden_pages_map); memory_bm_position_reset(free_pages_map); loop: fr_pfn = memory_bm_next_pfn(free_pages_map); fb_pfn = memory_bm_next_pfn(forbidden_pages_map); /* * Find the next bit set in both bitmaps. This is guaranteed to * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP. */ do { if (fb_pfn < fr_pfn) fb_pfn = memory_bm_next_pfn(forbidden_pages_map); if (fr_pfn < fb_pfn) fr_pfn = memory_bm_next_pfn(free_pages_map); } while (fb_pfn != fr_pfn); if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) { struct page *page = pfn_to_page(fr_pfn); memory_bm_clear_current(forbidden_pages_map); memory_bm_clear_current(free_pages_map); hibernate_restore_unprotect_page(page_address(page)); __free_page(page); goto loop; } out: nr_copy_pages = 0; nr_meta_pages = 0; nr_zero_pages = 0; restore_pblist = NULL; buffer = NULL; alloc_normal = 0; alloc_highmem = 0; hibernate_restore_protection_end(); } /* Helper functions used for the shrinking of memory. */ #define GFP_IMAGE (GFP_KERNEL | __GFP_NOWARN) /** * preallocate_image_pages - Allocate a number of pages for hibernation image. * @nr_pages: Number of page frames to allocate. * @mask: GFP flags to use for the allocation. * * Return value: Number of page frames actually allocated */ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask) { unsigned long nr_alloc = 0; while (nr_pages > 0) { struct page *page; page = alloc_image_page(mask); if (!page) break; memory_bm_set_bit(©_bm, page_to_pfn(page)); if (PageHighMem(page)) alloc_highmem++; else alloc_normal++; nr_pages--; nr_alloc++; } return nr_alloc; } static unsigned long preallocate_image_memory(unsigned long nr_pages, unsigned long avail_normal) { unsigned long alloc; if (avail_normal <= alloc_normal) return 0; alloc = avail_normal - alloc_normal; if (nr_pages < alloc) alloc = nr_pages; return preallocate_image_pages(alloc, GFP_IMAGE); } #ifdef CONFIG_HIGHMEM static unsigned long preallocate_image_highmem(unsigned long nr_pages) { return preallocate_image_pages(nr_pages, GFP_IMAGE | __GFP_HIGHMEM); } /** * __fraction - Compute (an approximation of) x * (multiplier / base). */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { return div64_u64(x * multiplier, base); } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, unsigned long highmem, unsigned long total) { unsigned long alloc = __fraction(nr_pages, highmem, total); return preallocate_image_pages(alloc, GFP_IMAGE | __GFP_HIGHMEM); } #else /* CONFIG_HIGHMEM */ static inline unsigned long preallocate_image_highmem(unsigned long nr_pages) { return 0; } static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, unsigned long highmem, unsigned long total) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * free_unnecessary_pages - Release preallocated pages not needed for the image. */ static unsigned long free_unnecessary_pages(void) { unsigned long save, to_free_normal, to_free_highmem, free; save = count_data_pages(); if (alloc_normal >= save) { to_free_normal = alloc_normal - save; save = 0; } else { to_free_normal = 0; save -= alloc_normal; } save += count_highmem_pages(); if (alloc_highmem >= save) { to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; save -= alloc_highmem; if (to_free_normal > save) to_free_normal -= save; else to_free_normal = 0; } free = to_free_normal + to_free_highmem; memory_bm_position_reset(©_bm); while (to_free_normal > 0 || to_free_highmem > 0) { unsigned long pfn = memory_bm_next_pfn(©_bm); struct page *page = pfn_to_page(pfn); if (PageHighMem(page)) { if (!to_free_highmem) continue; to_free_highmem--; alloc_highmem--; } else { if (!to_free_normal) continue; to_free_normal--; alloc_normal--; } memory_bm_clear_bit(©_bm, pfn); swsusp_unset_page_forbidden(page); swsusp_unset_page_free(page); __free_page(page); } return free; } /** * minimum_image_size - Estimate the minimum acceptable size of an image. * @saveable: Number of saveable pages in the system. * * We want to avoid attempting to free too much memory too hard, so estimate the * minimum acceptable size of a hibernation image to use as the lower limit for * preallocating memory. * * We assume that the minimum image size should be proportional to * * [number of saveable pages] - [number of pages that can be freed in theory] * * where the second term is the sum of (1) reclaimable slab pages, (2) active * and (3) inactive anonymous pages, (4) active and (5) inactive file pages. */ static unsigned long minimum_image_size(unsigned long saveable) { unsigned long size; size = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_ACTIVE_ANON) + global_node_page_state(NR_INACTIVE_ANON) + global_node_page_state(NR_ACTIVE_FILE) + global_node_page_state(NR_INACTIVE_FILE); return saveable <= size ? 0 : saveable - size; } /** * hibernate_preallocate_memory - Preallocate memory for hibernation image. * * To create a hibernation image it is necessary to make a copy of every page * frame in use. We also need a number of page frames to be free during * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2 * - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * * If image_size is set below the number following from the above formula, * the preallocation of memory is continued until the total number of saveable * pages in the system is below the requested image size or the minimum * acceptable image size returned by minimum_image_size(), whichever is greater. */ int hibernate_preallocate_memory(void) { struct zone *zone; unsigned long saveable, size, max_size, count, highmem, pages = 0; unsigned long alloc, save_highmem, pages_highmem, avail_normal; ktime_t start, stop; int error; pr_info("Preallocating image memory\n"); start = ktime_get(); error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate original bitmap\n"); goto err_out; } error = memory_bm_create(©_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate copy bitmap\n"); goto err_out; } error = memory_bm_create(&zero_bm, GFP_IMAGE, PG_ANY); if (error) { pr_err("Cannot allocate zero bitmap\n"); goto err_out; } alloc_normal = 0; alloc_highmem = 0; nr_zero_pages = 0; /* Count the number of saveable data pages. */ save_highmem = count_highmem_pages(); saveable = count_data_pages(); /* * Compute the total number of page frames we can use (count) and the * number of pages needed for image metadata (size). */ count = saveable; saveable += save_highmem; highmem = save_highmem; size = 0; for_each_populated_zone(zone) { size += snapshot_additional_pages(zone); if (is_highmem(zone)) highmem += zone_page_state(zone, NR_FREE_PAGES); else count += zone_page_state(zone, NR_FREE_PAGES); } avail_normal = count; count += highmem; count -= totalreserve_pages; /* Compute the maximum number of saveable pages to leave in memory. */ max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); /* Compute the desired number of image pages specified by image_size. */ size = DIV_ROUND_UP(image_size, PAGE_SIZE); if (size > max_size) size = max_size; /* * If the desired number of image pages is at least as large as the * current number of saveable pages in memory, allocate page frames for * the image and we're done. */ if (size >= saveable) { pages = preallocate_image_highmem(save_highmem); pages += preallocate_image_memory(saveable - pages, avail_normal); goto out; } /* Estimate the minimum size of the image. */ pages = minimum_image_size(saveable); /* * To avoid excessive pressure on the normal zone, leave room in it to * accommodate an image of the minimum size (unless it's already too * small, in which case don't preallocate pages from it at all). */ if (avail_normal > pages) avail_normal -= pages; else avail_normal = 0; if (size < pages) size = min_t(unsigned long, pages, max_size); /* * Let the memory management subsystem know that we're going to need a * large number of page frames to allocate and make it free some memory. * NOTE: If this is not done, performance will be hurt badly in some * test cases. */ shrink_all_memory(saveable - size); /* * The number of saveable pages in memory was too high, so apply some * pressure to decrease it. First, make room for the largest possible * image and fail if that doesn't work. Next, try to decrease the size * of the image as much as indicated by 'size' using allocations from * highmem and non-highmem zones separately. */ pages_highmem = preallocate_image_highmem(highmem / 2); alloc = count - max_size; if (alloc > pages_highmem) alloc -= pages_highmem; else alloc = 0; pages = preallocate_image_memory(alloc, avail_normal); if (pages < alloc) { /* We have exhausted non-highmem pages, try highmem. */ alloc -= pages; pages += pages_highmem; pages_highmem = preallocate_image_highmem(alloc); if (pages_highmem < alloc) { pr_err("Image allocation is %lu pages short\n", alloc - pages_highmem); goto err_out; } pages += pages_highmem; /* * size is the desired number of saveable pages to leave in * memory, so try to preallocate (all memory - size) pages. */ alloc = (count - pages) - size; pages += preallocate_image_highmem(alloc); } else { /* * There are approximately max_size saveable pages at this point * and we want to reduce this number down to size. */ alloc = max_size - size; size = preallocate_highmem_fraction(alloc, highmem, count); pages_highmem += size; alloc -= size; size = preallocate_image_memory(alloc, avail_normal); pages_highmem += preallocate_image_highmem(alloc - size); pages += pages_highmem + size; } /* * We only need as many page frames for the image as there are saveable * pages in memory, but we have allocated more. Release the excessive * ones now. */ pages -= free_unnecessary_pages(); out: stop = ktime_get(); pr_info("Allocated %lu pages for snapshot\n", pages); swsusp_show_speed(start, stop, pages, "Allocated"); return 0; err_out: swsusp_free(); return -ENOMEM; } #ifdef CONFIG_HIGHMEM /** * count_pages_for_highmem - Count non-highmem pages needed for copying highmem. * * Compute the number of non-highmem pages that will be necessary for creating * copies of highmem pages. */ static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { unsigned int free_highmem = count_free_highmem_pages() + alloc_highmem; if (free_highmem >= nr_highmem) nr_highmem = 0; else nr_highmem -= free_highmem; return nr_highmem; } #else static unsigned int count_pages_for_highmem(unsigned int nr_highmem) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * enough_free_mem - Check if there is enough free memory for the image. */ static int enough_free_mem(unsigned int nr_pages, unsigned int nr_highmem) { struct zone *zone; unsigned int free = alloc_normal; for_each_populated_zone(zone) if (!is_highmem(zone)) free += zone_page_state(zone, NR_FREE_PAGES); nr_pages += count_pages_for_highmem(nr_highmem); pr_debug("Normal pages needed: %u + %u, available pages: %u\n", nr_pages, PAGES_FOR_IO, free); return free > nr_pages + PAGES_FOR_IO; } #ifdef CONFIG_HIGHMEM /** * get_highmem_buffer - Allocate a buffer for highmem pages. * * If there are some highmem pages in the hibernation image, we may need a * buffer to copy them and/or load their data. */ static inline int get_highmem_buffer(int safe_needed) { buffer = get_image_page(GFP_ATOMIC, safe_needed); return buffer ? 0 : -ENOMEM; } /** * alloc_highmem_pages - Allocate some highmem pages for the image. * * Try to allocate as many pages as needed, but if the number of free highmem * pages is less than that, allocate them all. */ static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem) { unsigned int to_alloc = count_free_highmem_pages(); if (to_alloc > nr_highmem) to_alloc = nr_highmem; nr_highmem -= to_alloc; while (to_alloc-- > 0) { struct page *page; page = alloc_image_page(__GFP_HIGHMEM|__GFP_KSWAPD_RECLAIM); memory_bm_set_bit(bm, page_to_pfn(page)); } return nr_highmem; } #else static inline int get_highmem_buffer(int safe_needed) { return 0; } static inline unsigned int alloc_highmem_pages(struct memory_bitmap *bm, unsigned int n) { return 0; } #endif /* CONFIG_HIGHMEM */ /** * swsusp_alloc - Allocate memory for hibernation image. * * We first try to allocate as many highmem pages as there are * saveable highmem pages in the system. If that fails, we allocate * non-highmem pages for the copies of the remaining highmem ones. * * In this approach it is likely that the copies of highmem pages will * also be located in the high memory, because of the way in which * copy_data_pages() works. */ static int swsusp_alloc(struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { if (nr_highmem > 0) { if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) { nr_highmem -= alloc_highmem; nr_pages += alloc_highmem_pages(copy_bm, nr_highmem); } } if (nr_pages > alloc_normal) { nr_pages -= alloc_normal; while (nr_pages-- > 0) { struct page *page; page = alloc_image_page(GFP_ATOMIC); if (!page) goto err_out; memory_bm_set_bit(copy_bm, page_to_pfn(page)); } } return 0; err_out: swsusp_free(); return -ENOMEM; } asmlinkage __visible int swsusp_save(void) { unsigned int nr_pages, nr_highmem; pr_info("Creating image:\n"); drain_local_pages(NULL); nr_pages = count_data_pages(); nr_highmem = count_highmem_pages(); pr_info("Need to copy %u pages\n", nr_pages + nr_highmem); if (!enough_free_mem(nr_pages, nr_highmem)) { pr_err("Not enough free memory\n"); return -ENOMEM; } if (swsusp_alloc(©_bm, nr_pages, nr_highmem)) { pr_err("Memory allocation failed\n"); return -ENOMEM; } /* * During allocating of suspend pagedir, new cold pages may appear. * Kill them. */ drain_local_pages(NULL); nr_copy_pages = copy_data_pages(©_bm, &orig_bm, &zero_bm); /* * End of critical section. From now on, we can write to memory, * but we should not touch disk. This specially means we must _not_ * touch swap space! Except we must write out our image of course. */ nr_pages += nr_highmem; /* We don't actually copy the zero pages */ nr_zero_pages = nr_pages - nr_copy_pages; nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); pr_info("Image created (%d pages copied, %d zero pages)\n", nr_copy_pages, nr_zero_pages); return 0; } #ifndef CONFIG_ARCH_HIBERNATION_HEADER static int init_header_complete(struct swsusp_info *info) { memcpy(&info->uts, init_utsname(), sizeof(struct new_utsname)); info->version_code = LINUX_VERSION_CODE; return 0; } static const char *check_image_kernel(struct swsusp_info *info) { if (info->version_code != LINUX_VERSION_CODE) return "kernel version"; if (strcmp(info->uts.sysname, init_utsname()->sysname)) return "system type"; if (strcmp(info->uts.release, init_utsname()->release)) return "kernel release"; if (strcmp(info->uts.version, init_utsname()->version)) return "version"; if (strcmp(info->uts.machine, init_utsname()->machine)) return "machine"; return NULL; } #endif /* CONFIG_ARCH_HIBERNATION_HEADER */ unsigned long snapshot_get_image_size(void) { return nr_copy_pages + nr_meta_pages + 1; } static int init_header(struct swsusp_info *info) { memset(info, 0, sizeof(struct swsusp_info)); info->num_physpages = get_num_physpages(); info->image_pages = nr_copy_pages; info->pages = snapshot_get_image_size(); info->size = info->pages; info->size <<= PAGE_SHIFT; return init_header_complete(info); } #define ENCODED_PFN_ZERO_FLAG ((unsigned long)1 << (BITS_PER_LONG - 1)) #define ENCODED_PFN_MASK (~ENCODED_PFN_ZERO_FLAG) /** * pack_pfns - Prepare PFNs for saving. * @bm: Memory bitmap. * @buf: Memory buffer to store the PFNs in. * @zero_bm: Memory bitmap containing PFNs of zero pages. * * PFNs corresponding to set bits in @bm are stored in the area of memory * pointed to by @buf (1 page at a time). Pages which were filled with only * zeros will have the highest bit set in the packed format to distinguish * them from PFNs which will be contained in the image file. */ static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { int j; for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { buf[j] = memory_bm_next_pfn(bm); if (unlikely(buf[j] == BM_END_OF_MAP)) break; if (memory_bm_test_bit(zero_bm, buf[j])) buf[j] |= ENCODED_PFN_ZERO_FLAG; } } /** * snapshot_read_next - Get the address to read the next image page from. * @handle: Snapshot handle to be used for the reading. * * On the first call, @handle should point to a zeroed snapshot_handle * structure. The structure gets populated then and a pointer to it should be * passed to this function every next time. * * On success, the function returns a positive number. Then, the caller * is allowed to read up to the returned number of bytes from the memory * location computed by the data_of() macro. * * The function returns 0 to indicate the end of the data stream condition, * and negative numbers are returned on errors. If that happens, the structure * pointed to by @handle is not updated and should not be used any more. */ int snapshot_read_next(struct snapshot_handle *handle) { if (handle->cur > nr_meta_pages + nr_copy_pages) return 0; if (!buffer) { /* This makes the buffer be freed by swsusp_free() */ buffer = get_image_page(GFP_ATOMIC, PG_ANY); if (!buffer) return -ENOMEM; } if (!handle->cur) { int error; error = init_header((struct swsusp_info *)buffer); if (error) return error; handle->buffer = buffer; memory_bm_position_reset(&orig_bm); memory_bm_position_reset(©_bm); } else if (handle->cur <= nr_meta_pages) { clear_page(buffer); pack_pfns(buffer, &orig_bm, &zero_bm); } else { struct page *page; page = pfn_to_page(memory_bm_next_pfn(©_bm)); if (PageHighMem(page)) { /* * Highmem pages are copied to the buffer, * because we can't return with a kmapped * highmem page (we may not be called again). */ void *kaddr; kaddr = kmap_local_page(page); copy_page(buffer, kaddr); kunmap_local(kaddr); handle->buffer = buffer; } else { handle->buffer = page_address(page); } } handle->cur++; return PAGE_SIZE; } static void duplicate_memory_bitmap(struct memory_bitmap *dst, struct memory_bitmap *src) { unsigned long pfn; memory_bm_position_reset(src); pfn = memory_bm_next_pfn(src); while (pfn != BM_END_OF_MAP) { memory_bm_set_bit(dst, pfn); pfn = memory_bm_next_pfn(src); } } /** * mark_unsafe_pages - Mark pages that were used before hibernation. * * Mark the pages that cannot be used for storing the image during restoration, * because they conflict with the pages that had been used before hibernation. */ static void mark_unsafe_pages(struct memory_bitmap *bm) { unsigned long pfn; /* Clear the "free"/"unsafe" bit for all PFNs */ memory_bm_position_reset(free_pages_map); pfn = memory_bm_next_pfn(free_pages_map); while (pfn != BM_END_OF_MAP) { memory_bm_clear_current(free_pages_map); pfn = memory_bm_next_pfn(free_pages_map); } /* Mark pages that correspond to the "original" PFNs as "unsafe" */ duplicate_memory_bitmap(free_pages_map, bm); allocated_unsafe_pages = 0; } static int check_header(struct swsusp_info *info) { const char *reason; reason = check_image_kernel(info); if (!reason && info->num_physpages != get_num_physpages()) reason = "memory size"; if (reason) { pr_err("Image mismatch: %s\n", reason); return -EPERM; } return 0; } /** * load_header - Check the image header and copy the data from it. */ static int load_header(struct swsusp_info *info) { int error; restore_pblist = NULL; error = check_header(info); if (!error) { nr_copy_pages = info->image_pages; nr_meta_pages = info->pages - info->image_pages - 1; } return error; } /** * unpack_orig_pfns - Set bits corresponding to given PFNs in a memory bitmap. * @bm: Memory bitmap. * @buf: Area of memory containing the PFNs. * @zero_bm: Memory bitmap with the zero PFNs marked. * * For each element of the array pointed to by @buf (1 page at a time), set the * corresponding bit in @bm. If the page was originally populated with only * zeros then a corresponding bit will also be set in @zero_bm. */ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { unsigned long decoded_pfn; bool zero; int j; for (j = 0; j < PAGE_SIZE / sizeof(long); j++) { if (unlikely(buf[j] == BM_END_OF_MAP)) break; zero = !!(buf[j] & ENCODED_PFN_ZERO_FLAG); decoded_pfn = buf[j] & ENCODED_PFN_MASK; if (pfn_valid(decoded_pfn) && memory_bm_pfn_present(bm, decoded_pfn)) { memory_bm_set_bit(bm, decoded_pfn); if (zero) { memory_bm_set_bit(zero_bm, decoded_pfn); nr_zero_pages++; } } else { if (!pfn_valid(decoded_pfn)) pr_err(FW_BUG "Memory map mismatch at 0x%llx after hibernation\n", (unsigned long long)PFN_PHYS(decoded_pfn)); return -EFAULT; } } return 0; } #ifdef CONFIG_HIGHMEM /* * struct highmem_pbe is used for creating the list of highmem pages that * should be restored atomically during the resume from disk, because the page * frames they have occupied before the suspend are in use. */ struct highmem_pbe { struct page *copy_page; /* data is here now */ struct page *orig_page; /* data was here before the suspend */ struct highmem_pbe *next; }; /* * List of highmem PBEs needed for restoring the highmem pages that were * allocated before the suspend and included in the suspend image, but have * also been allocated by the "resume" kernel, so their contents cannot be * written directly to their "original" page frames. */ static struct highmem_pbe *highmem_pblist; /** * count_highmem_image_pages - Compute the number of highmem pages in the image. * @bm: Memory bitmap. * * The bits in @bm that correspond to image pages are assumed to be set. */ static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { unsigned long pfn; unsigned int cnt = 0; memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); while (pfn != BM_END_OF_MAP) { if (PageHighMem(pfn_to_page(pfn))) cnt++; pfn = memory_bm_next_pfn(bm); } return cnt; } static unsigned int safe_highmem_pages; static struct memory_bitmap *safe_highmem_bm; /** * prepare_highmem_image - Allocate memory for loading highmem data from image. * @bm: Pointer to an uninitialized memory bitmap structure. * @nr_highmem_p: Pointer to the number of highmem image pages. * * Try to allocate as many highmem pages as there are highmem image pages * (@nr_highmem_p points to the variable containing the number of highmem image * pages). The pages that are "safe" (ie. will not be overwritten when the * hibernation image is restored entirely) have the corresponding bits set in * @bm (it must be uninitialized). * * NOTE: This function should not be called if there are no highmem image pages. */ static int prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) { unsigned int to_alloc; if (memory_bm_create(bm, GFP_ATOMIC, PG_SAFE)) return -ENOMEM; if (get_highmem_buffer(PG_SAFE)) return -ENOMEM; to_alloc = count_free_highmem_pages(); if (to_alloc > *nr_highmem_p) to_alloc = *nr_highmem_p; else *nr_highmem_p = to_alloc; safe_highmem_pages = 0; while (to_alloc-- > 0) { struct page *page; page = alloc_page(__GFP_HIGHMEM); if (!swsusp_page_is_free(page)) { /* The page is "safe", set its bit the bitmap */ memory_bm_set_bit(bm, page_to_pfn(page)); safe_highmem_pages++; } /* Mark the page as allocated */ swsusp_set_page_forbidden(page); swsusp_set_page_free(page); } memory_bm_position_reset(bm); safe_highmem_bm = bm; return 0; } static struct page *last_highmem_page; /** * get_highmem_page_buffer - Prepare a buffer to store a highmem image page. * * For a given highmem image page get a buffer that suspend_write_next() should * return to its caller to write to. * * If the page is to be saved to its "original" page frame or a copy of * the page is to be made in the highmem, @buffer is returned. Otherwise, * the copy of the page is to be made in normal memory, so the address of * the copy is returned. * * If @buffer is returned, the caller of suspend_write_next() will write * the page's contents to @buffer, so they will have to be copied to the * right location on the next call to suspend_write_next() and it is done * with the help of copy_last_highmem_page(). For this purpose, if * @buffer is returned, @last_highmem_page is set to the page to which * the data will have to be copied from @buffer. */ static void *get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) { struct highmem_pbe *pbe; void *kaddr; if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) { /* * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ last_highmem_page = page; return buffer; } /* * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct highmem_pbe)); if (!pbe) { swsusp_free(); return ERR_PTR(-ENOMEM); } pbe->orig_page = page; if (safe_highmem_pages > 0) { struct page *tmp; /* Copy of the page will be stored in high memory */ kaddr = buffer; tmp = pfn_to_page(memory_bm_next_pfn(safe_highmem_bm)); safe_highmem_pages--; last_highmem_page = tmp; pbe->copy_page = tmp; } else { /* Copy of the page will be stored in normal memory */ kaddr = __get_safe_page(ca->gfp_mask); if (!kaddr) return ERR_PTR(-ENOMEM); pbe->copy_page = virt_to_page(kaddr); } pbe->next = highmem_pblist; highmem_pblist = pbe; return kaddr; } /** * copy_last_highmem_page - Copy most the most recent highmem image page. * * Copy the contents of a highmem image from @buffer, where the caller of * snapshot_write_next() has stored them, to the right location represented by * @last_highmem_page . */ static void copy_last_highmem_page(void) { if (last_highmem_page) { void *dst; dst = kmap_local_page(last_highmem_page); copy_page(dst, buffer); kunmap_local(dst); last_highmem_page = NULL; } } static inline int last_highmem_page_copied(void) { return !last_highmem_page; } static inline void free_highmem_data(void) { if (safe_highmem_bm) memory_bm_free(safe_highmem_bm, PG_UNSAFE_CLEAR); if (buffer) free_image_page(buffer, PG_UNSAFE_CLEAR); } #else static unsigned int count_highmem_image_pages(struct memory_bitmap *bm) { return 0; } static inline int prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p) { return 0; } static inline void *get_highmem_page_buffer(struct page *page, struct chain_allocator *ca) { return ERR_PTR(-EINVAL); } static inline void copy_last_highmem_page(void) {} static inline int last_highmem_page_copied(void) { return 1; } static inline void free_highmem_data(void) {} #endif /* CONFIG_HIGHMEM */ #define PBES_PER_LINKED_PAGE (LINKED_PAGE_DATA_SIZE / sizeof(struct pbe)) /** * prepare_image - Make room for loading hibernation image. * @new_bm: Uninitialized memory bitmap structure. * @bm: Memory bitmap with unsafe pages marked. * @zero_bm: Memory bitmap containing the zero pages. * * Use @bm to mark the pages that will be overwritten in the process of * restoring the system memory state from the suspend image ("unsafe" pages) * and allocate memory for the image. * * The idea is to allocate a new memory bitmap first and then allocate * as many pages as needed for image data, but without specifying what those * pages will be used for just yet. Instead, we mark them all as allocated and * create a lists of "safe" pages to be used later. On systems with high * memory a list of "safe" highmem pages is created too. * * Because it was not known which pages were unsafe when @zero_bm was created, * make a copy of it and recreate it within safe pages. */ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm, struct memory_bitmap *zero_bm) { unsigned int nr_pages, nr_highmem; struct memory_bitmap tmp; struct linked_page *lp; int error; /* If there is no highmem, the buffer will not be necessary */ free_image_page(buffer, PG_UNSAFE_CLEAR); buffer = NULL; nr_highmem = count_highmem_image_pages(bm); mark_unsafe_pages(bm); error = memory_bm_create(new_bm, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(new_bm, bm); memory_bm_free(bm, PG_UNSAFE_KEEP); /* Make a copy of zero_bm so it can be created in safe pages */ error = memory_bm_create(&tmp, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(&tmp, zero_bm); memory_bm_free(zero_bm, PG_UNSAFE_KEEP); /* Recreate zero_bm in safe pages */ error = memory_bm_create(zero_bm, GFP_ATOMIC, PG_SAFE); if (error) goto Free; duplicate_memory_bitmap(zero_bm, &tmp); memory_bm_free(&tmp, PG_UNSAFE_CLEAR); /* At this point zero_bm is in safe pages and it can be used for restoring. */ if (nr_highmem > 0) { error = prepare_highmem_image(bm, &nr_highmem); if (error) goto Free; } /* * Reserve some safe pages for potential later use. * * NOTE: This way we make sure there will be enough safe pages for the * chain_alloc() in get_buffer(). It is a bit wasteful, but * nr_copy_pages cannot be greater than 50% of the memory anyway. * * nr_copy_pages cannot be less than allocated_unsafe_pages too. */ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages; nr_pages = DIV_ROUND_UP(nr_pages, PBES_PER_LINKED_PAGE); while (nr_pages > 0) { lp = get_image_page(GFP_ATOMIC, PG_SAFE); if (!lp) { error = -ENOMEM; goto Free; } lp->next = safe_pages_list; safe_pages_list = lp; nr_pages--; } /* Preallocate memory for the image */ nr_pages = (nr_zero_pages + nr_copy_pages) - nr_highmem - allocated_unsafe_pages; while (nr_pages > 0) { lp = (struct linked_page *)get_zeroed_page(GFP_ATOMIC); if (!lp) { error = -ENOMEM; goto Free; } if (!swsusp_page_is_free(virt_to_page(lp))) { /* The page is "safe", add it to the list */ lp->next = safe_pages_list; safe_pages_list = lp; } /* Mark the page as allocated */ swsusp_set_page_forbidden(virt_to_page(lp)); swsusp_set_page_free(virt_to_page(lp)); nr_pages--; } return 0; Free: swsusp_free(); return error; } /** * get_buffer - Get the address to store the next image data page. * * Get the address that snapshot_write_next() should return to its caller to * write to. */ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) { struct pbe *pbe; struct page *page; unsigned long pfn = memory_bm_next_pfn(bm); if (pfn == BM_END_OF_MAP) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); if (PageHighMem(page)) return get_highmem_page_buffer(page, ca); if (swsusp_page_is_forbidden(page) && swsusp_page_is_free(page)) /* * We have allocated the "original" page frame and we can * use it directly to store the loaded page. */ return page_address(page); /* * The "original" page frame has not been allocated and we have to * use a "safe" page frame to store the loaded page. */ pbe = chain_alloc(ca, sizeof(struct pbe)); if (!pbe) { swsusp_free(); return ERR_PTR(-ENOMEM); } pbe->orig_address = page_address(page); pbe->address = __get_safe_page(ca->gfp_mask); if (!pbe->address) return ERR_PTR(-ENOMEM); pbe->next = restore_pblist; restore_pblist = pbe; return pbe->address; } /** * snapshot_write_next - Get the address to store the next image page. * @handle: Snapshot handle structure to guide the writing. * * On the first call, @handle should point to a zeroed snapshot_handle * structure. The structure gets populated then and a pointer to it should be * passed to this function every next time. * * On success, the function returns a positive number. Then, the caller * is allowed to write up to the returned number of bytes to the memory * location computed by the data_of() macro. * * The function returns 0 to indicate the "end of file" condition. Negative * numbers are returned on errors, in which cases the structure pointed to by * @handle is not updated and should not be used any more. */ int snapshot_write_next(struct snapshot_handle *handle) { static struct chain_allocator ca; int error; next: /* Check if we have already loaded the entire image */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) return 0; if (!handle->cur) { if (!buffer) /* This makes the buffer be freed by swsusp_free() */ buffer = get_image_page(GFP_ATOMIC, PG_ANY); if (!buffer) return -ENOMEM; handle->buffer = buffer; } else if (handle->cur == 1) { error = load_header(buffer); if (error) return error; safe_pages_list = NULL; error = memory_bm_create(©_bm, GFP_ATOMIC, PG_ANY); if (error) return error; error = memory_bm_create(&zero_bm, GFP_ATOMIC, PG_ANY); if (error) return error; nr_zero_pages = 0; hibernate_restore_protection_begin(); } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm, &zero_bm); if (error) return error; if (handle->cur == nr_meta_pages + 1) { error = prepare_image(&orig_bm, ©_bm, &zero_bm); if (error) return error; chain_init(&ca, GFP_ATOMIC, PG_SAFE); memory_bm_position_reset(&orig_bm); memory_bm_position_reset(&zero_bm); restore_pblist = NULL; handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } } else { copy_last_highmem_page(); error = hibernate_restore_protect_page(handle->buffer); if (error) return error; handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } handle->sync_read = (handle->buffer == buffer); handle->cur++; /* Zero pages were not included in the image, memset it and move on. */ if (handle->cur > nr_meta_pages + 1 && memory_bm_test_bit(&zero_bm, memory_bm_get_current(&orig_bm))) { memset(handle->buffer, 0, PAGE_SIZE); goto next; } return PAGE_SIZE; } /** * snapshot_write_finalize - Complete the loading of a hibernation image. * * Must be called after the last call to snapshot_write_next() in case the last * page in the image happens to be a highmem page and its contents should be * stored in highmem. Additionally, it recycles bitmap memory that's not * necessary any more. */ int snapshot_write_finalize(struct snapshot_handle *handle) { int error; copy_last_highmem_page(); error = hibernate_restore_protect_page(handle->buffer); /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) { memory_bm_recycle(&orig_bm); free_highmem_data(); } return error; } int snapshot_image_loaded(struct snapshot_handle *handle) { return !(!nr_copy_pages || !last_highmem_page_copied() || handle->cur <= nr_meta_pages + nr_copy_pages + nr_zero_pages); } #ifdef CONFIG_HIGHMEM /* Assumes that @buf is ready and points to a "safe" page */ static inline void swap_two_pages_data(struct page *p1, struct page *p2, void *buf) { void *kaddr1, *kaddr2; kaddr1 = kmap_local_page(p1); kaddr2 = kmap_local_page(p2); copy_page(buf, kaddr1); copy_page(kaddr1, kaddr2); copy_page(kaddr2, buf); kunmap_local(kaddr2); kunmap_local(kaddr1); } /** * restore_highmem - Put highmem image pages into their original locations. * * For each highmem page that was in use before hibernation and is included in * the image, and also has been allocated by the "restore" kernel, swap its * current contents with the previous (ie. "before hibernation") ones. * * If the restore eventually fails, we can call this function once again and * restore the highmem state as seen by the restore kernel. */ int restore_highmem(void) { struct highmem_pbe *pbe = highmem_pblist; void *buf; if (!pbe) return 0; buf = get_image_page(GFP_ATOMIC, PG_SAFE); if (!buf) return -ENOMEM; while (pbe) { swap_two_pages_data(pbe->copy_page, pbe->orig_page, buf); pbe = pbe->next; } free_image_page(buf, PG_UNSAFE_CLEAR); return 0; } #endif /* CONFIG_HIGHMEM */ |
| 818 966 600 259 259 396 396 230 232 192 84 86 192 29 246 246 246 234 31 24 21 33 33 33 699 408 409 43 366 699 536 45 206 409 318 216 287 40 120 45 7 9 66 123 11 5 783 767 355 7 156 163 336 178 773 776 386 761 760 761 763 449 57 255 763 762 762 763 762 762 623 234 234 763 762 518 518 518 518 260 957 957 955 836 148 371 539 601 688 3 3 957 209 71 257 471 452 47 11 6 36 36 3 31 13 33 11 11 8 34 21 12 1 208 244 33 241 36 33 4 6 15 25 1 11 9 16 36 33 22 12 976 976 970 218 69 173 471 519 64 17 78 79 192 140 90 227 28 66 34 132 403 530 109 1 21 19 3 537 470 587 588 587 588 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 479 478 73 3 3 3 3 2 3 3 3 3 3 3 3 3 1 2 819 248 1 13 13 5 13 232 1 1 1 51 51 47 47 47 47 47 47 47 47 43 13 47 46 233 224 82 43 231 3 5 232 18 12 22 18 7 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.c * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Hugh Dickins <hughd@google.com> * Zheng Liu <wenqing.lz@taobao.com> * * Ext4 extents status tree core functions. */ #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" #include <trace/events/ext4.h> /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * ========================================================================== * 3. Assurance of Ext4 extent status tree consistency * * When mapping blocks, Ext4 queries the extent status tree first and should * always trusts that the extent status tree is consistent and up to date. * Therefore, it is important to adheres to the following rules when createing, * modifying and removing extents. * * 1. Besides fastcommit replay, when Ext4 creates or queries block mappings, * the extent information should always be processed through the extent * status tree instead of being organized manually through the on-disk * extent tree. * * 2. When updating the extent tree, Ext4 should acquire the i_data_sem * exclusively and update the extent status tree atomically. If the extents * to be modified are large enough to exceed the range that a single * i_data_sem can process (as ext4_datasem_ensure_credits() may drop * i_data_sem to restart a transaction), it must (e.g. as ext4_punch_hole() * does): * * a) Hold the i_rwsem and invalidate_lock exclusively. This ensures * exclusion against page faults, as well as reads and writes that may * concurrently modify the extent status tree. * b) Evict all page cache in the affected range and recommend rebuilding * or dropping the extent status tree after modifying the on-disk * extent tree. This ensures exclusion against concurrent writebacks * that do not hold those locks but only holds a folio lock. * * 3. Based on the rules above, when querying block mappings, Ext4 should at * least hold the i_rwsem or invalidate_lock or folio lock(s) for the * specified querying range. * * ========================================================================== * 4. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 5. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc); int __init ext4_init_es(void) { ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_extent_range - find extent with specified status within block * range or next extent following block range in * extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * @es - extent found, if any * * Find the first extent within the block range specified by @lblk and @end * in the extents status tree that satisfies @matching_fn. If a match * is found, it's returned in @es. If not, and a matching extent is found * beyond the block range, it's returned in @es. If no match is found, an * extent is returned in @es whose es_lblk, es_len, and es_pblk components * are 0. */ static void __es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; WARN_ON(es == NULL); WARN_ON(end < lblk); tree = &EXT4_I(inode)->i_es_tree; /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (matching_fn(es1)) break; } } if (es1 && matching_fn(es1)) { WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } } /* * Locking for __es_find_extent_range() for external use */ void ext4_es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { es->es_lblk = es->es_len = es->es_pblk = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_find_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); __es_find_extent_range(inode, matching_fn, lblk, end, es); read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_extent_range_exit(inode, es); } /* * __es_scan_range - search block range for block with specified status * in extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * * Returns true if at least one block in the specified block range satisfies * the criterion specified by @matching_fn, and false if not. If at least * one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t start, ext4_lblk_t end) { struct extent_status es; __es_find_extent_range(inode, matching_fn, start, end, &es); if (es.es_len == 0) return false; /* no matching extent in the tree */ else if (es.es_lblk <= start && start < es.es_lblk + es.es_len) return true; else if (start <= es.es_lblk && es.es_lblk <= end) return true; else return false; } /* * Locking for __es_scan_range() for external use */ bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } /* * __es_scan_clu - search cluster for block with specified status in * extents status tree * * @inode - file containing the cluster * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block in cluster to be searched * * Returns true if at least one extent in the cluster containing @lblk * satisfies the criterion specified by @matching_fn, and false if not. If at * least one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); } /* * Locking for __es_scan_clu() for external use */ bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_clu(inode, matching_fn, lblk); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static inline struct pending_reservation *__alloc_pending(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); } static inline void __free_pending(struct pending_reservation *pr) { kmem_cache_free(ext4_pending_cachep, pr); } /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. */ static inline bool ext4_es_must_keep(struct extent_status *es) { /* fiemap, bigalloc, and seek_data/hole need to use it. */ if (ext4_es_is_delayed(es)) return true; return false; } static inline struct extent_status *__es_alloc_extent(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL); } static void ext4_es_init_extent(struct inode *inode, struct extent_status *es, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* We never try to reclaim a must kept extent, so we don't count it. */ if (!ext4_es_must_keep(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); } static inline void __es_free_extent(struct extent_status *es) { kmem_cache_free(ext4_es_cachep, es); } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when we can reclaim the extent. */ if (!ext4_es_must_keep(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } __es_free_extent(es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent */ if (ext4_es_is_delayed(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_free_ext_path(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG(); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct extent_status *es; while (*p) { parent = *p; es = rb_entry(parent, struct extent_status, rb_node); if (newes->es_lblk < es->es_lblk) { if (ext4_es_can_be_merged(newes, es)) { /* * Here we can modify es_lblk directly * because it isn't overlapped. */ es->es_lblk = newes->es_lblk; es->es_len += newes->es_len; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) ext4_es_store_pblock(es, newes->es_pblk); es = ext4_es_try_to_merge_left(inode, es); goto out; } p = &(*p)->rb_left; } else if (newes->es_lblk > ext4_es_end(es)) { if (ext4_es_can_be_merged(es, newes)) { es->es_len += newes->es_len; es = ext4_es_try_to_merge_right(inode, es); goto out; } p = &(*p)->rb_right; } else { BUG(); return -EINVAL; } } if (prealloc) es = prealloc; else es = __es_alloc_extent(false); if (!es) return -ENOMEM; ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len, newes->es_pblk); rb_link_node(&es->rb_node, parent, p); rb_insert_color(&es->rb_node, &tree->root); out: tree->cache_es = es; return 0; } /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. */ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status, bool delalloc_reserve_used) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err1 = 0, err2 = 0, err3 = 0; int resv_used = 0, pending = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr = NULL; bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; es_debug("add [%u/%u) %llu %x %d to extent status tree of inode %lu\n", lblk, len, pblk, status, delalloc_reserve_used, inode->i_ino); if (!len) return; BUG_ON(end < lblk); WARN_ON_ONCE(status & EXTENT_STATUS_DELAYED); newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_insert_extent(inode, &newes); ext4_es_insert_extent_check(inode, &newes); revise_pending = sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & (EXTENT_STATUS_WRITTEN | EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if ((err1 || err2 || err3 < 0) && revise_pending && !pr) pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, &resv_used, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 == -ENOMEM && !ext4_es_must_keep(&newes)) err2 = 0; if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (revise_pending) { err3 = __revise_pending(inode, lblk, len, &pr); if (err3 < 0) goto error; if (pr) { __free_pending(pr); pr = NULL; } pending = err3; } error: write_unlock(&EXT4_I(inode)->i_es_lock); /* * Reduce the reserved cluster count to reflect successful deferred * allocation of delayed allocated clusters or direct allocation of * clusters discovered to be delayed allocated. Once allocated, a * cluster is not included in the reserved count. * * When direct allocating (from fallocate, filemap, DIO, or clusters * allocated when delalloc has been disabled by ext4_nonda_switch()) * an extent either 1) contains delayed blocks but start with * non-delayed allocated blocks (e.g. hole) or 2) contains non-delayed * allocated blocks which belong to delayed allocated clusters when * bigalloc feature is enabled, quota has already been claimed by * ext4_mb_new_blocks(), so release the quota reservations made for * any previously delayed allocated clusters instead of claim them * again. */ resv_used += pending; if (resv_used) ext4_da_update_reserve_space(inode, resv_used, delalloc_reserve_used); if (err1 || err2 || err3 < 0) goto retry; ext4_es_print_tree(inode); return; } /* * ext4_es_cache_extent() inserts information into the extent status * tree if and only if there isn't information about the range in * question already. */ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status *es; struct extent_status newes; ext4_lblk_t end = lblk + len - 1; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_cache_extent(inode, &newes); if (!len) return; BUG_ON(end < lblk); write_lock(&EXT4_I(inode)->i_es_lock); es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); if (!es || es->es_lblk > end) __es_insert_extent(inode, &newes, NULL); write_unlock(&EXT4_I(inode)->i_es_lock); } /* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. * * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; struct ext4_es_stats *stats; struct extent_status *es1 = NULL; struct rb_node *node; int found = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_lookup_extent_enter(inode, lblk); es_debug("lookup extent in block %u\n", lblk); tree = &EXT4_I(inode)->i_es_tree; read_lock(&EXT4_I(inode)->i_es_lock); /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u)\n", lblk, es1->es_lblk, es1->es_len); found = 1; goto out; } node = tree->root.rb_node; while (node) { es1 = rb_entry(node, struct extent_status, rb_node); if (lblk < es1->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es1)) node = node->rb_right; else { found = 1; break; } } out: stats = &EXT4_SB(inode->i_sb)->s_es_stats; if (found) { BUG_ON(!es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); percpu_counter_inc(&stats->es_stats_cache_hits); if (next_lblk) { node = rb_next(&es1->rb_node); if (node) { es1 = rb_entry(node, struct extent_status, rb_node); *next_lblk = es1->es_lblk; } else *next_lblk = 0; } } else { percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_lookup_extent_exit(inode, es, found); return found; } struct rsvd_count { int ndelayed; bool first_do_lblk_found; ext4_lblk_t first_do_lblk; ext4_lblk_t last_do_lblk; struct extent_status *left_es; bool partial; ext4_lblk_t lclu; }; /* * init_rsvd - initialize reserved count data before removing block range * in file from extent status tree * * @inode - file containing range * @lblk - first block in range * @es - pointer to first extent in range * @rc - pointer to reserved count data * * Assumes es is not NULL */ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; rc->ndelayed = 0; /* * for bigalloc, note the first delayed block in the range has not * been found, record the extent containing the block to the left of * the region to be removed, if any, and note that there's no partial * cluster to track */ if (sbi->s_cluster_ratio > 1) { rc->first_do_lblk_found = false; if (lblk > es->es_lblk) { rc->left_es = es; } else { node = rb_prev(&es->rb_node); rc->left_es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } rc->partial = false; } } /* * count_rsvd - count the clusters containing delayed blocks in a range * within an extent and add to the running tally in rsvd_count * * @inode - file containing extent * @lblk - first block in range * @len - length of range in blocks * @es - pointer to extent containing clusters to be counted * @rc - pointer to reserved count data * * Tracks partial clusters found at the beginning and end of extents so * they aren't overcounted when they span adjacent extents */ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t i, end, nclu; if (!ext4_es_is_delayed(es)) return; WARN_ON(len <= 0); if (sbi->s_cluster_ratio == 1) { rc->ndelayed += (int) len; return; } /* bigalloc */ i = (lblk < es->es_lblk) ? es->es_lblk : lblk; end = lblk + (ext4_lblk_t) len - 1; end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delayed extent seen */ if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } /* update the last lblk in the region seen so far */ rc->last_do_lblk = end; /* * if we're tracking a partial cluster and the current extent * doesn't start with it, count it and stop tracking */ if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { rc->ndelayed++; rc->partial = false; } /* * if the first cluster doesn't start on a cluster boundary but * ends on one, count it */ if (EXT4_LBLK_COFF(sbi, i) != 0) { if (end >= EXT4_LBLK_CFILL(sbi, i)) { rc->ndelayed++; rc->partial = false; i = EXT4_LBLK_CFILL(sbi, i) + 1; } } /* * if the current cluster starts on a cluster boundary, count the * number of whole delayed clusters in the extent */ if ((i + sbi->s_cluster_ratio - 1) <= end) { nclu = (end - i + 1) >> sbi->s_cluster_bits; rc->ndelayed += nclu; i += nclu << sbi->s_cluster_bits; } /* * start tracking a partial cluster if there's a partial at the end * of the current extent and we're not already tracking one */ if (!rc->partial && i <= end) { rc->partial = true; rc->lclu = EXT4_B2C(sbi, i); } } /* * __pr_tree_search - search for a pending cluster reservation * * @root - root of pending reservation tree * @lclu - logical cluster to search for * * Returns the pending reservation for the cluster identified by @lclu * if found. If not, returns a reservation for the next cluster if any, * and if not, returns NULL. */ static struct pending_reservation *__pr_tree_search(struct rb_root *root, ext4_lblk_t lclu) { struct rb_node *node = root->rb_node; struct pending_reservation *pr = NULL; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else return pr; } if (pr && lclu < pr->lclu) return pr; if (pr && lclu > pr->lclu) { node = rb_next(&pr->rb_node); return node ? rb_entry(node, struct pending_reservation, rb_node) : NULL; } return NULL; } /* * get_rsvd - calculates and returns the number of cluster reservations to be * released when removing a block range from the extent status tree * and releases any pending reservations within the range * * @inode - file containing block range * @end - last block in range * @right_es - pointer to extent containing next block beyond end or NULL * @rc - pointer to reserved count data * * The number of reservations to be released is equal to the number of * clusters containing delayed blocks within the range, minus the number of * clusters still containing delayed blocks at the ends of the range, and * minus the number of pending reservations within the range. */ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, struct extent_status *right_es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; bool left_delayed, right_delayed, count_pending; struct extent_status *es; if (sbi->s_cluster_ratio > 1) { /* count any remaining partial cluster */ if (rc->partial) rc->ndelayed++; if (rc->ndelayed == 0) return 0; first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); /* * decrease the delayed count by the number of clusters at the * ends of the range that still contain delayed blocks - * these clusters still need to be reserved */ left_delayed = right_delayed = false; es = rc->left_es; while (es && ext4_es_end(es) >= EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { if (ext4_es_is_delayed(es)) { rc->ndelayed--; left_delayed = true; break; } node = rb_prev(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } if (right_es && (!left_delayed || first_lclu != last_lclu)) { if (end < ext4_es_end(right_es)) { es = right_es; } else { node = rb_next(&right_es->rb_node); es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } while (es && es->es_lblk <= EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { if (ext4_es_is_delayed(es)) { rc->ndelayed--; right_delayed = true; break; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } } /* * Determine the block range that should be searched for * pending reservations, if any. Clusters on the ends of the * original removed range containing delayed blocks are * excluded. They've already been accounted for and it's not * possible to determine if an associated pending reservation * should be released with the information available in the * extents status tree. */ if (first_lclu == last_lclu) { if (left_delayed | right_delayed) count_pending = false; else count_pending = true; } else { if (left_delayed) first_lclu++; if (right_delayed) last_lclu--; if (first_lclu <= last_lclu) count_pending = true; else count_pending = false; } /* * a pending reservation found between first_lclu and last_lclu * represents an allocated cluster that contained at least one * delayed block, so the delayed total must be reduced by one * for each pending reservation found and released */ if (count_pending) { pr = __pr_tree_search(&tree->root, first_lclu); while (pr && pr->lclu <= last_lclu) { rc->ndelayed--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, rb_node); } } } return rc->ndelayed; } /* * __es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @end - last block in range * @reserved - number of cluster reservations released * @prealloc - pre-allocated es to avoid memory allocation failures * * If @reserved is not NULL and delayed allocation is enabled, counts * block/cluster reservations freed by removing range and if bigalloc * enabled cancels pending reservations as needed. Returns 0 on success, * error code on failure. */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; struct extent_status *es; struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; int err = 0; bool count_reserved = true; struct rsvd_count rc; if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) count_reserved = false; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; if (es->es_lblk > end) goto out; /* Simply invalidate cache_es. */ tree->cache_es = NULL; if (count_reserved) init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; orig_es.es_pblk = es->es_pblk; len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0; len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0; if (len1 > 0) es->es_len = len1; if (len2 > 0) { if (len1 > 0) { struct extent_status newes; newes.es_lblk = end + 1; newes.es_len = len2; block = 0x7FDEADBEEFULL; if (ext4_es_is_written(&orig_es) || ext4_es_is_unwritten(&orig_es)) block = ext4_es_pblock(&orig_es) + orig_es.es_len - len2; ext4_es_store_pblock_status(&newes, block, ext4_es_status(&orig_es)); err = __es_insert_extent(inode, &newes, prealloc); if (err) { if (!ext4_es_must_keep(&newes)) return 0; es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; goto out; } } else { es->es_lblk = end + 1; es->es_len = len2; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = orig_es.es_pblk + orig_es.es_len - len2; ext4_es_store_pblock(es, block); } } if (count_reserved) count_rsvd(inode, orig_es.es_lblk + len1, orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } if (len1 > 0) { if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1, &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); else es = NULL; } while (es && ext4_es_end(es) <= end) { if (count_reserved) count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); if (!node) { es = NULL; break; } es = rb_entry(node, struct extent_status, rb_node); } if (es && es->es_lblk < end + 1) { ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; if (count_reserved) count_rsvd(inode, es->es_lblk, orig_len - len1, es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = es->es_pblk + orig_len - len1; ext4_es_store_pblock(es, block); } } out_get_reserved: if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* * ext4_es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @len - number of blocks to remove * * Reduces block/cluster reservation count and for bigalloc cancels pending * reservations as needed. */ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; int reserved = 0; struct extent_status *es = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return; end = lblk + len - 1; BUG_ON(end < lblk); retry: if (err && !es) es = __es_alloc_extent(true); /* * ext4_clear_inode() depends on us taking i_es_lock unconditionally * so that we are sure __es_shrink() is done with the inode before it * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved, es); /* Free preallocated extent if it didn't get used. */ if (es) { if (!es->es_len) __es_free_extent(es); es = NULL; } write_unlock(&EXT4_I(inode)->i_es_lock); if (err) goto retry; ext4_es_print_tree(inode); ext4_da_release_space(inode, reserved); } static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei) { struct ext4_inode_info *ei; struct ext4_es_stats *es_stats; ktime_t start_time; u64 scan_time; int nr_to_walk; int nr_shrunk = 0; int retried = 0, nr_skipped = 0; es_stats = &sbi->s_es_stats; start_time = ktime_get(); retry: spin_lock(&sbi->s_es_lock); nr_to_walk = sbi->s_es_nr_inode; while (nr_to_walk-- > 0) { if (list_empty(&sbi->s_es_list)) { spin_unlock(&sbi->s_es_lock); goto out; } ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info, i_es_list); /* Move the inode to the tail */ list_move_tail(&ei->i_es_list, &sbi->s_es_list); /* * Normally we try hard to avoid shrinking precached inodes, * but we will as a last resort. */ if (!retried && ext4_test_inode_state(&ei->vfs_inode, EXT4_STATE_EXT_PRECACHED)) { nr_skipped++; continue; } if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) { nr_skipped++; continue; } /* * Now we hold i_es_lock which protects us from inode reclaim * freeing inode under us */ spin_unlock(&sbi->s_es_lock); nr_shrunk += es_reclaim_extents(ei, &nr_to_scan); write_unlock(&ei->i_es_lock); if (nr_to_scan <= 0) goto out; spin_lock(&sbi->s_es_lock); } spin_unlock(&sbi->s_es_lock); /* * If we skipped any inodes, and we weren't able to make any * forward progress, try again to scan precached inodes. */ if ((nr_shrunk == 0) && nr_skipped && !retried) { retried++; goto retry; } if (locked_ei && nr_shrunk == 0) nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan); out: scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); if (likely(es_stats->es_stats_scan_time)) es_stats->es_stats_scan_time = (scan_time + es_stats->es_stats_scan_time*3) / 4; else es_stats->es_stats_scan_time = scan_time; if (scan_time > es_stats->es_stats_max_scan_time) es_stats->es_stats_max_scan_time = scan_time; if (likely(es_stats->es_stats_shrunk)) es_stats->es_stats_shrunk = (nr_shrunk + es_stats->es_stats_shrunk*3) / 4; else es_stats->es_stats_shrunk = nr_shrunk; trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, nr_skipped, retried); return nr_shrunk; } static unsigned long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr; struct ext4_sb_info *sbi; sbi = shrink->private_data; nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; } static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ext4_sb_info *sbi = shrink->private_data; int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; if (v != SEQ_START_TOKEN) return 0; /* here we just find an inode that has the max nr. of objects */ spin_lock(&sbi->s_es_lock); list_for_each_entry(ei, &sbi->s_es_list, i_es_list) { inode_cnt++; if (max && max->i_es_all_nr < ei->i_es_all_nr) max = ei; else if (!max) max = ei; } spin_unlock(&sbi->s_es_lock); seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); seq_printf(seq, " %lld/%lld cache hits/misses\n", percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); seq_printf(seq, "average:\n %llu us scan time\n", div_u64(es_stats->es_stats_scan_time, 1000)); seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk); if (inode_cnt) seq_printf(seq, "maximum:\n %lu inode (%u objects, %u reclaimable)\n" " %llu us max scan time\n", max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr, div_u64(es_stats->es_stats_max_scan_time, 1000)); return 0; } int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; /* Make sure we have enough bits for physical block number */ BUILD_BUG_ON(ES_SHIFT < 48); INIT_LIST_HEAD(&sbi->s_es_list); sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL); if (err) goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) goto err3; sbi->s_es_shrinker = shrinker_alloc(0, "ext4-es:%s", sbi->s_sb->s_id); if (!sbi->s_es_shrinker) { err = -ENOMEM; goto err4; } sbi->s_es_shrinker->scan_objects = ext4_es_scan; sbi->s_es_shrinker->count_objects = ext4_es_count; sbi->s_es_shrinker->private_data = sbi; shrinker_register(sbi->s_es_shrinker); return 0; err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); err2: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); err1: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); shrinker_free(sbi->s_es_shrinker); } /* * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at * most *nr_to_scan extents, update *nr_to_scan accordingly. * * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan. * Increment *nr_shrunk by the number of reclaimed extents. Also update * ei->i_es_shrink_lblk to where we should continue scanning. */ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, int *nr_to_scan, int *nr_shrunk) { struct inode *inode = &ei->vfs_inode; struct ext4_es_tree *tree = &ei->i_es_tree; struct extent_status *es; struct rb_node *node; es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; return 0; } (*nr_to_scan)--; node = rb_next(&es->rb_node); if (ext4_es_must_keep(es)) goto next; if (ext4_es_is_referenced(es)) { ext4_es_clear_referenced(es); goto next; } rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); (*nr_shrunk)++; next: if (!node) goto out_wrap; es = rb_entry(node, struct extent_status, rb_node); } ei->i_es_shrink_lblk = es->es_lblk; return 1; out_wrap: ei->i_es_shrink_lblk = 0; return 0; } static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) { struct inode *inode = &ei->vfs_inode; int nr_shrunk = 0; ext4_lblk_t start = ei->i_es_shrink_lblk; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (ei->i_es_shk_nr == 0) return 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && __ratelimit(&_rs)) ext4_warning(inode->i_sb, "forced shrink of precached extents"); if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) && start != 0) es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk); ei->i_es_tree.cache_es = NULL; return nr_shrunk; } /* * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove * discretionary entries from the extent status cache. (Some entries * must be present for proper operations.) */ void ext4_clear_inode_es(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct extent_status *es; struct ext4_es_tree *tree; struct rb_node *node; write_lock(&ei->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; tree->cache_es = NULL; node = rb_first(&tree->root); while (node) { es = rb_entry(node, struct extent_status, rb_node); node = rb_next(node); if (!ext4_es_must_keep(es)) { rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); } } ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); write_unlock(&ei->i_es_lock); } #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr; printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_pending_tree; node = rb_first(&tree->root); while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); printk(KERN_DEBUG " %u", pr->lclu); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_print_pending_tree(inode) #endif int __init ext4_init_pending(void) { ext4_pending_cachep = KMEM_CACHE(pending_reservation, SLAB_RECLAIM_ACCOUNT); if (ext4_pending_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_pending(void) { kmem_cache_destroy(ext4_pending_cachep); } void ext4_init_pending_tree(struct ext4_pending_tree *tree) { tree->root = RB_ROOT; } /* * __get_pending - retrieve a pointer to a pending reservation * * @inode - file containing the pending cluster reservation * @lclu - logical cluster of interest * * Returns a pointer to a pending reservation if it's a member of * the set, and NULL if not. Must be called holding i_es_lock. */ static struct pending_reservation *__get_pending(struct inode *inode, ext4_lblk_t lclu) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr = NULL; tree = &EXT4_I(inode)->i_pending_tree; node = (&tree->root)->rb_node; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else if (lclu == pr->lclu) return pr; } return NULL; } /* * __insert_pending - adds a pending cluster reservation to the set of * pending reservations * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added * @prealloc - preallocated pending entry * * Returns 1 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct pending_reservation *pr; ext4_lblk_t lclu; int ret = 0; lclu = EXT4_B2C(sbi, lblk); /* search to find parent for insertion */ while (*p) { parent = *p; pr = rb_entry(parent, struct pending_reservation, rb_node); if (lclu < pr->lclu) { p = &(*p)->rb_left; } else if (lclu > pr->lclu) { p = &(*p)->rb_right; } else { /* pending reservation already inserted */ goto out; } } if (likely(*prealloc == NULL)) { pr = __alloc_pending(false); if (!pr) { ret = -ENOMEM; goto out; } } else { pr = *prealloc; *prealloc = NULL; } pr->lclu = lclu; rb_link_node(&pr->rb_node, parent, p); rb_insert_color(&pr->rb_node, &tree->root); ret = 1; out: return ret; } /* * __remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Returns successfully if pending reservation is not a member of the set. */ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree; pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); } } /* * ext4_remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Locking for external use of __remove_pending. */ void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_inode_info *ei = EXT4_I(inode); write_lock(&ei->i_es_lock); __remove_pending(inode, lblk); write_unlock(&ei->i_es_lock); } /* * ext4_is_pending - determine whether a cluster has a pending reservation * on it * * @inode - file containing the cluster * @lblk - logical block in the cluster * * Returns true if there's a pending reservation for the cluster in the * set of pending reservations, and false if not. */ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); bool ret; read_lock(&ei->i_es_lock); ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); read_unlock(&ei->i_es_lock); return ret; } /* * ext4_es_insert_delayed_extent - adds some delayed blocks to the extents * status tree, adding a pending reservation * where needed * * @inode - file containing the newly added block * @lblk - start logical block to be added * @len - length of blocks to be added * @lclu_allocated/end_allocated - indicates whether a physical cluster has * been allocated for the logical cluster * that contains the start/end block. Note that * end_allocated should always be set to false * if the start and the end block are in the * same cluster */ void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, bool lclu_allocated, bool end_allocated) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr1 = NULL; struct pending_reservation *pr2 = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; es_debug("add [%u/%u) delayed to extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return; WARN_ON_ONCE((EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) && end_allocated); newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); trace_ext4_es_insert_delayed_extent(inode, &newes, lclu_allocated, end_allocated); ext4_es_insert_extent_check(inode, &newes); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if (err1 || err2 || err3 < 0) { if (lclu_allocated && !pr1) pr1 = __alloc_pending(true); if (end_allocated && !pr2) pr2 = __alloc_pending(true); } write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (lclu_allocated) { err3 = __insert_pending(inode, lblk, &pr1); if (err3 < 0) goto error; if (pr1) { __free_pending(pr1); pr1 = NULL; } } if (end_allocated) { err3 = __insert_pending(inode, end, &pr2); if (err3 < 0) goto error; if (pr2) { __free_pending(pr2); pr2 = NULL; } } error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2 || err3 < 0) goto retry; ext4_es_print_tree(inode); ext4_print_pending_tree(inode); return; } /* * __revise_pending - makes, cancels, or leaves unchanged pending cluster * reservations for a specified block range depending * upon the presence or absence of delayed blocks * outside the range within clusters at the ends of the * range * * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. Returns number of new * inserts pending cluster on insert pendings, returns 0 on remove pendings, * return -ENOMEM on failure. */ static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; int pendings = 0; int ret = 0; if (len == 0) return 0; /* * Two cases - block range within single cluster and block range * spanning two or more clusters. Note that a cluster belonging * to a range starting and/or ending on a cluster boundary is treated * as if it does not contain a delayed extent. The new range may * have allocated space for previously delayed blocks out to the * cluster boundary, requiring that any pre-existing pending * reservation be canceled. Because this code only looks at blocks * outside the range, it should revise pending reservations * correctly even if the extent represented by the range can't be * inserted in the extents status tree due to ENOSPC. */ if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delayed, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; pendings += ret; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delayed, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, last); } } else { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delayed, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delayed, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; pendings += ret; } else __remove_pending(inode, last); } out: return (ret < 0) ? ret : pendings; } |
| 13 13 19 528 189 31 14 144 11 147 24 134 158 292 253 6 286 10 273 2 89 9 1 1 1 10 49 52 78 13 2 10 78 2 2 5 5 1 5 4 1 119 118 1 100 100 97 2 1 98 115 3 3 3 114 5 115 112 3 119 47 47 4 39 4 3 12 33 46 3 3 3 243 243 243 2 241 172 167 65 66 66 2 66 66 66 66 185 47 154 471 223 128 4 107 161 6 269 90 538 2 20 539 2 42 43 43 43 43 4 43 43 43 43 31 13 43 43 43 43 530 530 312 27 511 326 530 530 4 530 324 530 530 128 1 5 1 2 2 2 529 22 529 23 23 3 20 20 17 17 3 20 5 1 312 11 308 309 309 309 61 309 309 309 118 266 16 16 16 16 5 5 16 2 2 2 2 2 2 2 2 2 1 1 1 1 103 2 101 214 6 1 1 2 4 2 1 1 2 3 191 4 5 189 90 90 89 18 4 2 2 17 48 23 22 22 4 1 15 158 24 9 3 122 140 12 2 3 123 19 17 2 8 2 1 1 1 3 45 60 58 3 3 3 3 3 16 45 41 2 2 18 59 15 15 4 25 2 1 24 3 22 1 26 26 24 6 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/nls.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" // clang-format off const struct cpu_str NAME_MFT = { 4, 0, { '$', 'M', 'F', 'T' }, }; const struct cpu_str NAME_MIRROR = { 8, 0, { '$', 'M', 'F', 'T', 'M', 'i', 'r', 'r' }, }; const struct cpu_str NAME_LOGFILE = { 8, 0, { '$', 'L', 'o', 'g', 'F', 'i', 'l', 'e' }, }; const struct cpu_str NAME_VOLUME = { 7, 0, { '$', 'V', 'o', 'l', 'u', 'm', 'e' }, }; const struct cpu_str NAME_ATTRDEF = { 8, 0, { '$', 'A', 't', 't', 'r', 'D', 'e', 'f' }, }; const struct cpu_str NAME_ROOT = { 1, 0, { '.' }, }; const struct cpu_str NAME_BITMAP = { 7, 0, { '$', 'B', 'i', 't', 'm', 'a', 'p' }, }; const struct cpu_str NAME_BOOT = { 5, 0, { '$', 'B', 'o', 'o', 't' }, }; const struct cpu_str NAME_BADCLUS = { 8, 0, { '$', 'B', 'a', 'd', 'C', 'l', 'u', 's' }, }; const struct cpu_str NAME_QUOTA = { 6, 0, { '$', 'Q', 'u', 'o', 't', 'a' }, }; const struct cpu_str NAME_SECURE = { 7, 0, { '$', 'S', 'e', 'c', 'u', 'r', 'e' }, }; const struct cpu_str NAME_UPCASE = { 7, 0, { '$', 'U', 'p', 'C', 'a', 's', 'e' }, }; const struct cpu_str NAME_EXTEND = { 7, 0, { '$', 'E', 'x', 't', 'e', 'n', 'd' }, }; const struct cpu_str NAME_OBJID = { 6, 0, { '$', 'O', 'b', 'j', 'I', 'd' }, }; const struct cpu_str NAME_REPARSE = { 8, 0, { '$', 'R', 'e', 'p', 'a', 'r', 's', 'e' }, }; const struct cpu_str NAME_USNJRNL = { 8, 0, { '$', 'U', 's', 'n', 'J', 'r', 'n', 'l' }, }; const __le16 BAD_NAME[4] = { cpu_to_le16('$'), cpu_to_le16('B'), cpu_to_le16('a'), cpu_to_le16('d'), }; const __le16 I30_NAME[4] = { cpu_to_le16('$'), cpu_to_le16('I'), cpu_to_le16('3'), cpu_to_le16('0'), }; const __le16 SII_NAME[4] = { cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('I'), cpu_to_le16('I'), }; const __le16 SDH_NAME[4] = { cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('D'), cpu_to_le16('H'), }; const __le16 SDS_NAME[4] = { cpu_to_le16('$'), cpu_to_le16('S'), cpu_to_le16('D'), cpu_to_le16('S'), }; const __le16 SO_NAME[2] = { cpu_to_le16('$'), cpu_to_le16('O'), }; const __le16 SQ_NAME[2] = { cpu_to_le16('$'), cpu_to_le16('Q'), }; const __le16 SR_NAME[2] = { cpu_to_le16('$'), cpu_to_le16('R'), }; #ifdef CONFIG_NTFS3_LZX_XPRESS const __le16 WOF_NAME[17] = { cpu_to_le16('W'), cpu_to_le16('o'), cpu_to_le16('f'), cpu_to_le16('C'), cpu_to_le16('o'), cpu_to_le16('m'), cpu_to_le16('p'), cpu_to_le16('r'), cpu_to_le16('e'), cpu_to_le16('s'), cpu_to_le16('s'), cpu_to_le16('e'), cpu_to_le16('d'), cpu_to_le16('D'), cpu_to_le16('a'), cpu_to_le16('t'), cpu_to_le16('a'), }; #endif static const __le16 CON_NAME[3] = { cpu_to_le16('C'), cpu_to_le16('O'), cpu_to_le16('N'), }; static const __le16 NUL_NAME[3] = { cpu_to_le16('N'), cpu_to_le16('U'), cpu_to_le16('L'), }; static const __le16 AUX_NAME[3] = { cpu_to_le16('A'), cpu_to_le16('U'), cpu_to_le16('X'), }; static const __le16 PRN_NAME[3] = { cpu_to_le16('P'), cpu_to_le16('R'), cpu_to_le16('N'), }; static const __le16 COM_NAME[3] = { cpu_to_le16('C'), cpu_to_le16('O'), cpu_to_le16('M'), }; static const __le16 LPT_NAME[3] = { cpu_to_le16('L'), cpu_to_le16('P'), cpu_to_le16('T'), }; // clang-format on /* * ntfs_fix_pre_write - Insert fixups into @rhdr before writing to disk. */ bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes) { u16 *fixup, *ptr; u16 sample; u16 fo = le16_to_cpu(rhdr->fix_off); u16 fn = le16_to_cpu(rhdr->fix_num); if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { return false; } /* Get fixup pointer. */ fixup = Add2Ptr(rhdr, fo); if (*fixup >= 0x7FFF) *fixup = 1; else *fixup += 1; sample = *fixup; ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short)); while (fn--) { *++fixup = *ptr; *ptr = sample; ptr += SECTOR_SIZE / sizeof(short); } return true; } /* * ntfs_fix_post_read - Remove fixups after reading from disk. * * Return: < 0 if error, 0 if ok, 1 if need to update fixups. */ int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple) { int ret; u16 *fixup, *ptr; u16 sample, fo, fn; fo = le16_to_cpu(rhdr->fix_off); fn = simple ? ((bytes >> SECTOR_SHIFT) + 1) : le16_to_cpu(rhdr->fix_num); /* Check errors. */ if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { return -E_NTFS_CORRUPT; } /* Get fixup pointer. */ fixup = Add2Ptr(rhdr, fo); sample = *fixup; ptr = Add2Ptr(rhdr, SECTOR_SIZE - sizeof(short)); ret = 0; while (fn--) { /* Test current word. */ if (*ptr != sample) { /* Fixup does not match! Is it serious error? */ ret = -E_NTFS_FIXUP; } /* Replace fixup. */ *ptr = *++fixup; ptr += SECTOR_SIZE / sizeof(short); } return ret; } /* * ntfs_extend_init - Load $Extend file. */ int ntfs_extend_init(struct ntfs_sb_info *sbi) { int err; struct super_block *sb = sbi->sb; struct inode *inode, *inode2; struct MFT_REF ref; if (sbi->volume.major_ver < 3) { ntfs_notice(sb, "Skip $Extend 'cause NTFS version"); return 0; } ref.low = cpu_to_le32(MFT_REC_EXTEND); ref.high = 0; ref.seq = cpu_to_le16(MFT_REC_EXTEND); inode = ntfs_iget5(sb, &ref, &NAME_EXTEND); if (IS_ERR(inode)) { err = PTR_ERR(inode); ntfs_err(sb, "Failed to load $Extend (%d).", err); inode = NULL; goto out; } /* If ntfs_iget5() reads from disk it never returns bad inode. */ if (!S_ISDIR(inode->i_mode)) { err = -EINVAL; goto out; } /* Try to find $ObjId */ inode2 = dir_search_u(inode, &NAME_OBJID, NULL); if (inode2 && !IS_ERR(inode2)) { if (is_bad_inode(inode2)) { iput(inode2); } else { sbi->objid.ni = ntfs_i(inode2); sbi->objid_no = inode2->i_ino; } } /* Try to find $Quota */ inode2 = dir_search_u(inode, &NAME_QUOTA, NULL); if (inode2 && !IS_ERR(inode2)) { sbi->quota_no = inode2->i_ino; iput(inode2); } /* Try to find $Reparse */ inode2 = dir_search_u(inode, &NAME_REPARSE, NULL); if (inode2 && !IS_ERR(inode2)) { sbi->reparse.ni = ntfs_i(inode2); sbi->reparse_no = inode2->i_ino; } /* Try to find $UsnJrnl */ inode2 = dir_search_u(inode, &NAME_USNJRNL, NULL); if (inode2 && !IS_ERR(inode2)) { sbi->usn_jrnl_no = inode2->i_ino; iput(inode2); } err = 0; out: iput(inode); return err; } int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi) { int err = 0; struct super_block *sb = sbi->sb; bool initialized = false; struct MFT_REF ref; struct inode *inode; /* Check for 4GB. */ if (ni->vfs_inode.i_size >= 0x100000000ull) { ntfs_err(sb, "\x24LogFile is large than 4G."); err = -EINVAL; goto out; } sbi->flags |= NTFS_FLAGS_LOG_REPLAYING; ref.low = cpu_to_le32(MFT_REC_MFT); ref.high = 0; ref.seq = cpu_to_le16(1); inode = ntfs_iget5(sb, &ref, NULL); if (IS_ERR(inode)) inode = NULL; if (!inode) { /* Try to use MFT copy. */ u64 t64 = sbi->mft.lbo; sbi->mft.lbo = sbi->mft.lbo2; inode = ntfs_iget5(sb, &ref, NULL); sbi->mft.lbo = t64; if (IS_ERR(inode)) inode = NULL; } if (!inode) { err = -EINVAL; ntfs_err(sb, "Failed to load $MFT."); goto out; } sbi->mft.ni = ntfs_i(inode); /* LogFile should not contains attribute list. */ err = ni_load_all_mi(sbi->mft.ni); if (!err) err = log_replay(ni, &initialized); iput(inode); sbi->mft.ni = NULL; sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { err = 0; goto out; } if (sb_rdonly(sb) || !initialized) goto out; /* Fill LogFile by '-1' if it is initialized. */ err = ntfs_bio_fill_1(sbi, &ni->file.run); out: sbi->flags &= ~NTFS_FLAGS_LOG_REPLAYING; return err; } /* * ntfs_look_for_free_space - Look for a free space in bitmap. */ int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, CLST *new_lcn, CLST *new_len, enum ALLOCATE_OPT opt) { int err; CLST alen; struct super_block *sb = sbi->sb; size_t alcn, zlen, zeroes, zlcn, zlen2, ztrim, new_zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); if (opt & ALLOCATE_MFT) { zlen = wnd_zone_len(wnd); if (!zlen) { err = ntfs_refresh_zone(sbi); if (err) goto up_write; zlen = wnd_zone_len(wnd); } if (!zlen) { ntfs_err(sbi->sb, "no free space to extend mft"); err = -ENOSPC; goto up_write; } lcn = wnd_zone_bit(wnd); alen = min_t(CLST, len, zlen); wnd_zone_set(wnd, lcn + alen, zlen - alen); err = wnd_set_used(wnd, lcn, alen); if (err) goto up_write; alcn = lcn; goto space_found; } /* * 'Cause cluster 0 is always used this value means that we should use * cached value of 'next_free_lcn' to improve performance. */ if (!lcn) lcn = sbi->used.next_free_lcn; if (lcn >= wnd->nbits) lcn = 0; alen = wnd_find(wnd, len, lcn, BITMAP_FIND_MARK_AS_USED, &alcn); if (alen) goto space_found; /* Try to use clusters from MftZone. */ zlen = wnd_zone_len(wnd); zeroes = wnd_zeroes(wnd); /* Check too big request */ if (len > zeroes + zlen || zlen <= NTFS_MIN_MFT_ZONE) { err = -ENOSPC; goto up_write; } /* How many clusters to cat from zone. */ zlcn = wnd_zone_bit(wnd); zlen2 = zlen >> 1; ztrim = clamp_val(len, zlen2, zlen); new_zlen = max_t(size_t, zlen - ztrim, NTFS_MIN_MFT_ZONE); wnd_zone_set(wnd, zlcn, new_zlen); /* Allocate continues clusters. */ alen = wnd_find(wnd, len, 0, BITMAP_FIND_MARK_AS_USED | BITMAP_FIND_FULL, &alcn); if (!alen) { err = -ENOSPC; goto up_write; } space_found: err = 0; *new_len = alen; *new_lcn = alcn; ntfs_unmap_meta(sb, alcn, alen); /* Set hint for next requests. */ if (!(opt & ALLOCATE_MFT)) sbi->used.next_free_lcn = alcn + alen; up_write: up_write(&wnd->rw_lock); return err; } /* * ntfs_check_for_free_space * * Check if it is possible to allocate 'clen' clusters and 'mlen' Mft records */ bool ntfs_check_for_free_space(struct ntfs_sb_info *sbi, CLST clen, CLST mlen) { size_t free, zlen, avail; struct wnd_bitmap *wnd; wnd = &sbi->used.bitmap; down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); free = wnd_zeroes(wnd); zlen = min_t(size_t, NTFS_MIN_MFT_ZONE, wnd_zone_len(wnd)); up_read(&wnd->rw_lock); if (free < zlen + clen) return false; avail = free - (zlen + clen); wnd = &sbi->mft.bitmap; down_read_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); free = wnd_zeroes(wnd); zlen = wnd_zone_len(wnd); up_read(&wnd->rw_lock); if (free >= zlen + mlen) return true; return avail >= bytes_to_cluster(sbi, mlen << sbi->record_bits); } /* * ntfs_extend_mft - Allocate additional MFT records. * * sbi->mft.bitmap is locked for write. * * NOTE: recursive: * ntfs_look_free_mft -> * ntfs_extend_mft -> * attr_set_size -> * ni_insert_nonresident -> * ni_insert_attr -> * ni_ins_attr_ext -> * ntfs_look_free_mft -> * ntfs_extend_mft * * To avoid recursive always allocate space for two new MFT records * see attrib.c: "at least two MFT to avoid recursive loop". */ static int ntfs_extend_mft(struct ntfs_sb_info *sbi) { int err; struct ntfs_inode *ni = sbi->mft.ni; size_t new_mft_total; u64 new_mft_bytes, new_bitmap_bytes; struct ATTRIB *attr; struct wnd_bitmap *wnd = &sbi->mft.bitmap; new_mft_total = ALIGN(wnd->nbits + NTFS_MFT_INCREASE_STEP, 128); new_mft_bytes = (u64)new_mft_total << sbi->record_bits; /* Step 1: Resize $MFT::DATA. */ down_write(&ni->file.run_lock); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_mft_bytes, NULL, false, &attr); if (err) { up_write(&ni->file.run_lock); goto out; } attr->nres.valid_size = attr->nres.data_size; new_mft_total = le64_to_cpu(attr->nres.alloc_size) >> sbi->record_bits; ni->mi.dirty = true; /* Step 2: Resize $MFT::BITMAP. */ new_bitmap_bytes = ntfs3_bitmap_size(new_mft_total); err = attr_set_size(ni, ATTR_BITMAP, NULL, 0, &sbi->mft.bitmap.run, new_bitmap_bytes, &new_bitmap_bytes, true, NULL); /* Refresh MFT Zone if necessary. */ down_write_nested(&sbi->used.bitmap.rw_lock, BITMAP_MUTEX_CLUSTERS); ntfs_refresh_zone(sbi); up_write(&sbi->used.bitmap.rw_lock); up_write(&ni->file.run_lock); if (err) goto out; err = wnd_extend(wnd, new_mft_total); if (err) goto out; ntfs_clear_mft_tail(sbi, sbi->mft.used, new_mft_total); err = _ni_write_inode(&ni->vfs_inode, 0); out: return err; } /* * ntfs_look_free_mft - Look for a free MFT record. */ int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, struct ntfs_inode *ni, struct mft_inode **mi) { int err = 0; size_t zbit, zlen, from, to, fr; size_t mft_total; struct MFT_REF ref; struct super_block *sb = sbi->sb; struct wnd_bitmap *wnd = &sbi->mft.bitmap; u32 ir; static_assert(sizeof(sbi->mft.reserved_bitmap) * 8 >= MFT_REC_FREE - MFT_REC_RESERVED); if (!mft) down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); zlen = wnd_zone_len(wnd); /* Always reserve space for MFT. */ if (zlen) { if (mft) { zbit = wnd_zone_bit(wnd); *rno = zbit; wnd_zone_set(wnd, zbit + 1, zlen - 1); } goto found; } /* No MFT zone. Find the nearest to '0' free MFT. */ if (!wnd_find(wnd, 1, MFT_REC_FREE, 0, &zbit)) { /* Resize MFT */ mft_total = wnd->nbits; err = ntfs_extend_mft(sbi); if (!err) { zbit = mft_total; goto reserve_mft; } if (!mft || MFT_REC_FREE == sbi->mft.next_reserved) goto out; err = 0; /* * Look for free record reserved area [11-16) == * [MFT_REC_RESERVED, MFT_REC_FREE ) MFT bitmap always * marks it as used. */ if (!sbi->mft.reserved_bitmap) { /* Once per session create internal bitmap for 5 bits. */ sbi->mft.reserved_bitmap = 0xFF; ref.high = 0; for (ir = MFT_REC_RESERVED; ir < MFT_REC_FREE; ir++) { struct inode *i; struct ntfs_inode *ni; struct MFT_REC *mrec; ref.low = cpu_to_le32(ir); ref.seq = cpu_to_le16(ir); i = ntfs_iget5(sb, &ref, NULL); if (IS_ERR(i)) { next: ntfs_notice( sb, "Invalid reserved record %x", ref.low); continue; } if (is_bad_inode(i)) { iput(i); goto next; } ni = ntfs_i(i); mrec = ni->mi.mrec; if (!is_rec_base(mrec)) goto next; if (mrec->hard_links) goto next; if (!ni_std(ni)) goto next; if (ni_find_attr(ni, NULL, NULL, ATTR_NAME, NULL, 0, NULL, NULL)) goto next; __clear_bit(ir - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); } } /* Scan 5 bits for zero. Bit 0 == MFT_REC_RESERVED */ zbit = find_next_zero_bit(&sbi->mft.reserved_bitmap, MFT_REC_FREE, MFT_REC_RESERVED); if (zbit >= MFT_REC_FREE) { sbi->mft.next_reserved = MFT_REC_FREE; goto out; } zlen = 1; sbi->mft.next_reserved = zbit; } else { reserve_mft: zlen = zbit == MFT_REC_FREE ? (MFT_REC_USER - MFT_REC_FREE) : 4; if (zbit + zlen > wnd->nbits) zlen = wnd->nbits - zbit; while (zlen > 1 && !wnd_is_free(wnd, zbit, zlen)) zlen -= 1; /* [zbit, zbit + zlen) will be used for MFT itself. */ from = sbi->mft.used; if (from < zbit) from = zbit; to = zbit + zlen; if (from < to) { ntfs_clear_mft_tail(sbi, from, to); sbi->mft.used = to; } } if (mft) { *rno = zbit; zbit += 1; zlen -= 1; } wnd_zone_set(wnd, zbit, zlen); found: if (!mft) { /* The request to get record for general purpose. */ if (sbi->mft.next_free < MFT_REC_USER) sbi->mft.next_free = MFT_REC_USER; for (;;) { if (sbi->mft.next_free >= sbi->mft.bitmap.nbits) { } else if (!wnd_find(wnd, 1, MFT_REC_USER, 0, &fr)) { sbi->mft.next_free = sbi->mft.bitmap.nbits; } else { *rno = fr; sbi->mft.next_free = *rno + 1; break; } err = ntfs_extend_mft(sbi); if (err) goto out; } } if (ni && !ni_add_subrecord(ni, *rno, mi)) { err = -ENOMEM; goto out; } /* We have found a record that are not reserved for next MFT. */ if (*rno >= MFT_REC_FREE) wnd_set_used(wnd, *rno, 1); else if (*rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) __set_bit(*rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); out: if (!mft) up_write(&wnd->rw_lock); return err; } /* * ntfs_mark_rec_free - Mark record as free. * is_mft - true if we are changing MFT */ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft) { struct wnd_bitmap *wnd = &sbi->mft.bitmap; if (!is_mft) down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_MFT); if (rno >= wnd->nbits) goto out; if (rno >= MFT_REC_FREE) { if (!wnd_is_used(wnd, rno, 1)) ntfs_set_state(sbi, NTFS_DIRTY_ERROR); else wnd_set_free(wnd, rno, 1); } else if (rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) { __clear_bit(rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); } if (rno < wnd_zone_bit(wnd)) wnd_zone_set(wnd, rno, 1); else if (rno < sbi->mft.next_free && rno >= MFT_REC_USER) sbi->mft.next_free = rno; out: if (!is_mft) up_write(&wnd->rw_lock); } /* * ntfs_clear_mft_tail - Format empty records [from, to). * * sbi->mft.bitmap is locked for write. */ int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to) { int err; u32 rs; u64 vbo; struct runs_tree *run; struct ntfs_inode *ni; if (from >= to) return 0; rs = sbi->record_size; ni = sbi->mft.ni; run = &ni->file.run; down_read(&ni->file.run_lock); vbo = (u64)from * rs; for (; from < to; from++, vbo += rs) { struct ntfs_buffers nb; err = ntfs_get_bh(sbi, run, vbo, rs, &nb); if (err) goto out; err = ntfs_write_bh(sbi, &sbi->new_rec->rhdr, &nb, 0); nb_put(&nb); if (err) goto out; } out: sbi->mft.used = from; up_read(&ni->file.run_lock); return err; } /* * ntfs_refresh_zone - Refresh MFT zone. * * sbi->used.bitmap is locked for rw. * sbi->mft.bitmap is locked for write. * sbi->mft.ni->file.run_lock for write. */ int ntfs_refresh_zone(struct ntfs_sb_info *sbi) { CLST lcn, vcn, len; size_t lcn_s, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; struct ntfs_inode *ni = sbi->mft.ni; /* Do not change anything unless we have non empty MFT zone. */ if (wnd_zone_len(wnd)) return 0; vcn = bytes_to_cluster(sbi, (u64)sbi->mft.bitmap.nbits << sbi->record_bits); if (!run_lookup_entry(&ni->file.run, vcn - 1, &lcn, &len, NULL)) lcn = SPARSE_LCN; /* We should always find Last Lcn for MFT. */ if (lcn == SPARSE_LCN) return -EINVAL; lcn_s = lcn + 1; /* Try to allocate clusters after last MFT run. */ zlen = wnd_find(wnd, sbi->zone_max, lcn_s, 0, &lcn_s); wnd_zone_set(wnd, lcn_s, zlen); return 0; } /* * ntfs_update_mftmirr - Update $MFTMirr data. */ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) { int err; struct super_block *sb = sbi->sb; u32 blocksize, bytes; sector_t block1, block2; /* * sb can be NULL here. In this case sbi->flags should be 0 too. */ if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) || unlikely(ntfs3_forced_shutdown(sb))) return; blocksize = sb->s_blocksize; bytes = sbi->mft.recs_mirr << sbi->record_bits; block1 = sbi->mft.lbo >> sb->s_blocksize_bits; block2 = sbi->mft.lbo2 >> sb->s_blocksize_bits; for (; bytes >= blocksize; bytes -= blocksize) { struct buffer_head *bh1, *bh2; bh1 = sb_bread(sb, block1++); if (!bh1) return; bh2 = sb_getblk(sb, block2++); if (!bh2) { put_bh(bh1); return; } if (buffer_locked(bh2)) __wait_on_buffer(bh2); lock_buffer(bh2); memcpy(bh2->b_data, bh1->b_data, blocksize); set_buffer_uptodate(bh2); mark_buffer_dirty(bh2); unlock_buffer(bh2); put_bh(bh1); bh1 = NULL; err = wait ? sync_dirty_buffer(bh2) : 0; put_bh(bh2); if (err) return; } sbi->flags &= ~NTFS_FLAGS_MFTMIRR; } /* * ntfs_bad_inode * * Marks inode as bad and marks fs as 'dirty' */ void ntfs_bad_inode(struct inode *inode, const char *hint) { struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); ntfs_inode_err(inode, "%s", hint); /* Do not call make_bad_inode()! */ ni->ni_bad = true; /* Avoid recursion if bad inode is $Volume. */ if (inode->i_ino != MFT_REC_VOL && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING)) { ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } } /* * ntfs_set_state * * Mount: ntfs_set_state(NTFS_DIRTY_DIRTY) * Umount: ntfs_set_state(NTFS_DIRTY_CLEAR) * NTFS error: ntfs_set_state(NTFS_DIRTY_ERROR) */ int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty) { int err; struct ATTRIB *attr; struct VOLUME_INFO *info; struct mft_inode *mi; struct ntfs_inode *ni; __le16 info_flags; /* * Do not change state if fs was real_dirty. * Do not change state if fs already dirty(clear). * Do not change any thing if mounted read only. */ if (sbi->volume.real_dirty || sb_rdonly(sbi->sb)) return 0; /* Check cached value. */ if ((dirty == NTFS_DIRTY_CLEAR ? 0 : VOLUME_FLAG_DIRTY) == (sbi->volume.flags & VOLUME_FLAG_DIRTY)) return 0; ni = sbi->volume.ni; if (!ni) return -EINVAL; mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_DIRTY); attr = ni_find_attr(ni, NULL, NULL, ATTR_VOL_INFO, NULL, 0, NULL, &mi); if (!attr) { err = -EINVAL; goto out; } info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO); if (!info) { err = -EINVAL; goto out; } info_flags = info->flags; switch (dirty) { case NTFS_DIRTY_ERROR: ntfs_notice(sbi->sb, "Mark volume as dirty due to NTFS errors"); sbi->volume.real_dirty = true; fallthrough; case NTFS_DIRTY_DIRTY: info->flags |= VOLUME_FLAG_DIRTY; break; case NTFS_DIRTY_CLEAR: info->flags &= ~VOLUME_FLAG_DIRTY; break; } /* Cache current volume flags. */ if (info_flags != info->flags) { sbi->volume.flags = info->flags; mi->dirty = true; } err = 0; out: ni_unlock(ni); if (err) return err; mark_inode_dirty_sync(&ni->vfs_inode); /* verify(!ntfs_update_mftmirr()); */ /* write mft record on disk. */ err = _ni_write_inode(&ni->vfs_inode, 1); return err; } /* * security_hash - Calculates a hash of security descriptor. */ static inline __le32 security_hash(const void *sd, size_t bytes) { u32 hash = 0; const __le32 *ptr = sd; bytes >>= 2; while (bytes--) hash = ((hash >> 0x1D) | (hash << 3)) + le32_to_cpu(*ptr++); return cpu_to_le32(hash); } /* * simple wrapper for sb_bread_unmovable. */ struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) { struct ntfs_sb_info *sbi = sb->s_fs_info; struct buffer_head *bh; if (unlikely(block >= sbi->volume.blocks)) { /* prevent generic message "attempt to access beyond end of device" */ ntfs_err(sb, "try to read out of volume at offset 0x%llx", (u64)block << sb->s_blocksize_bits); return NULL; } bh = sb_bread_unmovable(sb, block); if (bh) return bh; ntfs_err(sb, "failed to read volume at offset 0x%llx", (u64)block << sb->s_blocksize_bits); return NULL; } int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes, const void *buf, int wait) { u32 blocksize = sb->s_blocksize; struct block_device *bdev = sb->s_bdev; sector_t block = lbo >> sb->s_blocksize_bits; u32 off = lbo & (blocksize - 1); u32 op = blocksize - off; struct buffer_head *bh; if (!wait && (sb->s_flags & SB_SYNCHRONOUS)) wait = 1; for (; bytes; block += 1, off = 0, op = blocksize) { if (op > bytes) op = bytes; if (op < blocksize) { bh = __bread(bdev, block, blocksize); if (!bh) { ntfs_err(sb, "failed to read block %llx", (u64)block); return -EIO; } } else { bh = __getblk(bdev, block, blocksize); if (!bh) return -ENOMEM; } if (buffer_locked(bh)) __wait_on_buffer(bh); lock_buffer(bh); if (buf) { memcpy(bh->b_data + off, buf, op); buf = Add2Ptr(buf, op); } else { memset(bh->b_data + off, -1, op); } set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); if (wait) { int err = sync_dirty_buffer(bh); if (err) { ntfs_err( sb, "failed to sync buffer at block %llx, error %d", (u64)block, err); put_bh(bh); return err; } } put_bh(bh); bytes -= op; } return 0; } int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, const void *buf, size_t bytes, int sync) { struct super_block *sb = sbi->sb; u8 cluster_bits = sbi->cluster_bits; u32 off = vbo & sbi->cluster_mask; CLST lcn, clen, vcn = vbo >> cluster_bits, vcn_next; u64 lbo, len; size_t idx; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) return -ENOENT; if (lcn == SPARSE_LCN) return -EINVAL; lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; for (;;) { u32 op = min_t(u64, len, bytes); int err = ntfs_sb_write(sb, lbo, op, buf, sync); if (err) return err; bytes -= op; if (!bytes) break; vcn_next = vcn + clen; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn != vcn_next) return -ENOENT; if (lcn == SPARSE_LCN) return -EINVAL; if (buf) buf = Add2Ptr(buf, op); lbo = ((u64)lcn << cluster_bits); len = ((u64)clen << cluster_bits); } return 0; } struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo) { struct super_block *sb = sbi->sb; u8 cluster_bits = sbi->cluster_bits; CLST lcn; u64 lbo; if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, NULL, NULL)) return ERR_PTR(-ENOENT); lbo = ((u64)lcn << cluster_bits) + (vbo & sbi->cluster_mask); return ntfs_bread(sb, lbo >> sb->s_blocksize_bits); } int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb) { int err; struct super_block *sb = sbi->sb; u32 blocksize = sb->s_blocksize; u8 cluster_bits = sbi->cluster_bits; u32 off = vbo & sbi->cluster_mask; u32 nbh = 0; CLST vcn_next, vcn = vbo >> cluster_bits; CLST lcn, clen; u64 lbo, len; size_t idx; struct buffer_head *bh; if (!run) { /* First reading of $Volume + $MFTMirr + $LogFile goes here. */ if (vbo > MFT_REC_VOL * sbi->record_size) { err = -ENOENT; goto out; } /* Use absolute boot's 'MFTCluster' to read record. */ lbo = vbo + sbi->mft.lbo; len = sbi->record_size; } else if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { err = -ENOENT; goto out; } else { if (lcn == SPARSE_LCN) { err = -EINVAL; goto out; } lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; } off = lbo & (blocksize - 1); if (nb) { nb->off = off; nb->bytes = bytes; } for (;;) { u32 len32 = len >= bytes ? bytes : len; sector_t block = lbo >> sb->s_blocksize_bits; do { u32 op = blocksize - off; if (op > len32) op = len32; bh = ntfs_bread(sb, block); if (!bh) { err = -EIO; goto out; } if (buf) { memcpy(buf, bh->b_data + off, op); buf = Add2Ptr(buf, op); } if (!nb) { put_bh(bh); } else if (nbh >= ARRAY_SIZE(nb->bh)) { err = -EINVAL; goto out; } else { nb->bh[nbh++] = bh; nb->nbufs = nbh; } bytes -= op; if (!bytes) return 0; len32 -= op; block += 1; off = 0; } while (len32); vcn_next = vcn + clen; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn != vcn_next) { err = -ENOENT; goto out; } if (lcn == SPARSE_LCN) { err = -EINVAL; goto out; } lbo = ((u64)lcn << cluster_bits); len = ((u64)clen << cluster_bits); } out: if (!nbh) return err; while (nbh) { put_bh(nb->bh[--nbh]); nb->bh[nbh] = NULL; } nb->nbufs = 0; return err; } /* * ntfs_read_bh * * Return: < 0 if error, 0 if ok, -E_NTFS_FIXUP if need to update fixups. */ int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, struct NTFS_RECORD_HEADER *rhdr, u32 bytes, struct ntfs_buffers *nb) { int err = ntfs_read_run_nb(sbi, run, vbo, rhdr, bytes, nb); if (err) return err; return ntfs_fix_post_read(rhdr, nb->bytes, true); } int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, u32 bytes, struct ntfs_buffers *nb) { int err = 0; struct super_block *sb = sbi->sb; u32 blocksize = sb->s_blocksize; u8 cluster_bits = sbi->cluster_bits; CLST vcn_next, vcn = vbo >> cluster_bits; u32 off; u32 nbh = 0; CLST lcn, clen; u64 lbo, len; size_t idx; nb->bytes = bytes; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { err = -ENOENT; goto out; } off = vbo & sbi->cluster_mask; lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; nb->off = off = lbo & (blocksize - 1); for (;;) { u32 len32 = min_t(u64, len, bytes); sector_t block = lbo >> sb->s_blocksize_bits; do { u32 op; struct buffer_head *bh; if (nbh >= ARRAY_SIZE(nb->bh)) { err = -EINVAL; goto out; } op = blocksize - off; if (op > len32) op = len32; if (op == blocksize) { bh = sb_getblk(sb, block); if (!bh) { err = -ENOMEM; goto out; } if (buffer_locked(bh)) __wait_on_buffer(bh); set_buffer_uptodate(bh); } else { bh = ntfs_bread(sb, block); if (!bh) { err = -EIO; goto out; } } nb->bh[nbh++] = bh; bytes -= op; if (!bytes) { nb->nbufs = nbh; return 0; } block += 1; len32 -= op; off = 0; } while (len32); vcn_next = vcn + clen; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn != vcn_next) { err = -ENOENT; goto out; } lbo = ((u64)lcn << cluster_bits); len = ((u64)clen << cluster_bits); } out: while (nbh) { put_bh(nb->bh[--nbh]); nb->bh[nbh] = NULL; } nb->nbufs = 0; return err; } int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, struct ntfs_buffers *nb, int sync) { int err = 0; struct super_block *sb = sbi->sb; u32 block_size = sb->s_blocksize; u32 bytes = nb->bytes; u32 off = nb->off; u16 fo = le16_to_cpu(rhdr->fix_off); u16 fn = le16_to_cpu(rhdr->fix_num); u32 idx; __le16 *fixup; __le16 sample; if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { return -EINVAL; } for (idx = 0; bytes && idx < nb->nbufs; idx += 1, off = 0) { u32 op = block_size - off; char *bh_data; struct buffer_head *bh = nb->bh[idx]; __le16 *ptr, *end_data; if (op > bytes) op = bytes; if (buffer_locked(bh)) __wait_on_buffer(bh); lock_buffer(bh); bh_data = bh->b_data + off; end_data = Add2Ptr(bh_data, op); memcpy(bh_data, rhdr, op); if (!idx) { u16 t16; fixup = Add2Ptr(bh_data, fo); sample = *fixup; t16 = le16_to_cpu(sample); if (t16 >= 0x7FFF) { sample = *fixup = cpu_to_le16(1); } else { sample = cpu_to_le16(t16 + 1); *fixup = sample; } *(__le16 *)Add2Ptr(rhdr, fo) = sample; } ptr = Add2Ptr(bh_data, SECTOR_SIZE - sizeof(short)); do { *++fixup = *ptr; *ptr = sample; ptr += SECTOR_SIZE / sizeof(short); } while (ptr < end_data); set_buffer_uptodate(bh); mark_buffer_dirty(bh); unlock_buffer(bh); if (sync) { int err2 = sync_dirty_buffer(bh); if (!err && err2) err = err2; } bytes -= op; rhdr = Add2Ptr(rhdr, op); } return err; } /* * ntfs_bio_pages - Read/write pages from/to disk. */ int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run, struct page **pages, u32 nr_pages, u64 vbo, u32 bytes, enum req_op op) { int err = 0; struct bio *new, *bio = NULL; struct super_block *sb = sbi->sb; struct block_device *bdev = sb->s_bdev; struct page *page; u8 cluster_bits = sbi->cluster_bits; CLST lcn, clen, vcn, vcn_next; u32 add, off, page_idx; u64 lbo, len; size_t run_idx; struct blk_plug plug; if (!bytes) return 0; blk_start_plug(&plug); /* Align vbo and bytes to be 512 bytes aligned. */ lbo = (vbo + bytes + 511) & ~511ull; vbo = vbo & ~511ull; bytes = lbo - vbo; vcn = vbo >> cluster_bits; if (!run_lookup_entry(run, vcn, &lcn, &clen, &run_idx)) { err = -ENOENT; goto out; } off = vbo & sbi->cluster_mask; page_idx = 0; page = pages[0]; for (;;) { lbo = ((u64)lcn << cluster_bits) + off; len = ((u64)clen << cluster_bits) - off; new_bio: new = bio_alloc(bdev, nr_pages - page_idx, op, GFP_NOFS); if (bio) { bio_chain(bio, new); submit_bio(bio); } bio = new; bio->bi_iter.bi_sector = lbo >> 9; while (len) { off = vbo & (PAGE_SIZE - 1); add = off + len > PAGE_SIZE ? (PAGE_SIZE - off) : len; if (bio_add_page(bio, page, add, off) < add) goto new_bio; if (bytes <= add) goto out; bytes -= add; vbo += add; if (add + off == PAGE_SIZE) { page_idx += 1; if (WARN_ON(page_idx >= nr_pages)) { err = -EINVAL; goto out; } page = pages[page_idx]; } if (len <= add) break; len -= add; lbo += add; } vcn_next = vcn + clen; if (!run_get_entry(run, ++run_idx, &vcn, &lcn, &clen) || vcn != vcn_next) { err = -ENOENT; goto out; } off = 0; } out: if (bio) { if (!err) err = submit_bio_wait(bio); bio_put(bio); } blk_finish_plug(&plug); return err; } /* * ntfs_bio_fill_1 - Helper for ntfs_loadlog_and_replay(). * * Fill on-disk logfile range by (-1) * this means empty logfile. */ int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run) { int err = 0; struct super_block *sb = sbi->sb; struct block_device *bdev = sb->s_bdev; u8 cluster_bits = sbi->cluster_bits; struct bio *new, *bio = NULL; CLST lcn, clen; u64 lbo, len; size_t run_idx; struct page *fill; void *kaddr; struct blk_plug plug; fill = alloc_page(GFP_KERNEL); if (!fill) return -ENOMEM; kaddr = kmap_atomic(fill); memset(kaddr, -1, PAGE_SIZE); kunmap_atomic(kaddr); flush_dcache_page(fill); lock_page(fill); if (!run_lookup_entry(run, 0, &lcn, &clen, &run_idx)) { err = -ENOENT; goto out; } /* * TODO: Try blkdev_issue_write_same. */ blk_start_plug(&plug); do { lbo = (u64)lcn << cluster_bits; len = (u64)clen << cluster_bits; new_bio: new = bio_alloc(bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOFS); if (bio) { bio_chain(bio, new); submit_bio(bio); } bio = new; bio->bi_iter.bi_sector = lbo >> 9; for (;;) { u32 add = len > PAGE_SIZE ? PAGE_SIZE : len; if (bio_add_page(bio, fill, add, 0) < add) goto new_bio; lbo += add; if (len <= add) break; len -= add; } } while (run_get_entry(run, ++run_idx, NULL, &lcn, &clen)); if (!err) err = submit_bio_wait(bio); bio_put(bio); blk_finish_plug(&plug); out: unlock_page(fill); put_page(fill); return err; } int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, u64 *lbo, u64 *bytes) { u32 off; CLST lcn, len; u8 cluster_bits = sbi->cluster_bits; if (!run_lookup_entry(run, vbo >> cluster_bits, &lcn, &len, NULL)) return -ENOENT; off = vbo & sbi->cluster_mask; *lbo = lcn == SPARSE_LCN ? -1 : (((u64)lcn << cluster_bits) + off); *bytes = ((u64)len << cluster_bits) - off; return 0; } struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, enum RECORD_FLAG flag) { int err = 0; struct super_block *sb = sbi->sb; struct inode *inode = new_inode(sb); struct ntfs_inode *ni; if (!inode) return ERR_PTR(-ENOMEM); ni = ntfs_i(inode); err = mi_format_new(&ni->mi, sbi, rno, flag, false); if (err) goto out; inode->i_ino = rno; if (insert_inode_locked(inode) < 0) { err = -EIO; goto out; } out: if (err) { make_bad_inode(inode); iput(inode); ni = ERR_PTR(err); } return ni; } /* * O:BAG:BAD:(A;OICI;FA;;;WD) * Owner S-1-5-32-544 (Administrators) * Group S-1-5-32-544 (Administrators) * ACE: allow S-1-1-0 (Everyone) with FILE_ALL_ACCESS */ const u8 s_default_security[] __aligned(8) = { 0x01, 0x00, 0x04, 0x80, 0x30, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x02, 0x00, 0x1C, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x03, 0x14, 0x00, 0xFF, 0x01, 0x1F, 0x00, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x20, 0x00, 0x00, 0x00, 0x20, 0x02, 0x00, 0x00, 0x01, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x20, 0x00, 0x00, 0x00, 0x20, 0x02, 0x00, 0x00, }; static_assert(sizeof(s_default_security) == 0x50); static inline u32 sid_length(const struct SID *sid) { return struct_size(sid, SubAuthority, sid->SubAuthorityCount); } /* * is_acl_valid * * Thanks Mark Harmstone for idea. */ static bool is_acl_valid(const struct ACL *acl, u32 len) { const struct ACE_HEADER *ace; u32 i; u16 ace_count, ace_size; if (acl->AclRevision != ACL_REVISION && acl->AclRevision != ACL_REVISION_DS) { /* * This value should be ACL_REVISION, unless the ACL contains an * object-specific ACE, in which case this value must be ACL_REVISION_DS. * All ACEs in an ACL must be at the same revision level. */ return false; } if (acl->Sbz1) return false; if (le16_to_cpu(acl->AclSize) > len) return false; if (acl->Sbz2) return false; len -= sizeof(struct ACL); ace = (struct ACE_HEADER *)&acl[1]; ace_count = le16_to_cpu(acl->AceCount); for (i = 0; i < ace_count; i++) { if (len < sizeof(struct ACE_HEADER)) return false; ace_size = le16_to_cpu(ace->AceSize); if (len < ace_size) return false; len -= ace_size; ace = Add2Ptr(ace, ace_size); } return true; } bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len) { u32 sd_owner, sd_group, sd_sacl, sd_dacl; if (len < sizeof(struct SECURITY_DESCRIPTOR_RELATIVE)) return false; if (sd->Revision != 1) return false; if (sd->Sbz1) return false; if (!(sd->Control & SE_SELF_RELATIVE)) return false; sd_owner = le32_to_cpu(sd->Owner); if (sd_owner) { const struct SID *owner = Add2Ptr(sd, sd_owner); if (sd_owner + offsetof(struct SID, SubAuthority) > len) return false; if (owner->Revision != 1) return false; if (sd_owner + sid_length(owner) > len) return false; } sd_group = le32_to_cpu(sd->Group); if (sd_group) { const struct SID *group = Add2Ptr(sd, sd_group); if (sd_group + offsetof(struct SID, SubAuthority) > len) return false; if (group->Revision != 1) return false; if (sd_group + sid_length(group) > len) return false; } sd_sacl = le32_to_cpu(sd->Sacl); if (sd_sacl) { const struct ACL *sacl = Add2Ptr(sd, sd_sacl); if (sd_sacl + sizeof(struct ACL) > len) return false; if (!is_acl_valid(sacl, len - sd_sacl)) return false; } sd_dacl = le32_to_cpu(sd->Dacl); if (sd_dacl) { const struct ACL *dacl = Add2Ptr(sd, sd_dacl); if (sd_dacl + sizeof(struct ACL) > len) return false; if (!is_acl_valid(dacl, len - sd_dacl)) return false; } return true; } /* * ntfs_security_init - Load and parse $Secure. */ int ntfs_security_init(struct ntfs_sb_info *sbi) { int err; struct super_block *sb = sbi->sb; struct inode *inode; struct ntfs_inode *ni; struct MFT_REF ref; struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le; u64 sds_size; size_t off; struct NTFS_DE *ne; struct NTFS_DE_SII *sii_e; struct ntfs_fnd *fnd_sii = NULL; const struct INDEX_ROOT *root_sii; const struct INDEX_ROOT *root_sdh; struct ntfs_index *indx_sdh = &sbi->security.index_sdh; struct ntfs_index *indx_sii = &sbi->security.index_sii; ref.low = cpu_to_le32(MFT_REC_SECURE); ref.high = 0; ref.seq = cpu_to_le16(MFT_REC_SECURE); inode = ntfs_iget5(sb, &ref, &NAME_SECURE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ntfs_err(sb, "Failed to load $Secure (%d).", err); inode = NULL; goto out; } ni = ntfs_i(inode); le = NULL; attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SDH_NAME, ARRAY_SIZE(SDH_NAME), NULL, NULL); if (!attr || !(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root_sdh->ihdr.used) > le32_to_cpu(attr->res.data_size)) { ntfs_err(sb, "$Secure::$SDH is corrupted."); err = -EINVAL; goto out; } err = indx_init(indx_sdh, sbi, attr, INDEX_MUTEX_SDH); if (err) { ntfs_err(sb, "Failed to initialize $Secure::$SDH (%d).", err); goto out; } attr = ni_find_attr(ni, attr, &le, ATTR_ROOT, SII_NAME, ARRAY_SIZE(SII_NAME), NULL, NULL); if (!attr || !(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root_sii->ihdr.used) > le32_to_cpu(attr->res.data_size)) { ntfs_err(sb, "$Secure::$SII is corrupted."); err = -EINVAL; goto out; } err = indx_init(indx_sii, sbi, attr, INDEX_MUTEX_SII); if (err) { ntfs_err(sb, "Failed to initialize $Secure::$SII (%d).", err); goto out; } fnd_sii = fnd_get(); if (!fnd_sii) { err = -ENOMEM; goto out; } sds_size = inode->i_size; /* Find the last valid Id. */ sbi->security.next_id = SECURITY_ID_FIRST; /* Always write new security at the end of bucket. */ sbi->security.next_off = ALIGN(sds_size - SecurityDescriptorsBlockSize, 16); off = 0; ne = NULL; for (;;) { u32 next_id; err = indx_find_raw(indx_sii, ni, root_sii, &ne, &off, fnd_sii); if (err || !ne) break; sii_e = (struct NTFS_DE_SII *)ne; if (le16_to_cpu(ne->view.data_size) < sizeof(sii_e->sec_hdr)) continue; next_id = le32_to_cpu(sii_e->sec_id) + 1; if (next_id >= sbi->security.next_id) sbi->security.next_id = next_id; } sbi->security.ni = ni; inode = NULL; out: iput(inode); fnd_put(fnd_sii); return err; } /* * ntfs_get_security_by_id - Read security descriptor by id. */ int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, struct SECURITY_DESCRIPTOR_RELATIVE **sd, size_t *size) { int err; int diff; struct ntfs_inode *ni = sbi->security.ni; struct ntfs_index *indx = &sbi->security.index_sii; void *p = NULL; struct NTFS_DE_SII *sii_e; struct ntfs_fnd *fnd_sii; struct SECURITY_HDR d_security; const struct INDEX_ROOT *root_sii; u32 t32; *sd = NULL; mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY); fnd_sii = fnd_get(); if (!fnd_sii) { err = -ENOMEM; goto out; } root_sii = indx_get_root(indx, ni, NULL, NULL); if (!root_sii) { err = -EINVAL; goto out; } /* Try to find this SECURITY descriptor in SII indexes. */ err = indx_find(indx, ni, root_sii, &security_id, sizeof(security_id), NULL, &diff, (struct NTFS_DE **)&sii_e, fnd_sii); if (err) goto out; if (diff) goto out; t32 = le32_to_cpu(sii_e->sec_hdr.size); if (t32 < sizeof(struct SECURITY_HDR)) { err = -EINVAL; goto out; } if (t32 > sizeof(struct SECURITY_HDR) + 0x10000) { /* Looks like too big security. 0x10000 - is arbitrary big number. */ err = -EFBIG; goto out; } *size = t32 - sizeof(struct SECURITY_HDR); p = kmalloc(*size, GFP_NOFS); if (!p) { err = -ENOMEM; goto out; } err = ntfs_read_run_nb(sbi, &ni->file.run, le64_to_cpu(sii_e->sec_hdr.off), &d_security, sizeof(d_security), NULL); if (err) goto out; if (memcmp(&d_security, &sii_e->sec_hdr, sizeof(d_security))) { err = -EINVAL; goto out; } err = ntfs_read_run_nb(sbi, &ni->file.run, le64_to_cpu(sii_e->sec_hdr.off) + sizeof(struct SECURITY_HDR), p, *size, NULL); if (err) goto out; *sd = p; p = NULL; out: kfree(p); fnd_put(fnd_sii); ni_unlock(ni); return err; } /* * ntfs_insert_security - Insert security descriptor into $Secure::SDS. * * SECURITY Descriptor Stream data is organized into chunks of 256K bytes * and it contains a mirror copy of each security descriptor. When writing * to a security descriptor at location X, another copy will be written at * location (X+256K). * When writing a security descriptor that will cross the 256K boundary, * the pointer will be advanced by 256K to skip * over the mirror portion. */ int ntfs_insert_security(struct ntfs_sb_info *sbi, const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 size_sd, __le32 *security_id, bool *inserted) { int err, diff; struct ntfs_inode *ni = sbi->security.ni; struct ntfs_index *indx_sdh = &sbi->security.index_sdh; struct ntfs_index *indx_sii = &sbi->security.index_sii; struct NTFS_DE_SDH *e; struct NTFS_DE_SDH sdh_e; struct NTFS_DE_SII sii_e; struct SECURITY_HDR *d_security; u32 new_sec_size = size_sd + sizeof(struct SECURITY_HDR); u32 aligned_sec_size = ALIGN(new_sec_size, 16); struct SECURITY_KEY hash_key; struct ntfs_fnd *fnd_sdh = NULL; const struct INDEX_ROOT *root_sdh; const struct INDEX_ROOT *root_sii; u64 mirr_off, new_sds_size; u32 next, left; static_assert((1 << Log2OfSecurityDescriptorsBlockSize) == SecurityDescriptorsBlockSize); hash_key.hash = security_hash(sd, size_sd); hash_key.sec_id = SECURITY_ID_INVALID; if (inserted) *inserted = false; *security_id = SECURITY_ID_INVALID; /* Allocate a temporal buffer. */ d_security = kzalloc(aligned_sec_size, GFP_NOFS); if (!d_security) return -ENOMEM; mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_SECURITY); fnd_sdh = fnd_get(); if (!fnd_sdh) { err = -ENOMEM; goto out; } root_sdh = indx_get_root(indx_sdh, ni, NULL, NULL); if (!root_sdh) { err = -EINVAL; goto out; } root_sii = indx_get_root(indx_sii, ni, NULL, NULL); if (!root_sii) { err = -EINVAL; goto out; } /* * Check if such security already exists. * Use "SDH" and hash -> to get the offset in "SDS". */ err = indx_find(indx_sdh, ni, root_sdh, &hash_key, sizeof(hash_key), &d_security->key.sec_id, &diff, (struct NTFS_DE **)&e, fnd_sdh); if (err) goto out; while (e) { if (le32_to_cpu(e->sec_hdr.size) == new_sec_size) { err = ntfs_read_run_nb(sbi, &ni->file.run, le64_to_cpu(e->sec_hdr.off), d_security, new_sec_size, NULL); if (err) goto out; if (le32_to_cpu(d_security->size) == new_sec_size && d_security->key.hash == hash_key.hash && !memcmp(d_security + 1, sd, size_sd)) { /* Such security already exists. */ *security_id = d_security->key.sec_id; err = 0; goto out; } } err = indx_find_sort(indx_sdh, ni, root_sdh, (struct NTFS_DE **)&e, fnd_sdh); if (err) goto out; if (!e || e->key.hash != hash_key.hash) break; } /* Zero unused space. */ next = sbi->security.next_off & (SecurityDescriptorsBlockSize - 1); left = SecurityDescriptorsBlockSize - next; /* Zero gap until SecurityDescriptorsBlockSize. */ if (left < new_sec_size) { /* Zero "left" bytes from sbi->security.next_off. */ sbi->security.next_off += SecurityDescriptorsBlockSize + left; } /* Zero tail of previous security. */ //used = ni->vfs_inode.i_size & (SecurityDescriptorsBlockSize - 1); /* * Example: * 0x40438 == ni->vfs_inode.i_size * 0x00440 == sbi->security.next_off * need to zero [0x438-0x440) * if (next > used) { * u32 tozero = next - used; * zero "tozero" bytes from sbi->security.next_off - tozero */ /* Format new security descriptor. */ d_security->key.hash = hash_key.hash; d_security->key.sec_id = cpu_to_le32(sbi->security.next_id); d_security->off = cpu_to_le64(sbi->security.next_off); d_security->size = cpu_to_le32(new_sec_size); memcpy(d_security + 1, sd, size_sd); /* Write main SDS bucket. */ err = ntfs_sb_write_run(sbi, &ni->file.run, sbi->security.next_off, d_security, aligned_sec_size, 0); if (err) goto out; mirr_off = sbi->security.next_off + SecurityDescriptorsBlockSize; new_sds_size = mirr_off + aligned_sec_size; if (new_sds_size > ni->vfs_inode.i_size) { err = attr_set_size(ni, ATTR_DATA, SDS_NAME, ARRAY_SIZE(SDS_NAME), &ni->file.run, new_sds_size, &new_sds_size, false, NULL); if (err) goto out; } /* Write copy SDS bucket. */ err = ntfs_sb_write_run(sbi, &ni->file.run, mirr_off, d_security, aligned_sec_size, 0); if (err) goto out; /* Fill SII entry. */ sii_e.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_SII, sec_hdr)); sii_e.de.view.data_size = cpu_to_le16(sizeof(struct SECURITY_HDR)); sii_e.de.view.res = 0; sii_e.de.size = cpu_to_le16(sizeof(struct NTFS_DE_SII)); sii_e.de.key_size = cpu_to_le16(sizeof(d_security->key.sec_id)); sii_e.de.flags = 0; sii_e.de.res = 0; sii_e.sec_id = d_security->key.sec_id; memcpy(&sii_e.sec_hdr, d_security, sizeof(struct SECURITY_HDR)); err = indx_insert_entry(indx_sii, ni, &sii_e.de, NULL, NULL, 0); if (err) goto out; /* Fill SDH entry. */ sdh_e.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_SDH, sec_hdr)); sdh_e.de.view.data_size = cpu_to_le16(sizeof(struct SECURITY_HDR)); sdh_e.de.view.res = 0; sdh_e.de.size = cpu_to_le16(SIZEOF_SDH_DIRENTRY); sdh_e.de.key_size = cpu_to_le16(sizeof(sdh_e.key)); sdh_e.de.flags = 0; sdh_e.de.res = 0; sdh_e.key.hash = d_security->key.hash; sdh_e.key.sec_id = d_security->key.sec_id; memcpy(&sdh_e.sec_hdr, d_security, sizeof(struct SECURITY_HDR)); sdh_e.magic[0] = cpu_to_le16('I'); sdh_e.magic[1] = cpu_to_le16('I'); fnd_clear(fnd_sdh); err = indx_insert_entry(indx_sdh, ni, &sdh_e.de, (void *)(size_t)1, fnd_sdh, 0); if (err) goto out; *security_id = d_security->key.sec_id; if (inserted) *inserted = true; /* Update Id and offset for next descriptor. */ sbi->security.next_id += 1; sbi->security.next_off += aligned_sec_size; out: fnd_put(fnd_sdh); mark_inode_dirty(&ni->vfs_inode); ni_unlock(ni); kfree(d_security); return err; } /* * ntfs_reparse_init - Load and parse $Extend/$Reparse. */ int ntfs_reparse_init(struct ntfs_sb_info *sbi) { int err; struct ntfs_inode *ni = sbi->reparse.ni; struct ntfs_index *indx = &sbi->reparse.index_r; struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le; const struct INDEX_ROOT *root_r; if (!ni) return 0; le = NULL; attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SR_NAME, ARRAY_SIZE(SR_NAME), NULL, NULL); if (!attr) { err = -EINVAL; goto out; } root_r = resident_data(attr); if (root_r->type != ATTR_ZERO || root_r->rule != NTFS_COLLATION_TYPE_UINTS) { err = -EINVAL; goto out; } err = indx_init(indx, sbi, attr, INDEX_MUTEX_SR); if (err) goto out; out: return err; } /* * ntfs_objid_init - Load and parse $Extend/$ObjId. */ int ntfs_objid_init(struct ntfs_sb_info *sbi) { int err; struct ntfs_inode *ni = sbi->objid.ni; struct ntfs_index *indx = &sbi->objid.index_o; struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le; const struct INDEX_ROOT *root; if (!ni) return 0; le = NULL; attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SO_NAME, ARRAY_SIZE(SO_NAME), NULL, NULL); if (!attr) { err = -EINVAL; goto out; } root = resident_data(attr); if (root->type != ATTR_ZERO || root->rule != NTFS_COLLATION_TYPE_UINTS) { err = -EINVAL; goto out; } err = indx_init(indx, sbi, attr, INDEX_MUTEX_SO); if (err) goto out; out: return err; } int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid) { int err; struct ntfs_inode *ni = sbi->objid.ni; struct ntfs_index *indx = &sbi->objid.index_o; if (!ni) return -EINVAL; mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_OBJID); err = indx_delete_entry(indx, ni, guid, sizeof(*guid), NULL); mark_inode_dirty(&ni->vfs_inode); ni_unlock(ni); return err; } int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, const struct MFT_REF *ref) { int err; struct ntfs_inode *ni = sbi->reparse.ni; struct ntfs_index *indx = &sbi->reparse.index_r; struct NTFS_DE_R re; if (!ni) return -EINVAL; memset(&re, 0, sizeof(re)); re.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_R, zero)); re.de.size = cpu_to_le16(sizeof(struct NTFS_DE_R)); re.de.key_size = cpu_to_le16(sizeof(re.key)); re.key.ReparseTag = rtag; memcpy(&re.key.ref, ref, sizeof(*ref)); mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE); err = indx_insert_entry(indx, ni, &re.de, NULL, NULL, 0); mark_inode_dirty(&ni->vfs_inode); ni_unlock(ni); return err; } int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, const struct MFT_REF *ref) { int err, diff; struct ntfs_inode *ni = sbi->reparse.ni; struct ntfs_index *indx = &sbi->reparse.index_r; struct ntfs_fnd *fnd = NULL; struct REPARSE_KEY rkey; struct NTFS_DE_R *re; struct INDEX_ROOT *root_r; if (!ni) return -EINVAL; rkey.ReparseTag = rtag; rkey.ref = *ref; mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_REPARSE); if (rtag) { err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL); goto out1; } fnd = fnd_get(); if (!fnd) { err = -ENOMEM; goto out1; } root_r = indx_get_root(indx, ni, NULL, NULL); if (!root_r) { err = -EINVAL; goto out; } /* 1 - forces to ignore rkey.ReparseTag when comparing keys. */ err = indx_find(indx, ni, root_r, &rkey, sizeof(rkey), (void *)1, &diff, (struct NTFS_DE **)&re, fnd); if (err) goto out; if (memcmp(&re->key.ref, ref, sizeof(*ref))) { /* Impossible. Looks like volume corrupt? */ goto out; } memcpy(&rkey, &re->key, sizeof(rkey)); fnd_put(fnd); fnd = NULL; err = indx_delete_entry(indx, ni, &rkey, sizeof(rkey), NULL); if (err) goto out; out: fnd_put(fnd); out1: mark_inode_dirty(&ni->vfs_inode); ni_unlock(ni); return err; } static inline void ntfs_unmap_and_discard(struct ntfs_sb_info *sbi, CLST lcn, CLST len) { ntfs_unmap_meta(sbi->sb, lcn, len); ntfs_discard(sbi, lcn, len); } void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; bool dirty = false; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); if (!wnd_is_used(wnd, lcn, len)) { /* mark volume as dirty out of wnd->rw_lock */ dirty = true; end = lcn + len; len = 0; for (i = lcn; i < end; i++) { if (wnd_is_used(wnd, i, 1)) { if (!len) lcn = i; len += 1; continue; } if (!len) continue; if (trim) ntfs_unmap_and_discard(sbi, lcn, len); wnd_set_free(wnd, lcn, len); len = 0; } if (!len) goto out; } if (trim) ntfs_unmap_and_discard(sbi, lcn, len); wnd_set_free(wnd, lcn, len); /* append to MFT zone, if possible. */ zone_len = wnd_zone_len(wnd); zlen = min(zone_len + len, sbi->zone_max); if (zlen == zone_len) { /* MFT zone already has maximum size. */ } else if (!zone_len) { /* Create MFT zone only if 'zlen' is large enough. */ if (zlen == sbi->zone_max) wnd_zone_set(wnd, lcn, zlen); } else { CLST zone_lcn = wnd_zone_bit(wnd); if (lcn + len == zone_lcn) { /* Append into head MFT zone. */ wnd_zone_set(wnd, lcn, zlen); } else if (zone_lcn + zone_len == lcn) { /* Append into tail MFT zone. */ wnd_zone_set(wnd, zone_lcn, zlen); } } out: up_write(&wnd->rw_lock); if (dirty) ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* * run_deallocate - Deallocate clusters. */ int run_deallocate(struct ntfs_sb_info *sbi, const struct runs_tree *run, bool trim) { CLST lcn, len; size_t idx = 0; while (run_get_entry(run, idx++, NULL, &lcn, &len)) { if (lcn == SPARSE_LCN) continue; mark_as_free_ex(sbi, lcn, len, trim); } return 0; } static inline bool name_has_forbidden_chars(const struct le_str *fname) { int i, ch; /* check for forbidden chars */ for (i = 0; i < fname->len; ++i) { ch = le16_to_cpu(fname->name[i]); /* control chars */ if (ch < 0x20) return true; switch (ch) { /* disallowed by Windows */ case '\\': case '/': case ':': case '*': case '?': case '<': case '>': case '|': case '\"': return true; default: /* allowed char */ break; } } /* file names cannot end with space or . */ if (fname->len > 0) { ch = le16_to_cpu(fname->name[fname->len - 1]); if (ch == ' ' || ch == '.') return true; } return false; } static inline bool is_reserved_name(const struct ntfs_sb_info *sbi, const struct le_str *fname) { int port_digit; const __le16 *name = fname->name; int len = fname->len; const u16 *upcase = sbi->upcase; /* check for 3 chars reserved names (device names) */ /* name by itself or with any extension is forbidden */ if (len == 3 || (len > 3 && le16_to_cpu(name[3]) == '.')) if (!ntfs_cmp_names(name, 3, CON_NAME, 3, upcase, false) || !ntfs_cmp_names(name, 3, NUL_NAME, 3, upcase, false) || !ntfs_cmp_names(name, 3, AUX_NAME, 3, upcase, false) || !ntfs_cmp_names(name, 3, PRN_NAME, 3, upcase, false)) return true; /* check for 4 chars reserved names (port name followed by 1..9) */ /* name by itself or with any extension is forbidden */ if (len == 4 || (len > 4 && le16_to_cpu(name[4]) == '.')) { port_digit = le16_to_cpu(name[3]); if (port_digit >= '1' && port_digit <= '9') if (!ntfs_cmp_names(name, 3, COM_NAME, 3, upcase, false) || !ntfs_cmp_names(name, 3, LPT_NAME, 3, upcase, false)) return true; } return false; } /* * valid_windows_name - Check if a file name is valid in Windows. */ bool valid_windows_name(struct ntfs_sb_info *sbi, const struct le_str *fname) { return !name_has_forbidden_chars(fname) && !is_reserved_name(sbi, fname); } /* * ntfs_set_label - updates current ntfs label. */ int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len) { int err; struct ATTRIB *attr; u32 uni_bytes; struct ntfs_inode *ni = sbi->volume.ni; /* Allocate PATH_MAX bytes. */ struct cpu_str *uni = __getname(); if (!uni) return -ENOMEM; err = ntfs_nls_to_utf16(sbi, label, len, uni, (PATH_MAX - 2) / 2, UTF16_LITTLE_ENDIAN); if (err < 0) goto out; uni_bytes = uni->len * sizeof(u16); if (uni_bytes > NTFS_LABEL_MAX_LENGTH * sizeof(u16)) { ntfs_warn(sbi->sb, "new label is too long"); err = -EFBIG; goto out; } ni_lock(ni); /* Ignore any errors. */ ni_remove_attr(ni, ATTR_LABEL, NULL, 0, false, NULL); err = ni_insert_resident(ni, uni_bytes, ATTR_LABEL, NULL, 0, &attr, NULL, NULL); if (err < 0) goto unlock_out; /* write new label in on-disk struct. */ memcpy(resident_data(attr), uni->name, uni_bytes); /* update cached value of current label. */ if (len >= ARRAY_SIZE(sbi->volume.label)) len = ARRAY_SIZE(sbi->volume.label) - 1; memcpy(sbi->volume.label, label, len); sbi->volume.label[len] = 0; mark_inode_dirty_sync(&ni->vfs_inode); unlock_out: ni_unlock(ni); if (!err) err = _ni_write_inode(&ni->vfs_inode, 0); out: __putname(uni); return err; } |
| 3333 3328 3325 12 3291 792 789 686 686 686 783 783 783 776 1 777 776 770 770 769 790 789 790 791 8 786 787 1 661 661 73 72 16 202 203 674 3139 3136 1746 3283 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H /* Avoid a dependency loop by declaring here. */ extern int rcuwait_wake_up(struct rcuwait *w); #include <linux/lockdep.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/rwsem.h> #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> #include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), DECLARE_TRACEPOINT(mmap_lock_start_locking); DECLARE_TRACEPOINT(mmap_lock_acquire_returned); DECLARE_TRACEPOINT(mmap_lock_released); #ifdef CONFIG_TRACING void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write); static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_start_locking)) __mmap_lock_do_trace_start_locking(mm, write); } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { if (tracepoint_enabled(mmap_lock_acquire_returned)) __mmap_lock_do_trace_acquire_returned(mm, write, success); } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_released)) __mmap_lock_do_trace_released(mm, write); } #else /* !CONFIG_TRACING */ static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { } #endif /* CONFIG_TRACING */ static inline void mmap_assert_locked(const struct mm_struct *mm) { rwsem_assert_held(&mm->mmap_lock); } static inline void mmap_assert_write_locked(const struct mm_struct *mm) { rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK static inline void mm_lock_seqcount_init(struct mm_struct *mm) { seqcount_init(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_begin(struct mm_struct *mm) { do_raw_write_seqcount_begin(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_end(struct mm_struct *mm) { ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq); do_raw_write_seqcount_end(&mm->mm_lock_seq); } static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { /* * Since mmap_lock is a sleeping lock, and waiting for it to become * unlocked is more or less equivalent with taking it ourselves, don't * bother with the speculative path if mmap_lock is already write-locked * and take the slow path, which takes the lock. */ return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq); } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return read_seqcount_retry(&mm->mm_lock_seq, seq); } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) { #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key lockdep_key; lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); #endif if (reset_refcnt) refcount_set(&vma->vm_refcnt, 0); vma->vm_lock_seq = UINT_MAX; } static inline bool is_vma_writer_only(int refcnt) { /* * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on * a detached vma happens only in vma_mark_detached() and is a rare * case, therefore most of the time there will be no unnecessary wakeup. */ return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; } static inline void vma_refcount_put(struct vm_area_struct *vma) { /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ struct mm_struct *mm = vma->vm_mm; int oldcnt; rwsem_release(&vma->vmlock_dep_map, _RET_IP_); if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { if (is_vma_writer_only(oldcnt - 1)) rcuwait_wake_up(&mm->vma_writer_wait); } } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { int oldcnt; mmap_assert_locked(vma->vm_mm); if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VMA_REF_LIMIT))) return false; rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); return true; } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked(struct vm_area_struct *vma) { return vma_start_read_locked_nested(vma, 0); } static inline void vma_end_read(struct vm_area_struct *vma) { vma_refcount_put(vma); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ static bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq) { mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ *mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence; return (vma->vm_lock_seq == *mm_lock_seq); } void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq); /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { unsigned int mm_lock_seq; if (__is_vma_write_locked(vma, &mm_lock_seq)) return; __vma_start_write(vma, mm_lock_seq); } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { unsigned int mm_lock_seq; VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } static inline void vma_assert_locked(struct vm_area_struct *vma) { unsigned int mm_lock_seq; VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && !__is_vma_write_locked(vma, &mm_lock_seq), vma); } /* * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these * assertions should be made either under mmap_write_lock or when the object * has been isolated under mmap_write_lock, ensuring no competing writers. */ static inline void vma_assert_attached(struct vm_area_struct *vma) { WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); } static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); refcount_set_release(&vma->vm_refcnt, 1); } void vma_mark_detached(struct vm_area_struct *vma); struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); /* * Locks next vma pointed by the iterator. Confirms the locked vma has not * been modified and will retry under mmap_lock protection if modification * was detected. Should be called from read RCU section. * Returns either a valid locked VMA, NULL if no more VMAs or -EINTR if the * process was interrupted. */ struct vm_area_struct *lock_next_vma(struct mm_struct *mm, struct vma_iterator *iter, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {} static inline void mm_lock_seqcount_end(struct mm_struct *mm) {} static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { return false; } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return true; } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) { return NULL; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_assert_attached(struct vm_area_struct *vma) {} static inline void vma_assert_detached(struct vm_area_struct *vma) {} static inline void vma_mark_attached(struct vm_area_struct *vma) {} static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); if (!ret) mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } /* * Drop all currently-held per-VMA locks. * This is called from the mmap_lock implementation directly before releasing * a write-locked mmap_lock (or downgrading it to read-locked). * This should normally NOT be called manually from other places. * If you want to call this manually anyway, keep in mind that this will release * *all* VMA write locks, including ones from further up the stack. */ static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); mm_lock_seqcount_end(mm); } static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, false); down_read(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, true); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_killable(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, ret == 0); return ret; } static inline bool mmap_read_trylock(struct mm_struct *mm) { bool ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_trylock(&mm->mmap_lock) != 0; __mmap_lock_trace_acquire_returned(mm, false, ret); return ret; } static inline void mmap_read_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read(&mm->mmap_lock); } DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read_non_owner(&mm->mmap_lock); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 1 1 328 328 1 1 1 1 1 1 1 1 1 1 1 450 450 450 2 4 4 341 12 338 451 450 439 154 2 450 451 439 1 1 430 1 2 2 1 1 142 438 25 310 318 318 310 318 149 188 188 188 450 2 450 1 437 436 1 1 439 439 137 139 148 148 139 151 2 2 2 2 1 438 451 451 30 438 317 150 2 310 150 150 187 187 125 163 23 23 1 1 439 438 1 439 450 449 1 2 451 151 30 1 439 1 433 434 1 1 450 448 449 448 1 32 81 183 434 173 166 416 431 433 113 104 34 433 426 75 276 277 277 94 94 307 308 94 277 277 300 300 300 89 268 148 148 148 148 147 148 148 148 148 148 147 112 135 148 148 148 148 148 1 1 1 1 136 137 137 137 113 54 137 137 1 1 1 137 137 137 137 430 433 27 430 326 328 328 328 328 291 292 261 261 172 172 36 36 5 5 2 25 25 25 25 25 7 19 12 20 17 25 60 36 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 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 | // 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_bit.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_btree.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_alloc.h" #include "xfs_log.h" #include "xfs_btree_staging.h" #include "xfs_ag.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc_btree.h" #include "xfs_bmap_btree.h" #include "xfs_rmap_btree.h" #include "xfs_refcount_btree.h" #include "xfs_health.h" #include "xfs_buf_mem.h" #include "xfs_btree_mem.h" #include "xfs_rtrmap_btree.h" #include "xfs_bmap.h" #include "xfs_rmap.h" #include "xfs_quota.h" #include "xfs_metafile.h" #include "xfs_rtrefcount_btree.h" /* * Btree magic numbers. */ uint32_t xfs_btree_magic( struct xfs_mount *mp, const struct xfs_btree_ops *ops) { int idx = xfs_has_crc(mp) ? 1 : 0; __be32 magic = ops->buf_ops->magic[idx]; /* Ensure we asked for crc for crc-only magics. */ ASSERT(magic != 0); return be32_to_cpu(magic); } /* * These sibling pointer checks are optimised for null sibling pointers. This * happens a lot, and we don't need to byte swap at runtime if the sibling * pointer is NULL. * * These are explicitly marked at inline because the cost of calling them as * functions instead of inlining them is about 36 bytes extra code per call site * on x86-64. Yes, gcc-11 fails to inline them, and explicit inlining of these * two sibling check functions reduces the compiled code size by over 300 * bytes. */ static inline xfs_failaddr_t xfs_btree_check_fsblock_siblings( struct xfs_mount *mp, xfs_fsblock_t fsb, __be64 dsibling) { xfs_fsblock_t sibling; if (dsibling == cpu_to_be64(NULLFSBLOCK)) return NULL; sibling = be64_to_cpu(dsibling); if (sibling == fsb) return __this_address; if (!xfs_verify_fsbno(mp, sibling)) return __this_address; return NULL; } static inline xfs_failaddr_t xfs_btree_check_memblock_siblings( struct xfs_buftarg *btp, xfbno_t bno, __be64 dsibling) { xfbno_t sibling; if (dsibling == cpu_to_be64(NULLFSBLOCK)) return NULL; sibling = be64_to_cpu(dsibling); if (sibling == bno) return __this_address; if (!xmbuf_verify_daddr(btp, xfbno_to_daddr(sibling))) return __this_address; return NULL; } static inline xfs_failaddr_t xfs_btree_check_agblock_siblings( struct xfs_perag *pag, xfs_agblock_t agbno, __be32 dsibling) { xfs_agblock_t sibling; if (dsibling == cpu_to_be32(NULLAGBLOCK)) return NULL; sibling = be32_to_cpu(dsibling); if (sibling == agbno) return __this_address; if (!xfs_verify_agbno(pag, sibling)) return __this_address; return NULL; } static xfs_failaddr_t __xfs_btree_check_lblock_hdr( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; if (xfs_has_crc(mp)) { if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (block->bb_u.l.bb_blkno != cpu_to_be64(bp ? xfs_buf_daddr(bp) : XFS_BUF_DADDR_NULL)) return __this_address; if (block->bb_u.l.bb_pad != cpu_to_be32(0)) return __this_address; } if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops)) return __this_address; if (be16_to_cpu(block->bb_level) != level) return __this_address; if (be16_to_cpu(block->bb_numrecs) > cur->bc_ops->get_maxrecs(cur, level)) return __this_address; return NULL; } /* * Check a long btree block header. Return the address of the failing check, * or NULL if everything is ok. */ static xfs_failaddr_t __xfs_btree_check_fsblock( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; xfs_failaddr_t fa; xfs_fsblock_t fsb; fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp); if (fa) return fa; /* * For inode-rooted btrees, the root block sits in the inode fork. In * that case bp is NULL, and the block must not have any siblings. */ if (!bp) { if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK)) return __this_address; if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK)) return __this_address; return NULL; } fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_leftsib); if (!fa) fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_rightsib); return fa; } /* * Check an in-memory btree block header. Return the address of the failing * check, or NULL if everything is ok. */ static xfs_failaddr_t __xfs_btree_check_memblock( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; xfs_failaddr_t fa; xfbno_t bno; fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp); if (fa) return fa; bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); fa = xfs_btree_check_memblock_siblings(btp, bno, block->bb_u.l.bb_leftsib); if (!fa) fa = xfs_btree_check_memblock_siblings(btp, bno, block->bb_u.l.bb_rightsib); return fa; } /* * Check a short btree block header. Return the address of the failing check, * or NULL if everything is ok. */ static xfs_failaddr_t __xfs_btree_check_agblock( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = to_perag(cur->bc_group); xfs_failaddr_t fa; xfs_agblock_t agbno; if (xfs_has_crc(mp)) { if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp))) return __this_address; } if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops)) return __this_address; if (be16_to_cpu(block->bb_level) != level) return __this_address; if (be16_to_cpu(block->bb_numrecs) > cur->bc_ops->get_maxrecs(cur, level)) return __this_address; agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); fa = xfs_btree_check_agblock_siblings(pag, agbno, block->bb_u.s.bb_leftsib); if (!fa) fa = xfs_btree_check_agblock_siblings(pag, agbno, block->bb_u.s.bb_rightsib); return fa; } /* * Internal btree block check. * * Return NULL if the block is ok or the address of the failed check otherwise. */ xfs_failaddr_t __xfs_btree_check_block( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *bp) { switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_MEM: return __xfs_btree_check_memblock(cur, block, level, bp); case XFS_BTREE_TYPE_AG: return __xfs_btree_check_agblock(cur, block, level, bp); case XFS_BTREE_TYPE_INODE: return __xfs_btree_check_fsblock(cur, block, level, bp); default: ASSERT(0); return __this_address; } } static inline unsigned int xfs_btree_block_errtag(struct xfs_btree_cur *cur) { if (cur->bc_ops->ptr_len == XFS_BTREE_SHORT_PTR_LEN) return XFS_ERRTAG_BTREE_CHECK_SBLOCK; return XFS_ERRTAG_BTREE_CHECK_LBLOCK; } /* * Debug routine: check that block header is ok. */ int xfs_btree_check_block( struct xfs_btree_cur *cur, /* btree cursor */ struct xfs_btree_block *block, /* generic btree block pointer */ int level, /* level of the btree block */ struct xfs_buf *bp) /* buffer containing block, if any */ { struct xfs_mount *mp = cur->bc_mp; xfs_failaddr_t fa; fa = __xfs_btree_check_block(cur, block, level, bp); if (XFS_IS_CORRUPT(mp, fa != NULL) || XFS_TEST_ERROR(mp, xfs_btree_block_errtag(cur))) { if (bp) trace_xfs_btree_corrupt(bp, _RET_IP_); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return 0; } int __xfs_btree_check_ptr( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, int index, int level) { if (level <= 0) return -EFSCORRUPTED; switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_MEM: if (!xfbtree_verify_bno(cur->bc_mem.xfbtree, be64_to_cpu((&ptr->l)[index]))) return -EFSCORRUPTED; break; case XFS_BTREE_TYPE_INODE: if (!xfs_verify_fsbno(cur->bc_mp, be64_to_cpu((&ptr->l)[index]))) return -EFSCORRUPTED; break; case XFS_BTREE_TYPE_AG: if (!xfs_verify_agbno(to_perag(cur->bc_group), be32_to_cpu((&ptr->s)[index]))) return -EFSCORRUPTED; break; } return 0; } /* * Check that a given (indexed) btree pointer at a certain level of a * btree is valid and doesn't point past where it should. */ static int xfs_btree_check_ptr( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, int index, int level) { int error; error = __xfs_btree_check_ptr(cur, ptr, index, level); if (error) { switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_MEM: xfs_err(cur->bc_mp, "In-memory: Corrupt %sbt flags 0x%x pointer at level %d index %d fa %pS.", cur->bc_ops->name, cur->bc_flags, level, index, __this_address); break; case XFS_BTREE_TYPE_INODE: xfs_err(cur->bc_mp, "Inode %llu fork %d: Corrupt %sbt pointer at level %d index %d.", cur->bc_ino.ip->i_ino, cur->bc_ino.whichfork, cur->bc_ops->name, level, index); break; case XFS_BTREE_TYPE_AG: xfs_err(cur->bc_mp, "AG %u: Corrupt %sbt pointer at level %d index %d.", cur->bc_group->xg_gno, cur->bc_ops->name, level, index); break; } xfs_btree_mark_sick(cur); } return error; } #ifdef DEBUG # define xfs_btree_debug_check_ptr xfs_btree_check_ptr #else # define xfs_btree_debug_check_ptr(...) (0) #endif /* * Calculate CRC on the whole btree block and stuff it into the * long-form btree header. * * Prior to calculting the CRC, pull the LSN out of the buffer log item and put * it into the buffer so recovery knows what the last modification was that made * it to disk. */ void xfs_btree_fsblock_calc_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_buf_log_item *bip = bp->b_log_item; if (!xfs_has_crc(bp->b_mount)) return; if (bip) block->bb_u.l.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF); } bool xfs_btree_fsblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.l.bb_lsn))) return false; return xfs_buf_verify_cksum(bp, XFS_BTREE_LBLOCK_CRC_OFF); } return true; } /* * Calculate CRC on the whole btree block and stuff it into the * short-form btree header. * * Prior to calculting the CRC, pull the LSN out of the buffer log item and put * it into the buffer so recovery knows what the last modification was that made * it to disk. */ void xfs_btree_agblock_calc_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_buf_log_item *bip = bp->b_log_item; if (!xfs_has_crc(bp->b_mount)) return; if (bip) block->bb_u.s.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn); xfs_buf_update_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF); } bool xfs_btree_agblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_mount *mp = bp->b_mount; if (xfs_has_crc(mp)) { if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn))) return false; return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF); } return true; } static int xfs_btree_free_block( struct xfs_btree_cur *cur, struct xfs_buf *bp) { int error; trace_xfs_btree_free_block(cur, bp); /* * Don't allow block freeing for a staging cursor, because staging * cursors do not support regular btree modifications. */ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { ASSERT(0); return -EFSCORRUPTED; } error = cur->bc_ops->free_block(cur, bp); if (!error) { xfs_trans_binval(cur->bc_tp, bp); XFS_BTREE_STATS_INC(cur, free); } return error; } /* * Delete the btree cursor. */ void xfs_btree_del_cursor( struct xfs_btree_cur *cur, /* btree cursor */ int error) /* del because of error */ { int i; /* btree level */ /* * Clear the buffer pointers and release the buffers. If we're doing * this because of an error, inspect all of the entries in the bc_bufs * array for buffers to be unlocked. This is because some of the btree * code works from level n down to 0, and if we get an error along the * way we won't have initialized all the entries down to 0. */ for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_levels[i].bp) xfs_trans_brelse(cur->bc_tp, cur->bc_levels[i].bp); else if (!error) break; } /* * If we are doing a BMBT update, the number of unaccounted blocks * allocated during this cursor life time should be zero. If it's not * zero, then we should be shut down or on our way to shutdown due to * cancelling a dirty transaction on error. */ ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 || xfs_is_shutdown(cur->bc_mp) || error != 0); if (cur->bc_group) xfs_group_put(cur->bc_group); kmem_cache_free(cur->bc_cache, cur); } /* Return the buffer target for this btree's buffer. */ static inline struct xfs_buftarg * xfs_btree_buftarg( struct xfs_btree_cur *cur) { if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) return cur->bc_mem.xfbtree->target; return cur->bc_mp->m_ddev_targp; } /* Return the block size (in units of 512b sectors) for this btree. */ static inline unsigned int xfs_btree_bbsize( struct xfs_btree_cur *cur) { if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM) return XFBNO_BBSIZE; return cur->bc_mp->m_bsize; } /* * Duplicate the btree cursor. * Allocate a new one, copy the record, re-get the buffers. */ int /* error */ xfs_btree_dup_cursor( struct xfs_btree_cur *cur, /* input cursor */ struct xfs_btree_cur **ncur) /* output cursor */ { struct xfs_mount *mp = cur->bc_mp; struct xfs_trans *tp = cur->bc_tp; struct xfs_buf *bp; struct xfs_btree_cur *new; int error; int i; /* * Don't allow staging cursors to be duplicated because they're supposed * to be kept private to a single thread. */ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { ASSERT(0); return -EFSCORRUPTED; } /* * Allocate a new cursor like the old one. */ new = cur->bc_ops->dup_cursor(cur); /* * Copy the record currently in the cursor. */ new->bc_rec = cur->bc_rec; /* * For each level current, re-get the buffer and copy the ptr value. */ for (i = 0; i < new->bc_nlevels; i++) { new->bc_levels[i].ptr = cur->bc_levels[i].ptr; new->bc_levels[i].ra = cur->bc_levels[i].ra; bp = cur->bc_levels[i].bp; if (bp) { error = xfs_trans_read_buf(mp, tp, xfs_btree_buftarg(cur), xfs_buf_daddr(bp), xfs_btree_bbsize(cur), 0, &bp, cur->bc_ops->buf_ops); if (xfs_metadata_is_sick(error)) xfs_btree_mark_sick(new); if (error) { xfs_btree_del_cursor(new, error); *ncur = NULL; return error; } } new->bc_levels[i].bp = bp; } *ncur = new; return 0; } /* * XFS btree block layout and addressing: * * There are two types of blocks in the btree: leaf and non-leaf blocks. * * The leaf record start with a header then followed by records containing * the values. A non-leaf block also starts with the same header, and * then first contains lookup keys followed by an equal number of pointers * to the btree blocks at the previous level. * * +--------+-------+-------+-------+-------+-------+-------+ * Leaf: | header | rec 1 | rec 2 | rec 3 | rec 4 | rec 5 | rec N | * +--------+-------+-------+-------+-------+-------+-------+ * * +--------+-------+-------+-------+-------+-------+-------+ * Non-Leaf: | header | key 1 | key 2 | key N | ptr 1 | ptr 2 | ptr N | * +--------+-------+-------+-------+-------+-------+-------+ * * The header is called struct xfs_btree_block for reasons better left unknown * and comes in different versions for short (32bit) and long (64bit) block * pointers. The record and key structures are defined by the btree instances * and opaque to the btree core. The block pointers are simple disk endian * integers, available in a short (32bit) and long (64bit) variant. * * The helpers below calculate the offset of a given record, key or pointer * into a btree block (xfs_btree_*_offset) or return a pointer to the given * record, key or pointer (xfs_btree_*_addr). Note that all addressing * inside the btree block is done using indices starting at one, not zero! * * If XFS_BTGEO_OVERLAPPING is set, then this btree supports keys containing * overlapping intervals. In such a tree, records are still sorted lowest to * highest and indexed by the smallest key value that refers to the record. * However, nodes are different: each pointer has two associated keys -- one * indexing the lowest key available in the block(s) below (the same behavior * as the key in a regular btree) and another indexing the highest key * available in the block(s) below. Because records are /not/ sorted by the * highest key, all leaf block updates require us to compute the highest key * that matches any record in the leaf and to recursively update the high keys * in the nodes going further up in the tree, if necessary. Nodes look like * this: * * +--------+-----+-----+-----+-----+-----+-------+-------+-----+ * Non-Leaf: | header | lo1 | hi1 | lo2 | hi2 | ... | ptr 1 | ptr 2 | ... | * +--------+-----+-----+-----+-----+-----+-------+-------+-----+ * * To perform an interval query on an overlapped tree, perform the usual * depth-first search and use the low and high keys to decide if we can skip * that particular node. If a leaf node is reached, return the records that * intersect the interval. Note that an interval query may return numerous * entries. For a non-overlapped tree, simply search for the record associated * with the lowest key and iterate forward until a non-matching record is * found. Section 14.3 ("Interval Trees") of _Introduction to Algorithms_ by * Cormen, Leiserson, Rivest, and Stein (2nd or 3rd ed. only) discuss this in * more detail. * * Why do we care about overlapping intervals? Let's say you have a bunch of * reverse mapping records on a reflink filesystem: * * 1: +- file A startblock B offset C length D -----------+ * 2: +- file E startblock F offset G length H --------------+ * 3: +- file I startblock F offset J length K --+ * 4: +- file L... --+ * * Now say we want to map block (B+D) into file A at offset (C+D). Ideally, * we'd simply increment the length of record 1. But how do we find the record * that ends at (B+D-1) (i.e. record 1)? A LE lookup of (B+D-1) would return * record 3 because the keys are ordered first by startblock. An interval * query would return records 1 and 2 because they both overlap (B+D-1), and * from that we can pick out record 1 as the appropriate left neighbor. * * In the non-overlapped case you can do a LE lookup and decrement the cursor * because a record's interval must end before the next record. */ /* * Return size of the btree block header for this btree instance. */ static inline size_t xfs_btree_block_len(struct xfs_btree_cur *cur) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (xfs_has_crc(cur->bc_mp)) return XFS_BTREE_LBLOCK_CRC_LEN; return XFS_BTREE_LBLOCK_LEN; } if (xfs_has_crc(cur->bc_mp)) return XFS_BTREE_SBLOCK_CRC_LEN; return XFS_BTREE_SBLOCK_LEN; } /* * Calculate offset of the n-th record in a btree block. */ STATIC size_t xfs_btree_rec_offset( struct xfs_btree_cur *cur, int n) { return xfs_btree_block_len(cur) + (n - 1) * cur->bc_ops->rec_len; } /* * Calculate offset of the n-th key in a btree block. */ STATIC size_t xfs_btree_key_offset( struct xfs_btree_cur *cur, int n) { return xfs_btree_block_len(cur) + (n - 1) * cur->bc_ops->key_len; } /* * Calculate offset of the n-th high key in a btree block. */ STATIC size_t xfs_btree_high_key_offset( struct xfs_btree_cur *cur, int n) { return xfs_btree_block_len(cur) + (n - 1) * cur->bc_ops->key_len + (cur->bc_ops->key_len / 2); } /* * Calculate offset of the n-th block pointer in a btree block. */ STATIC size_t xfs_btree_ptr_offset( struct xfs_btree_cur *cur, int n, int level) { return xfs_btree_block_len(cur) + cur->bc_ops->get_maxrecs(cur, level) * cur->bc_ops->key_len + (n - 1) * cur->bc_ops->ptr_len; } /* * Return a pointer to the n-th record in the btree block. */ union xfs_btree_rec * xfs_btree_rec_addr( struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block) { return (union xfs_btree_rec *) ((char *)block + xfs_btree_rec_offset(cur, n)); } /* * Return a pointer to the n-th key in the btree block. */ union xfs_btree_key * xfs_btree_key_addr( struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block) { return (union xfs_btree_key *) ((char *)block + xfs_btree_key_offset(cur, n)); } /* * Return a pointer to the n-th high key in the btree block. */ union xfs_btree_key * xfs_btree_high_key_addr( struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block) { return (union xfs_btree_key *) ((char *)block + xfs_btree_high_key_offset(cur, n)); } /* * Return a pointer to the n-th block pointer in the btree block. */ union xfs_btree_ptr * xfs_btree_ptr_addr( struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block) { int level = xfs_btree_get_level(block); ASSERT(block->bb_level != 0); return (union xfs_btree_ptr *) ((char *)block + xfs_btree_ptr_offset(cur, n, level)); } struct xfs_ifork * xfs_btree_ifork_ptr( struct xfs_btree_cur *cur) { ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); if (cur->bc_flags & XFS_BTREE_STAGING) return cur->bc_ino.ifake->if_fork; return xfs_ifork_ptr(cur->bc_ino.ip, cur->bc_ino.whichfork); } /* * Get the root block which is stored in the inode. * * For now this btree implementation assumes the btree root is always * stored in the if_broot field of an inode fork. */ STATIC struct xfs_btree_block * xfs_btree_get_iroot( struct xfs_btree_cur *cur) { struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur); return (struct xfs_btree_block *)ifp->if_broot; } /* * Retrieve the block pointer from the cursor at the given level. * This may be an inode btree root or from a buffer. */ struct xfs_btree_block * /* generic btree block pointer */ xfs_btree_get_block( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level in btree */ struct xfs_buf **bpp) /* buffer containing the block */ { if (xfs_btree_at_iroot(cur, level)) { *bpp = NULL; return xfs_btree_get_iroot(cur); } *bpp = cur->bc_levels[level].bp; return XFS_BUF_TO_BLOCK(*bpp); } /* * Change the cursor to point to the first record at the given level. * Other levels are unaffected. */ STATIC int /* success=1, failure=0 */ xfs_btree_firstrec( struct xfs_btree_cur *cur, /* btree cursor */ int level) /* level to change */ { struct xfs_btree_block *block; /* generic btree block pointer */ struct xfs_buf *bp; /* buffer containing block */ /* * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); if (xfs_btree_check_block(cur, block, level, bp)) return 0; /* * It's empty, there is no such record. */ if (!block->bb_numrecs) return 0; /* * Set the ptr value to 1, that's the first record/key. */ cur->bc_levels[level].ptr = 1; return 1; } /* * Change the cursor to point to the last record in the current block * at the given level. Other levels are unaffected. */ STATIC int /* success=1, failure=0 */ xfs_btree_lastrec( struct xfs_btree_cur *cur, /* btree cursor */ int level) /* level to change */ { struct xfs_btree_block *block; /* generic btree block pointer */ struct xfs_buf *bp; /* buffer containing block */ /* * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); if (xfs_btree_check_block(cur, block, level, bp)) return 0; /* * It's empty, there is no such record. */ if (!block->bb_numrecs) return 0; /* * Set the ptr value to numrecs, that's the last record/key. */ cur->bc_levels[level].ptr = be16_to_cpu(block->bb_numrecs); return 1; } /* * Compute first and last byte offsets for the fields given. * Interprets the offsets table, which contains struct field offsets. */ void xfs_btree_offsets( uint32_t fields, /* bitmask of fields */ const short *offsets, /* table of field offsets */ int nbits, /* number of bits to inspect */ int *first, /* output: first byte offset */ int *last) /* output: last byte offset */ { int i; /* current bit number */ uint32_t imask; /* mask for current bit number */ ASSERT(fields != 0); /* * Find the lowest bit, so the first byte offset. */ for (i = 0, imask = 1u; ; i++, imask <<= 1) { if (imask & fields) { *first = offsets[i]; break; } } /* * Find the highest bit, so the last byte offset. */ for (i = nbits - 1, imask = 1u << i; ; i--, imask >>= 1) { if (imask & fields) { *last = offsets[i + 1] - 1; break; } } } STATIC int xfs_btree_readahead_fsblock( struct xfs_btree_cur *cur, int lr, struct xfs_btree_block *block) { struct xfs_mount *mp = cur->bc_mp; xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); int rval = 0; if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) { xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, left), mp->m_bsize, cur->bc_ops->buf_ops); rval++; } if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) { xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, right), mp->m_bsize, cur->bc_ops->buf_ops); rval++; } return rval; } STATIC int xfs_btree_readahead_memblock( struct xfs_btree_cur *cur, int lr, struct xfs_btree_block *block) { struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target; xfbno_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); xfbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); int rval = 0; if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) { xfs_buf_readahead(btp, xfbno_to_daddr(left), XFBNO_BBSIZE, cur->bc_ops->buf_ops); rval++; } if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) { xfs_buf_readahead(btp, xfbno_to_daddr(right), XFBNO_BBSIZE, cur->bc_ops->buf_ops); rval++; } return rval; } STATIC int xfs_btree_readahead_agblock( struct xfs_btree_cur *cur, int lr, struct xfs_btree_block *block) { struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = to_perag(cur->bc_group); xfs_agblock_t left = be32_to_cpu(block->bb_u.s.bb_leftsib); xfs_agblock_t right = be32_to_cpu(block->bb_u.s.bb_rightsib); int rval = 0; if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) { xfs_buf_readahead(mp->m_ddev_targp, xfs_agbno_to_daddr(pag, left), mp->m_bsize, cur->bc_ops->buf_ops); rval++; } if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) { xfs_buf_readahead(mp->m_ddev_targp, xfs_agbno_to_daddr(pag, right), mp->m_bsize, cur->bc_ops->buf_ops); rval++; } return rval; } /* * Read-ahead btree blocks, at the given level. * Bits in lr are set from XFS_BTCUR_{LEFT,RIGHT}RA. */ STATIC int xfs_btree_readahead( struct xfs_btree_cur *cur, /* btree cursor */ int lev, /* level in btree */ int lr) /* left/right bits */ { struct xfs_btree_block *block; /* * No readahead needed if we are at the root level and the * btree root is stored in the inode. */ if (xfs_btree_at_iroot(cur, lev)) return 0; if ((cur->bc_levels[lev].ra | lr) == cur->bc_levels[lev].ra) return 0; cur->bc_levels[lev].ra |= lr; block = XFS_BUF_TO_BLOCK(cur->bc_levels[lev].bp); switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_AG: return xfs_btree_readahead_agblock(cur, lr, block); case XFS_BTREE_TYPE_INODE: return xfs_btree_readahead_fsblock(cur, lr, block); case XFS_BTREE_TYPE_MEM: return xfs_btree_readahead_memblock(cur, lr, block); default: ASSERT(0); return 0; } } STATIC int xfs_btree_ptr_to_daddr( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, xfs_daddr_t *daddr) { int error; error = xfs_btree_check_ptr(cur, ptr, 0, 1); if (error) return error; switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_AG: *daddr = xfs_agbno_to_daddr(to_perag(cur->bc_group), be32_to_cpu(ptr->s)); break; case XFS_BTREE_TYPE_INODE: *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l)); break; case XFS_BTREE_TYPE_MEM: *daddr = xfbno_to_daddr(be64_to_cpu(ptr->l)); break; } return 0; } /* * Readahead @count btree blocks at the given @ptr location. * * We don't need to care about long or short form btrees here as we have a * method of converting the ptr directly to a daddr available to us. */ STATIC void xfs_btree_readahead_ptr( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, xfs_extlen_t count) { xfs_daddr_t daddr; if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr)) return; xfs_buf_readahead(xfs_btree_buftarg(cur), daddr, xfs_btree_bbsize(cur) * count, cur->bc_ops->buf_ops); } /* * Set the buffer for level "lev" in the cursor to bp, releasing * any previous buffer. */ STATIC void xfs_btree_setbuf( struct xfs_btree_cur *cur, /* btree cursor */ int lev, /* level in btree */ struct xfs_buf *bp) /* new buffer to set */ { struct xfs_btree_block *b; /* btree block */ if (cur->bc_levels[lev].bp) xfs_trans_brelse(cur->bc_tp, cur->bc_levels[lev].bp); cur->bc_levels[lev].bp = bp; cur->bc_levels[lev].ra = 0; b = XFS_BUF_TO_BLOCK(bp); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK)) cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA; if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK)) cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA; } else { if (b->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK)) cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA; if (b->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK)) cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA; } } bool xfs_btree_ptr_is_null( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return ptr->l == cpu_to_be64(NULLFSBLOCK); else return ptr->s == cpu_to_be32(NULLAGBLOCK); } void xfs_btree_set_ptr_null( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) ptr->l = cpu_to_be64(NULLFSBLOCK); else ptr->s = cpu_to_be32(NULLAGBLOCK); } static inline bool xfs_btree_ptrs_equal( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr1, union xfs_btree_ptr *ptr2) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return ptr1->l == ptr2->l; return ptr1->s == ptr2->s; } /* * Get/set/init sibling pointers */ void xfs_btree_get_sibling( struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_ptr *ptr, int lr) { ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (lr == XFS_BB_RIGHTSIB) ptr->l = block->bb_u.l.bb_rightsib; else ptr->l = block->bb_u.l.bb_leftsib; } else { if (lr == XFS_BB_RIGHTSIB) ptr->s = block->bb_u.s.bb_rightsib; else ptr->s = block->bb_u.s.bb_leftsib; } } void xfs_btree_set_sibling( struct xfs_btree_cur *cur, struct xfs_btree_block *block, const union xfs_btree_ptr *ptr, int lr) { ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (lr == XFS_BB_RIGHTSIB) block->bb_u.l.bb_rightsib = ptr->l; else block->bb_u.l.bb_leftsib = ptr->l; } else { if (lr == XFS_BB_RIGHTSIB) block->bb_u.s.bb_rightsib = ptr->s; else block->bb_u.s.bb_leftsib = ptr->s; } } static void __xfs_btree_init_block( struct xfs_mount *mp, struct xfs_btree_block *buf, const struct xfs_btree_ops *ops, xfs_daddr_t blkno, __u16 level, __u16 numrecs, __u64 owner) { bool crc = xfs_has_crc(mp); __u32 magic = xfs_btree_magic(mp, ops); buf->bb_magic = cpu_to_be32(magic); buf->bb_level = cpu_to_be16(level); buf->bb_numrecs = cpu_to_be16(numrecs); if (ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK); buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK); if (crc) { buf->bb_u.l.bb_blkno = cpu_to_be64(blkno); buf->bb_u.l.bb_owner = cpu_to_be64(owner); uuid_copy(&buf->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid); buf->bb_u.l.bb_pad = 0; buf->bb_u.l.bb_lsn = 0; } } else { buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK); buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK); if (crc) { buf->bb_u.s.bb_blkno = cpu_to_be64(blkno); /* owner is a 32 bit value on short blocks */ buf->bb_u.s.bb_owner = cpu_to_be32((__u32)owner); uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid); buf->bb_u.s.bb_lsn = 0; } } } void xfs_btree_init_block( struct xfs_mount *mp, struct xfs_btree_block *block, const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs, __u64 owner) { __xfs_btree_init_block(mp, block, ops, XFS_BUF_DADDR_NULL, level, numrecs, owner); } void xfs_btree_init_buf( struct xfs_mount *mp, struct xfs_buf *bp, const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs, __u64 owner) { __xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops, xfs_buf_daddr(bp), level, numrecs, owner); bp->b_ops = ops->buf_ops; } static inline __u64 xfs_btree_owner( struct xfs_btree_cur *cur) { switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_MEM: return cur->bc_mem.xfbtree->owner; case XFS_BTREE_TYPE_INODE: return cur->bc_ino.ip->i_ino; case XFS_BTREE_TYPE_AG: return cur->bc_group->xg_gno; default: ASSERT(0); return 0; } } void xfs_btree_init_block_cur( struct xfs_btree_cur *cur, struct xfs_buf *bp, int level, int numrecs) { xfs_btree_init_buf(cur->bc_mp, bp, cur->bc_ops, level, numrecs, xfs_btree_owner(cur)); } STATIC void xfs_btree_buf_to_ptr( struct xfs_btree_cur *cur, struct xfs_buf *bp, union xfs_btree_ptr *ptr) { switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_AG: ptr->s = cpu_to_be32(xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp))); break; case XFS_BTREE_TYPE_INODE: ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp))); break; case XFS_BTREE_TYPE_MEM: ptr->l = cpu_to_be64(xfs_daddr_to_xfbno(xfs_buf_daddr(bp))); break; } } static inline void xfs_btree_set_refs( struct xfs_btree_cur *cur, struct xfs_buf *bp) { xfs_buf_set_ref(bp, cur->bc_ops->lru_refs); } int xfs_btree_get_buf_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, struct xfs_btree_block **block, struct xfs_buf **bpp) { xfs_daddr_t d; int error; error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d, xfs_btree_bbsize(cur), 0, bpp); if (error) return error; (*bpp)->b_ops = cur->bc_ops->buf_ops; *block = XFS_BUF_TO_BLOCK(*bpp); return 0; } /* * Read in the buffer at the given ptr and return the buffer and * the block pointer within the buffer. */ int xfs_btree_read_buf_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, int flags, struct xfs_btree_block **block, struct xfs_buf **bpp) { struct xfs_mount *mp = cur->bc_mp; xfs_daddr_t d; int error; /* need to sort out how callers deal with failures first */ ASSERT(!(flags & XBF_TRYLOCK)); error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d, xfs_btree_bbsize(cur), flags, bpp, cur->bc_ops->buf_ops); if (xfs_metadata_is_sick(error)) xfs_btree_mark_sick(cur); if (error) return error; xfs_btree_set_refs(cur, *bpp); *block = XFS_BUF_TO_BLOCK(*bpp); return 0; } /* * Copy keys from one btree block to another. */ void xfs_btree_copy_keys( struct xfs_btree_cur *cur, union xfs_btree_key *dst_key, const union xfs_btree_key *src_key, int numkeys) { ASSERT(numkeys >= 0); memcpy(dst_key, src_key, numkeys * cur->bc_ops->key_len); } /* * Copy records from one btree block to another. */ STATIC void xfs_btree_copy_recs( struct xfs_btree_cur *cur, union xfs_btree_rec *dst_rec, union xfs_btree_rec *src_rec, int numrecs) { ASSERT(numrecs >= 0); memcpy(dst_rec, src_rec, numrecs * cur->bc_ops->rec_len); } /* * Copy block pointers from one btree block to another. */ void xfs_btree_copy_ptrs( struct xfs_btree_cur *cur, union xfs_btree_ptr *dst_ptr, const union xfs_btree_ptr *src_ptr, int numptrs) { ASSERT(numptrs >= 0); memcpy(dst_ptr, src_ptr, numptrs * cur->bc_ops->ptr_len); } /* * Shift keys one index left/right inside a single btree block. */ STATIC void xfs_btree_shift_keys( struct xfs_btree_cur *cur, union xfs_btree_key *key, int dir, int numkeys) { char *dst_key; ASSERT(numkeys >= 0); ASSERT(dir == 1 || dir == -1); dst_key = (char *)key + (dir * cur->bc_ops->key_len); memmove(dst_key, key, numkeys * cur->bc_ops->key_len); } /* * Shift records one index left/right inside a single btree block. */ STATIC void xfs_btree_shift_recs( struct xfs_btree_cur *cur, union xfs_btree_rec *rec, int dir, int numrecs) { char *dst_rec; ASSERT(numrecs >= 0); ASSERT(dir == 1 || dir == -1); dst_rec = (char *)rec + (dir * cur->bc_ops->rec_len); memmove(dst_rec, rec, numrecs * cur->bc_ops->rec_len); } /* * Shift block pointers one index left/right inside a single btree block. */ STATIC void xfs_btree_shift_ptrs( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, int dir, int numptrs) { char *dst_ptr; ASSERT(numptrs >= 0); ASSERT(dir == 1 || dir == -1); dst_ptr = (char *)ptr + (dir * cur->bc_ops->ptr_len); memmove(dst_ptr, ptr, numptrs * cur->bc_ops->ptr_len); } /* * Log key values from the btree block. */ STATIC void xfs_btree_log_keys( struct xfs_btree_cur *cur, struct xfs_buf *bp, int first, int last) { if (bp) { xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_key_offset(cur, first), xfs_btree_key_offset(cur, last + 1) - 1); } else { xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, xfs_ilog_fbroot(cur->bc_ino.whichfork)); } } /* * Log record values from the btree block. */ void xfs_btree_log_recs( struct xfs_btree_cur *cur, struct xfs_buf *bp, int first, int last) { if (!bp) { xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, xfs_ilog_fbroot(cur->bc_ino.whichfork)); return; } xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_rec_offset(cur, first), xfs_btree_rec_offset(cur, last + 1) - 1); } /* * Log block pointer fields from a btree block (nonleaf). */ STATIC void xfs_btree_log_ptrs( struct xfs_btree_cur *cur, /* btree cursor */ struct xfs_buf *bp, /* buffer containing btree block */ int first, /* index of first pointer to log */ int last) /* index of last pointer to log */ { if (bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); int level = xfs_btree_get_level(block); xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, xfs_btree_ptr_offset(cur, first, level), xfs_btree_ptr_offset(cur, last + 1, level) - 1); } else { xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, xfs_ilog_fbroot(cur->bc_ino.whichfork)); } } /* * Log fields from a btree block header. */ void xfs_btree_log_block( struct xfs_btree_cur *cur, /* btree cursor */ struct xfs_buf *bp, /* buffer containing btree block */ uint32_t fields) /* mask of fields: XFS_BB_... */ { int first; /* first byte offset logged */ int last; /* last byte offset logged */ static const short soffsets[] = { /* table of offsets (short) */ offsetof(struct xfs_btree_block, bb_magic), offsetof(struct xfs_btree_block, bb_level), offsetof(struct xfs_btree_block, bb_numrecs), offsetof(struct xfs_btree_block, bb_u.s.bb_leftsib), offsetof(struct xfs_btree_block, bb_u.s.bb_rightsib), offsetof(struct xfs_btree_block, bb_u.s.bb_blkno), offsetof(struct xfs_btree_block, bb_u.s.bb_lsn), offsetof(struct xfs_btree_block, bb_u.s.bb_uuid), offsetof(struct xfs_btree_block, bb_u.s.bb_owner), offsetof(struct xfs_btree_block, bb_u.s.bb_crc), XFS_BTREE_SBLOCK_CRC_LEN }; static const short loffsets[] = { /* table of offsets (long) */ offsetof(struct xfs_btree_block, bb_magic), offsetof(struct xfs_btree_block, bb_level), offsetof(struct xfs_btree_block, bb_numrecs), offsetof(struct xfs_btree_block, bb_u.l.bb_leftsib), offsetof(struct xfs_btree_block, bb_u.l.bb_rightsib), offsetof(struct xfs_btree_block, bb_u.l.bb_blkno), offsetof(struct xfs_btree_block, bb_u.l.bb_lsn), offsetof(struct xfs_btree_block, bb_u.l.bb_uuid), offsetof(struct xfs_btree_block, bb_u.l.bb_owner), offsetof(struct xfs_btree_block, bb_u.l.bb_crc), offsetof(struct xfs_btree_block, bb_u.l.bb_pad), XFS_BTREE_LBLOCK_CRC_LEN }; if (bp) { int nbits; if (xfs_has_crc(cur->bc_mp)) { /* * We don't log the CRC when updating a btree * block but instead recreate it during log * recovery. As the log buffers have checksums * of their own this is safe and avoids logging a crc * update in a lot of places. */ if (fields == XFS_BB_ALL_BITS) fields = XFS_BB_ALL_BITS_CRC; nbits = XFS_BB_NUM_BITS_CRC; } else { nbits = XFS_BB_NUM_BITS; } xfs_btree_offsets(fields, (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) ? loffsets : soffsets, nbits, &first, &last); xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(cur->bc_tp, bp, first, last); } else { xfs_trans_log_inode(cur->bc_tp, cur->bc_ino.ip, xfs_ilog_fbroot(cur->bc_ino.whichfork)); } } /* * Increment cursor by one record at the level. * For nonzero levels the leaf-ward information is untouched. */ int /* error */ xfs_btree_increment( struct xfs_btree_cur *cur, int level, int *stat) /* success/failure */ { struct xfs_btree_block *block; union xfs_btree_ptr ptr; struct xfs_buf *bp; int error; /* error return value */ int lev; ASSERT(level < cur->bc_nlevels); /* Read-ahead to the right at this level. */ xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA); /* Get a pointer to the btree block. */ block = xfs_btree_get_block(cur, level, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto error0; #endif /* We're done if we remain in the block after the increment. */ if (++cur->bc_levels[level].ptr <= xfs_btree_get_numrecs(block)) goto out1; /* Fail if we just went off the right edge of the tree. */ xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB); if (xfs_btree_ptr_is_null(cur, &ptr)) goto out0; XFS_BTREE_STATS_INC(cur, increment); /* * March up the tree incrementing pointers. * Stop when we don't go off the right edge of a block. */ for (lev = level + 1; lev < cur->bc_nlevels; lev++) { block = xfs_btree_get_block(cur, lev, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, lev, bp); if (error) goto error0; #endif if (++cur->bc_levels[lev].ptr <= xfs_btree_get_numrecs(block)) break; /* Read-ahead the right block for the next loop. */ xfs_btree_readahead(cur, lev, XFS_BTCUR_RIGHTRA); } /* * If we went off the root then we are either seriously * confused or have the tree root in an inode. */ if (lev == cur->bc_nlevels) { if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) goto out0; ASSERT(0); xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } ASSERT(lev < cur->bc_nlevels); /* * Now walk back down the tree, fixing up the cursor's buffer * pointers and key numbers. */ for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) { union xfs_btree_ptr *ptrp; ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block); --lev; error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp); if (error) goto error0; xfs_btree_setbuf(cur, lev, bp); cur->bc_levels[lev].ptr = 1; } out1: *stat = 1; return 0; out0: *stat = 0; return 0; error0: return error; } /* * Decrement cursor by one record at the level. * For nonzero levels the leaf-ward information is untouched. */ int /* error */ xfs_btree_decrement( struct xfs_btree_cur *cur, int level, int *stat) /* success/failure */ { struct xfs_btree_block *block; struct xfs_buf *bp; int error; /* error return value */ int lev; union xfs_btree_ptr ptr; ASSERT(level < cur->bc_nlevels); /* Read-ahead to the left at this level. */ xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA); /* We're done if we remain in the block after the decrement. */ if (--cur->bc_levels[level].ptr > 0) goto out1; /* Get a pointer to the btree block. */ block = xfs_btree_get_block(cur, level, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto error0; #endif /* Fail if we just went off the left edge of the tree. */ xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_LEFTSIB); if (xfs_btree_ptr_is_null(cur, &ptr)) goto out0; XFS_BTREE_STATS_INC(cur, decrement); /* * March up the tree decrementing pointers. * Stop when we don't go off the left edge of a block. */ for (lev = level + 1; lev < cur->bc_nlevels; lev++) { if (--cur->bc_levels[lev].ptr > 0) break; /* Read-ahead the left block for the next loop. */ xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA); } /* * If we went off the root then we are seriously confused. * or the root of the tree is in an inode. */ if (lev == cur->bc_nlevels) { if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) goto out0; ASSERT(0); xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } ASSERT(lev < cur->bc_nlevels); /* * Now walk back down the tree, fixing up the cursor's buffer * pointers and key numbers. */ for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) { union xfs_btree_ptr *ptrp; ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block); --lev; error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp); if (error) goto error0; xfs_btree_setbuf(cur, lev, bp); cur->bc_levels[lev].ptr = xfs_btree_get_numrecs(block); } out1: *stat = 1; return 0; out0: *stat = 0; return 0; error0: return error; } /* * Check the btree block owner now that we have the context to know who the * real owner is. */ static inline xfs_failaddr_t xfs_btree_check_block_owner( struct xfs_btree_cur *cur, struct xfs_btree_block *block) { __u64 owner; if (!xfs_has_crc(cur->bc_mp) || (cur->bc_flags & XFS_BTREE_BMBT_INVALID_OWNER)) return NULL; owner = xfs_btree_owner(cur); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (be64_to_cpu(block->bb_u.l.bb_owner) != owner) return __this_address; } else { if (be32_to_cpu(block->bb_u.s.bb_owner) != owner) return __this_address; } return NULL; } int xfs_btree_lookup_get_block( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level in the btree */ const union xfs_btree_ptr *pp, /* ptr to btree block */ struct xfs_btree_block **blkp) /* return btree block */ { struct xfs_buf *bp; /* buffer pointer for btree block */ xfs_daddr_t daddr; int error = 0; /* special case the root block if in an inode */ if (xfs_btree_at_iroot(cur, level)) { *blkp = xfs_btree_get_iroot(cur); return 0; } /* * If the old buffer at this level for the disk address we are * looking for re-use it. * * Otherwise throw it away and get a new one. */ bp = cur->bc_levels[level].bp; error = xfs_btree_ptr_to_daddr(cur, pp, &daddr); if (error) return error; if (bp && xfs_buf_daddr(bp) == daddr) { *blkp = XFS_BUF_TO_BLOCK(bp); return 0; } error = xfs_btree_read_buf_block(cur, pp, 0, blkp, &bp); if (error) return error; /* Check the inode owner since the verifiers don't. */ if (xfs_btree_check_block_owner(cur, *blkp) != NULL) goto out_bad; /* Did we get the level we were looking for? */ if (be16_to_cpu((*blkp)->bb_level) != level) goto out_bad; /* Check that internal nodes have at least one record. */ if (level != 0 && be16_to_cpu((*blkp)->bb_numrecs) == 0) goto out_bad; xfs_btree_setbuf(cur, level, bp); return 0; out_bad: *blkp = NULL; xfs_buf_mark_corrupt(bp); xfs_trans_brelse(cur->bc_tp, bp); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } /* * Get current search key. For level 0 we don't actually have a key * structure so we make one up from the record. For all other levels * we just return the right key. */ STATIC union xfs_btree_key * xfs_lookup_get_search_key( struct xfs_btree_cur *cur, int level, int keyno, struct xfs_btree_block *block, union xfs_btree_key *kp) { if (level == 0) { cur->bc_ops->init_key_from_rec(kp, xfs_btree_rec_addr(cur, keyno, block)); return kp; } return xfs_btree_key_addr(cur, keyno, block); } /* * Initialize a pointer to the root block. */ void xfs_btree_init_ptr_from_cur( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr) { if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { /* * Inode-rooted btrees call xfs_btree_get_iroot to find the root * in xfs_btree_lookup_get_block and don't need a pointer here. */ ptr->l = 0; } else if (cur->bc_flags & XFS_BTREE_STAGING) { ptr->s = cpu_to_be32(cur->bc_ag.afake->af_root); } else { cur->bc_ops->init_ptr_from_cur(cur, ptr); } } /* * Lookup the record. The cursor is made to point to it, based on dir. * stat is set to 0 if can't find any such record, 1 for success. */ int /* error */ xfs_btree_lookup( struct xfs_btree_cur *cur, /* btree cursor */ xfs_lookup_t dir, /* <=, ==, or >= */ int *stat) /* success/failure */ { struct xfs_btree_block *block; /* current btree block */ int cmp_r; /* current key comparison result */ int error; /* error return value */ int keyno; /* current key number */ int level; /* level in the btree */ union xfs_btree_ptr *pp; /* ptr to btree block */ union xfs_btree_ptr ptr; /* ptr to btree block */ XFS_BTREE_STATS_INC(cur, lookup); /* No such thing as a zero-level tree. */ if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } block = NULL; keyno = 0; /* initialise start pointer from cursor */ xfs_btree_init_ptr_from_cur(cur, &ptr); pp = &ptr; /* * Iterate over each level in the btree, starting at the root. * For each level above the leaves, find the key we need, based * on the lookup record, then follow the corresponding block * pointer down to the next level. */ for (level = cur->bc_nlevels - 1, cmp_r = 1; level >= 0; level--) { /* Get the block we need to do the lookup on. */ error = xfs_btree_lookup_get_block(cur, level, pp, &block); if (error) goto error0; if (cmp_r == 0) { /* * If we already had a key match at a higher level, we * know we need to use the first entry in this block. */ keyno = 1; } else { /* Otherwise search this block. Do a binary search. */ int high; /* high entry number */ int low; /* low entry number */ /* Set low and high entry numbers, 1-based. */ low = 1; high = xfs_btree_get_numrecs(block); if (!high) { /* Block is empty, must be an empty leaf. */ if (level != 0 || cur->bc_nlevels != 1) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, cur->bc_mp, block, sizeof(*block)); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } cur->bc_levels[0].ptr = dir != XFS_LOOKUP_LE; *stat = 0; return 0; } /* Binary search the block. */ while (low <= high) { union xfs_btree_key key; union xfs_btree_key *kp; XFS_BTREE_STATS_INC(cur, compare); /* keyno is average of low and high. */ keyno = (low + high) >> 1; /* Get current search key */ kp = xfs_lookup_get_search_key(cur, level, keyno, block, &key); /* * Compute comparison result to get next * direction: * - less than, move right * - greater than, move left * - equal, we're done */ cmp_r = cur->bc_ops->cmp_key_with_cur(cur, kp); if (cmp_r < 0) low = keyno + 1; else if (cmp_r > 0) high = keyno - 1; else break; } } /* * If there are more levels, set up for the next level * by getting the block number and filling in the cursor. */ if (level > 0) { /* * If we moved left, need the previous key number, * unless there isn't one. */ if (cmp_r > 0 && --keyno < 1) keyno = 1; pp = xfs_btree_ptr_addr(cur, keyno, block); error = xfs_btree_debug_check_ptr(cur, pp, 0, level); if (error) goto error0; cur->bc_levels[level].ptr = keyno; } } /* Done with the search. See if we need to adjust the results. */ if (dir != XFS_LOOKUP_LE && cmp_r < 0) { keyno++; /* * If ge search and we went off the end of the block, but it's * not the last block, we're in the wrong block. */ xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB); if (dir == XFS_LOOKUP_GE && keyno > xfs_btree_get_numrecs(block) && !xfs_btree_ptr_is_null(cur, &ptr)) { int i; cur->bc_levels[0].ptr = keyno; error = xfs_btree_increment(cur, 0, &i); if (error) goto error0; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } *stat = 1; return 0; } } else if (dir == XFS_LOOKUP_LE && cmp_r > 0) keyno--; cur->bc_levels[0].ptr = keyno; /* Return if we succeeded or not. */ if (keyno == 0 || keyno > xfs_btree_get_numrecs(block)) *stat = 0; else if (dir != XFS_LOOKUP_EQ || cmp_r == 0) *stat = 1; else *stat = 0; return 0; error0: return error; } /* Find the high key storage area from a regular key. */ union xfs_btree_key * xfs_btree_high_key_from_key( struct xfs_btree_cur *cur, union xfs_btree_key *key) { ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING); return (union xfs_btree_key *)((char *)key + (cur->bc_ops->key_len / 2)); } /* Determine the low (and high if overlapped) keys of a leaf block */ STATIC void xfs_btree_get_leaf_keys( struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_key *key) { union xfs_btree_key max_hkey; union xfs_btree_key hkey; union xfs_btree_rec *rec; union xfs_btree_key *high; int n; rec = xfs_btree_rec_addr(cur, 1, block); cur->bc_ops->init_key_from_rec(key, rec); if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { cur->bc_ops->init_high_key_from_rec(&max_hkey, rec); for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { rec = xfs_btree_rec_addr(cur, n, block); cur->bc_ops->init_high_key_from_rec(&hkey, rec); if (xfs_btree_keycmp_gt(cur, &hkey, &max_hkey)) max_hkey = hkey; } high = xfs_btree_high_key_from_key(cur, key); memcpy(high, &max_hkey, cur->bc_ops->key_len / 2); } } /* Determine the low (and high if overlapped) keys of a node block */ STATIC void xfs_btree_get_node_keys( struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_key *key) { union xfs_btree_key *hkey; union xfs_btree_key *max_hkey; union xfs_btree_key *high; int n; if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { memcpy(key, xfs_btree_key_addr(cur, 1, block), cur->bc_ops->key_len / 2); max_hkey = xfs_btree_high_key_addr(cur, 1, block); for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { hkey = xfs_btree_high_key_addr(cur, n, block); if (xfs_btree_keycmp_gt(cur, hkey, max_hkey)) max_hkey = hkey; } high = xfs_btree_high_key_from_key(cur, key); memcpy(high, max_hkey, cur->bc_ops->key_len / 2); } else { memcpy(key, xfs_btree_key_addr(cur, 1, block), cur->bc_ops->key_len); } } /* Derive the keys for any btree block. */ void xfs_btree_get_keys( struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_key *key) { if (be16_to_cpu(block->bb_level) == 0) xfs_btree_get_leaf_keys(cur, block, key); else xfs_btree_get_node_keys(cur, block, key); } /* * Decide if we need to update the parent keys of a btree block. For * a standard btree this is only necessary if we're updating the first * record/key. For an overlapping btree, we must always update the * keys because the highest key can be in any of the records or keys * in the block. */ static inline bool xfs_btree_needs_key_update( struct xfs_btree_cur *cur, int ptr) { return (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) || ptr == 1; } /* * Update the low and high parent keys of the given level, progressing * towards the root. If force_all is false, stop if the keys for a given * level do not need updating. */ STATIC int __xfs_btree_updkeys( struct xfs_btree_cur *cur, int level, struct xfs_btree_block *block, struct xfs_buf *bp0, bool force_all) { union xfs_btree_key key; /* keys from current level */ union xfs_btree_key *lkey; /* keys from the next level up */ union xfs_btree_key *hkey; union xfs_btree_key *nlkey; /* keys from the next level up */ union xfs_btree_key *nhkey; struct xfs_buf *bp; int ptr; ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING); /* Exit if there aren't any parent levels to update. */ if (level + 1 >= cur->bc_nlevels) return 0; trace_xfs_btree_updkeys(cur, level, bp0); lkey = &key; hkey = xfs_btree_high_key_from_key(cur, lkey); xfs_btree_get_keys(cur, block, lkey); for (level++; level < cur->bc_nlevels; level++) { #ifdef DEBUG int error; #endif block = xfs_btree_get_block(cur, level, &bp); trace_xfs_btree_updkeys(cur, level, bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) return error; #endif ptr = cur->bc_levels[level].ptr; nlkey = xfs_btree_key_addr(cur, ptr, block); nhkey = xfs_btree_high_key_addr(cur, ptr, block); if (!force_all && xfs_btree_keycmp_eq(cur, nlkey, lkey) && xfs_btree_keycmp_eq(cur, nhkey, hkey)) break; xfs_btree_copy_keys(cur, nlkey, lkey, 1); xfs_btree_log_keys(cur, bp, ptr, ptr); if (level + 1 >= cur->bc_nlevels) break; xfs_btree_get_node_keys(cur, block, lkey); } return 0; } /* Update all the keys from some level in cursor back to the root. */ STATIC int xfs_btree_updkeys_force( struct xfs_btree_cur *cur, int level) { struct xfs_buf *bp; struct xfs_btree_block *block; block = xfs_btree_get_block(cur, level, &bp); return __xfs_btree_updkeys(cur, level, block, bp, true); } /* * Update the parent keys of the given level, progressing towards the root. */ STATIC int xfs_btree_update_keys( struct xfs_btree_cur *cur, int level) { struct xfs_btree_block *block; struct xfs_buf *bp; union xfs_btree_key *kp; union xfs_btree_key key; int ptr; ASSERT(level >= 0); block = xfs_btree_get_block(cur, level, &bp); if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) return __xfs_btree_updkeys(cur, level, block, bp, false); /* * Go up the tree from this level toward the root. * At each level, update the key value to the value input. * Stop when we reach a level where the cursor isn't pointing * at the first entry in the block. */ xfs_btree_get_keys(cur, block, &key); for (level++, ptr = 1; ptr == 1 && level < cur->bc_nlevels; level++) { #ifdef DEBUG int error; #endif block = xfs_btree_get_block(cur, level, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) return error; #endif ptr = cur->bc_levels[level].ptr; kp = xfs_btree_key_addr(cur, ptr, block); xfs_btree_copy_keys(cur, kp, &key, 1); xfs_btree_log_keys(cur, bp, ptr, ptr); } return 0; } /* * Update the record referred to by cur to the value in the * given record. This either works (return 0) or gets an * EFSCORRUPTED error. */ int xfs_btree_update( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) { struct xfs_btree_block *block; struct xfs_buf *bp; int error; int ptr; union xfs_btree_rec *rp; /* Pick up the current block. */ block = xfs_btree_get_block(cur, 0, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, 0, bp); if (error) goto error0; #endif /* Get the address of the rec to be updated. */ ptr = cur->bc_levels[0].ptr; rp = xfs_btree_rec_addr(cur, ptr, block); /* Fill in the new contents and log them. */ xfs_btree_copy_recs(cur, rp, rec, 1); xfs_btree_log_recs(cur, bp, ptr, ptr); /* Pass new key value up to our parent. */ if (xfs_btree_needs_key_update(cur, ptr)) { error = xfs_btree_update_keys(cur, 0); if (error) goto error0; } return 0; error0: return error; } /* * Move 1 record left from cur/level if possible. * Update cur to reflect the new path. */ STATIC int /* error */ xfs_btree_lshift( struct xfs_btree_cur *cur, int level, int *stat) /* success/failure */ { struct xfs_buf *lbp; /* left buffer pointer */ struct xfs_btree_block *left; /* left btree block */ int lrecs; /* left record count */ struct xfs_buf *rbp; /* right buffer pointer */ struct xfs_btree_block *right; /* right btree block */ struct xfs_btree_cur *tcur; /* temporary btree cursor */ int rrecs; /* right record count */ union xfs_btree_ptr lptr; /* left btree pointer */ union xfs_btree_key *rkp = NULL; /* right btree key */ union xfs_btree_ptr *rpp = NULL; /* right address pointer */ union xfs_btree_rec *rrp = NULL; /* right record pointer */ int error; /* error return value */ int i; if (xfs_btree_at_iroot(cur, level)) goto out0; /* Set up variables for this block as "right". */ right = xfs_btree_get_block(cur, level, &rbp); #ifdef DEBUG error = xfs_btree_check_block(cur, right, level, rbp); if (error) goto error0; #endif /* If we've got no left sibling then we can't shift an entry left. */ xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB); if (xfs_btree_ptr_is_null(cur, &lptr)) goto out0; /* * If the cursor entry is the one that would be moved, don't * do it... it's too complicated. */ if (cur->bc_levels[level].ptr <= 1) goto out0; /* Set up the left neighbor as "left". */ error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp); if (error) goto error0; /* If it's full, it can't take another entry. */ lrecs = xfs_btree_get_numrecs(left); if (lrecs == cur->bc_ops->get_maxrecs(cur, level)) goto out0; rrecs = xfs_btree_get_numrecs(right); /* * We add one entry to the left side and remove one for the right side. * Account for it here, the changes will be updated on disk and logged * later. */ lrecs++; rrecs--; XFS_BTREE_STATS_INC(cur, lshift); XFS_BTREE_STATS_ADD(cur, moves, 1); /* * If non-leaf, copy a key and a ptr to the left block. * Log the changes to the left block. */ if (level > 0) { /* It's a non-leaf. Move keys and pointers. */ union xfs_btree_key *lkp; /* left btree key */ union xfs_btree_ptr *lpp; /* left address pointer */ lkp = xfs_btree_key_addr(cur, lrecs, left); rkp = xfs_btree_key_addr(cur, 1, right); lpp = xfs_btree_ptr_addr(cur, lrecs, left); rpp = xfs_btree_ptr_addr(cur, 1, right); error = xfs_btree_debug_check_ptr(cur, rpp, 0, level); if (error) goto error0; xfs_btree_copy_keys(cur, lkp, rkp, 1); xfs_btree_copy_ptrs(cur, lpp, rpp, 1); xfs_btree_log_keys(cur, lbp, lrecs, lrecs); xfs_btree_log_ptrs(cur, lbp, lrecs, lrecs); ASSERT(cur->bc_ops->keys_inorder(cur, xfs_btree_key_addr(cur, lrecs - 1, left), lkp)); } else { /* It's a leaf. Move records. */ union xfs_btree_rec *lrp; /* left record pointer */ lrp = xfs_btree_rec_addr(cur, lrecs, left); rrp = xfs_btree_rec_addr(cur, 1, right); xfs_btree_copy_recs(cur, lrp, rrp, 1); xfs_btree_log_recs(cur, lbp, lrecs, lrecs); ASSERT(cur->bc_ops->recs_inorder(cur, xfs_btree_rec_addr(cur, lrecs - 1, left), lrp)); } xfs_btree_set_numrecs(left, lrecs); xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS); xfs_btree_set_numrecs(right, rrecs); xfs_btree_log_block(cur, rbp, XFS_BB_NUMRECS); /* * Slide the contents of right down one entry. */ XFS_BTREE_STATS_ADD(cur, moves, rrecs - 1); if (level > 0) { /* It's a nonleaf. operate on keys and ptrs */ for (i = 0; i < rrecs; i++) { error = xfs_btree_debug_check_ptr(cur, rpp, i + 1, level); if (error) goto error0; } xfs_btree_shift_keys(cur, xfs_btree_key_addr(cur, 2, right), -1, rrecs); xfs_btree_shift_ptrs(cur, xfs_btree_ptr_addr(cur, 2, right), -1, rrecs); xfs_btree_log_keys(cur, rbp, 1, rrecs); xfs_btree_log_ptrs(cur, rbp, 1, rrecs); } else { /* It's a leaf. operate on records */ xfs_btree_shift_recs(cur, xfs_btree_rec_addr(cur, 2, right), -1, rrecs); xfs_btree_log_recs(cur, rbp, 1, rrecs); } /* * Using a temporary cursor, update the parent key values of the * block on the left. */ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_dup_cursor(cur, &tcur); if (error) goto error0; i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_btree_decrement(tcur, level, &i); if (error) goto error1; /* Update the parent high keys of the left block, if needed. */ error = xfs_btree_update_keys(tcur, level); if (error) goto error1; xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); } /* Update the parent keys of the right block. */ error = xfs_btree_update_keys(cur, level); if (error) goto error0; /* Slide the cursor value left one. */ cur->bc_levels[level].ptr--; *stat = 1; return 0; out0: *stat = 0; return 0; error0: return error; error1: xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR); return error; } /* * Move 1 record right from cur/level if possible. * Update cur to reflect the new path. */ STATIC int /* error */ xfs_btree_rshift( struct xfs_btree_cur *cur, int level, int *stat) /* success/failure */ { struct xfs_buf *lbp; /* left buffer pointer */ struct xfs_btree_block *left; /* left btree block */ struct xfs_buf *rbp; /* right buffer pointer */ struct xfs_btree_block *right; /* right btree block */ struct xfs_btree_cur *tcur; /* temporary btree cursor */ union xfs_btree_ptr rptr; /* right block pointer */ union xfs_btree_key *rkp; /* right btree key */ int rrecs; /* right record count */ int lrecs; /* left record count */ int error; /* error return value */ int i; /* loop counter */ if (xfs_btree_at_iroot(cur, level)) goto out0; /* Set up variables for this block as "left". */ left = xfs_btree_get_block(cur, level, &lbp); #ifdef DEBUG error = xfs_btree_check_block(cur, left, level, lbp); if (error) goto error0; #endif /* If we've got no right sibling then we can't shift an entry right. */ xfs_btree_get_sibling(cur, left, &rptr, XFS_BB_RIGHTSIB); if (xfs_btree_ptr_is_null(cur, &rptr)) goto out0; /* * If the cursor entry is the one that would be moved, don't * do it... it's too complicated. */ lrecs = xfs_btree_get_numrecs(left); if (cur->bc_levels[level].ptr >= lrecs) goto out0; /* Set up the right neighbor as "right". */ error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp); if (error) goto error0; /* If it's full, it can't take another entry. */ rrecs = xfs_btree_get_numrecs(right); if (rrecs == cur->bc_ops->get_maxrecs(cur, level)) goto out0; XFS_BTREE_STATS_INC(cur, rshift); XFS_BTREE_STATS_ADD(cur, moves, rrecs); /* * Make a hole at the start of the right neighbor block, then * copy the last left block entry to the hole. */ if (level > 0) { /* It's a nonleaf. make a hole in the keys and ptrs */ union xfs_btree_key *lkp; union xfs_btree_ptr *lpp; union xfs_btree_ptr *rpp; lkp = xfs_btree_key_addr(cur, lrecs, left); lpp = xfs_btree_ptr_addr(cur, lrecs, left); rkp = xfs_btree_key_addr(cur, 1, right); rpp = xfs_btree_ptr_addr(cur, 1, right); for (i = rrecs - 1; i >= 0; i--) { error = xfs_btree_debug_check_ptr(cur, rpp, i, level); if (error) goto error0; } xfs_btree_shift_keys(cur, rkp, 1, rrecs); xfs_btree_shift_ptrs(cur, rpp, 1, rrecs); error = xfs_btree_debug_check_ptr(cur, lpp, 0, level); if (error) goto error0; /* Now put the new data in, and log it. */ xfs_btree_copy_keys(cur, rkp, lkp, 1); xfs_btree_copy_ptrs(cur, rpp, lpp, 1); xfs_btree_log_keys(cur, rbp, 1, rrecs + 1); xfs_btree_log_ptrs(cur, rbp, 1, rrecs + 1); ASSERT(cur->bc_ops->keys_inorder(cur, rkp, xfs_btree_key_addr(cur, 2, right))); } else { /* It's a leaf. make a hole in the records */ union xfs_btree_rec *lrp; union xfs_btree_rec *rrp; lrp = xfs_btree_rec_addr(cur, lrecs, left); rrp = xfs_btree_rec_addr(cur, 1, right); xfs_btree_shift_recs(cur, rrp, 1, rrecs); /* Now put the new data in, and log it. */ xfs_btree_copy_recs(cur, rrp, lrp, 1); xfs_btree_log_recs(cur, rbp, 1, rrecs + 1); } /* * Decrement and log left's numrecs, bump and log right's numrecs. */ xfs_btree_set_numrecs(left, --lrecs); xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS); xfs_btree_set_numrecs(right, ++rrecs); xfs_btree_log_block(cur, rbp, XFS_BB_NUMRECS); /* * Using a temporary cursor, update the parent key values of the * block on the right. */ error = xfs_btree_dup_cursor(cur, &tcur); if (error) goto error0; i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_btree_increment(tcur, level, &i); if (error) goto error1; /* Update the parent high keys of the left block, if needed. */ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_update_keys(cur, level); if (error) goto error1; } /* Update the parent keys of the right block. */ error = xfs_btree_update_keys(tcur, level); if (error) goto error1; xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); *stat = 1; return 0; out0: *stat = 0; return 0; error0: return error; error1: xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR); return error; } static inline int xfs_btree_alloc_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *hint_block, union xfs_btree_ptr *new_block, int *stat) { int error; /* * Don't allow block allocation for a staging cursor, because staging * cursors do not support regular btree modifications. * * Bulk loading uses a separate callback to obtain new blocks from a * preallocated list, which prevents ENOSPC failures during loading. */ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) { ASSERT(0); return -EFSCORRUPTED; } error = cur->bc_ops->alloc_block(cur, hint_block, new_block, stat); trace_xfs_btree_alloc_block(cur, new_block, *stat, error); return error; } /* * Split cur/level block in half. * Return new block number and the key to its first * record (to be inserted into parent). */ STATIC int /* error */ __xfs_btree_split( struct xfs_btree_cur *cur, int level, union xfs_btree_ptr *ptrp, union xfs_btree_key *key, struct xfs_btree_cur **curp, int *stat) /* success/failure */ { union xfs_btree_ptr lptr; /* left sibling block ptr */ struct xfs_buf *lbp; /* left buffer pointer */ struct xfs_btree_block *left; /* left btree block */ union xfs_btree_ptr rptr; /* right sibling block ptr */ struct xfs_buf *rbp; /* right buffer pointer */ struct xfs_btree_block *right; /* right btree block */ union xfs_btree_ptr rrptr; /* right-right sibling ptr */ struct xfs_buf *rrbp; /* right-right buffer pointer */ struct xfs_btree_block *rrblock; /* right-right btree block */ int lrecs; int rrecs; int src_index; int error; /* error return value */ int i; XFS_BTREE_STATS_INC(cur, split); /* Set up left block (current one). */ left = xfs_btree_get_block(cur, level, &lbp); #ifdef DEBUG error = xfs_btree_check_block(cur, left, level, lbp); if (error) goto error0; #endif xfs_btree_buf_to_ptr(cur, lbp, &lptr); /* Allocate the new block. If we can't do it, we're toast. Give up. */ error = xfs_btree_alloc_block(cur, &lptr, &rptr, stat); if (error) goto error0; if (*stat == 0) goto out0; XFS_BTREE_STATS_INC(cur, alloc); /* Set up the new block as "right". */ error = xfs_btree_get_buf_block(cur, &rptr, &right, &rbp); if (error) goto error0; /* Fill in the btree header for the new right block. */ xfs_btree_init_block_cur(cur, rbp, xfs_btree_get_level(left), 0); /* * Split the entries between the old and the new block evenly. * Make sure that if there's an odd number of entries now, that * each new block will have the same number of entries. */ lrecs = xfs_btree_get_numrecs(left); rrecs = lrecs / 2; if ((lrecs & 1) && cur->bc_levels[level].ptr <= rrecs + 1) rrecs++; src_index = (lrecs - rrecs + 1); XFS_BTREE_STATS_ADD(cur, moves, rrecs); /* Adjust numrecs for the later get_*_keys() calls. */ lrecs -= rrecs; xfs_btree_set_numrecs(left, lrecs); xfs_btree_set_numrecs(right, xfs_btree_get_numrecs(right) + rrecs); /* * Copy btree block entries from the left block over to the * new block, the right. Update the right block and log the * changes. */ if (level > 0) { /* It's a non-leaf. Move keys and pointers. */ union xfs_btree_key *lkp; /* left btree key */ union xfs_btree_ptr *lpp; /* left address pointer */ union xfs_btree_key *rkp; /* right btree key */ union xfs_btree_ptr *rpp; /* right address pointer */ lkp = xfs_btree_key_addr(cur, src_index, left); lpp = xfs_btree_ptr_addr(cur, src_index, left); rkp = xfs_btree_key_addr(cur, 1, right); rpp = xfs_btree_ptr_addr(cur, 1, right); for (i = src_index; i < rrecs; i++) { error = xfs_btree_debug_check_ptr(cur, lpp, i, level); if (error) goto error0; } /* Copy the keys & pointers to the new block. */ xfs_btree_copy_keys(cur, rkp, lkp, rrecs); xfs_btree_copy_ptrs(cur, rpp, lpp, rrecs); xfs_btree_log_keys(cur, rbp, 1, rrecs); xfs_btree_log_ptrs(cur, rbp, 1, rrecs); /* Stash the keys of the new block for later insertion. */ xfs_btree_get_node_keys(cur, right, key); } else { /* It's a leaf. Move records. */ union xfs_btree_rec *lrp; /* left record pointer */ union xfs_btree_rec *rrp; /* right record pointer */ lrp = xfs_btree_rec_addr(cur, src_index, left); rrp = xfs_btree_rec_addr(cur, 1, right); /* Copy records to the new block. */ xfs_btree_copy_recs(cur, rrp, lrp, rrecs); xfs_btree_log_recs(cur, rbp, 1, rrecs); /* Stash the keys of the new block for later insertion. */ xfs_btree_get_leaf_keys(cur, right, key); } /* * Find the left block number by looking in the buffer. * Adjust sibling pointers. */ xfs_btree_get_sibling(cur, left, &rrptr, XFS_BB_RIGHTSIB); xfs_btree_set_sibling(cur, right, &rrptr, XFS_BB_RIGHTSIB); xfs_btree_set_sibling(cur, right, &lptr, XFS_BB_LEFTSIB); xfs_btree_set_sibling(cur, left, &rptr, XFS_BB_RIGHTSIB); xfs_btree_log_block(cur, rbp, XFS_BB_ALL_BITS); xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB); /* * If there's a block to the new block's right, make that block * point back to right instead of to left. */ if (!xfs_btree_ptr_is_null(cur, &rrptr)) { error = xfs_btree_read_buf_block(cur, &rrptr, 0, &rrblock, &rrbp); if (error) goto error0; xfs_btree_set_sibling(cur, rrblock, &rptr, XFS_BB_LEFTSIB); xfs_btree_log_block(cur, rrbp, XFS_BB_LEFTSIB); } /* Update the parent high keys of the left block, if needed. */ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) { error = xfs_btree_update_keys(cur, level); if (error) goto error0; } /* * If the cursor is really in the right block, move it there. * If it's just pointing past the last entry in left, then we'll * insert there, so don't change anything in that case. */ if (cur->bc_levels[level].ptr > lrecs + 1) { xfs_btree_setbuf(cur, level, rbp); cur->bc_levels[level].ptr -= lrecs; } /* * If there are more levels, we'll need another cursor which refers * the right block, no matter where this cursor was. */ if (level + 1 < cur->bc_nlevels) { error = xfs_btree_dup_cursor(cur, curp); if (error) goto error0; (*curp)->bc_levels[level + 1].ptr++; } *ptrp = rptr; *stat = 1; return 0; out0: *stat = 0; return 0; error0: return error; } #ifdef __KERNEL__ struct xfs_btree_split_args { struct xfs_btree_cur *cur; int level; union xfs_btree_ptr *ptrp; union xfs_btree_key *key; struct xfs_btree_cur **curp; int *stat; /* success/failure */ int result; bool kswapd; /* allocation in kswapd context */ struct completion *done; struct work_struct work; }; /* * Stack switching interfaces for allocation */ static void xfs_btree_split_worker( struct work_struct *work) { struct xfs_btree_split_args *args = container_of(work, struct xfs_btree_split_args, work); unsigned long pflags; unsigned long new_pflags = 0; /* * we are in a transaction context here, but may also be doing work * in kswapd context, and hence we may need to inherit that state * temporarily to ensure that we don't block waiting for memory reclaim * in any way. */ if (args->kswapd) new_pflags |= PF_MEMALLOC | PF_KSWAPD; current_set_flags_nested(&pflags, new_pflags); xfs_trans_set_context(args->cur->bc_tp); args->result = __xfs_btree_split(args->cur, args->level, args->ptrp, args->key, args->curp, args->stat); xfs_trans_clear_context(args->cur->bc_tp); current_restore_flags_nested(&pflags, new_pflags); /* * Do not access args after complete() has run here. We don't own args * and the owner may run and free args before we return here. */ complete(args->done); } /* * BMBT split requests often come in with little stack to work on so we push * them off to a worker thread so there is lots of stack to use. For the other * btree types, just call directly to avoid the context switch overhead here. * * Care must be taken here - the work queue rescuer thread introduces potential * AGF <> worker queue deadlocks if the BMBT block allocation has to lock new * AGFs to allocate blocks. A task being run by the rescuer could attempt to * lock an AGF that is already locked by a task queued to run by the rescuer, * resulting in an ABBA deadlock as the rescuer cannot run the lock holder to * release it until the current thread it is running gains the lock. * * To avoid this issue, we only ever queue BMBT splits that don't have an AGF * already locked to allocate from. The only place that doesn't hold an AGF * locked is unwritten extent conversion at IO completion, but that has already * been offloaded to a worker thread and hence has no stack consumption issues * we have to worry about. */ STATIC int /* error */ xfs_btree_split( struct xfs_btree_cur *cur, int level, union xfs_btree_ptr *ptrp, union xfs_btree_key *key, struct xfs_btree_cur **curp, int *stat) /* success/failure */ { struct xfs_btree_split_args args; DECLARE_COMPLETION_ONSTACK(done); if (!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_tp->t_highest_agno == NULLAGNUMBER) return __xfs_btree_split(cur, level, ptrp, key, curp, stat); args.cur = cur; args.level = level; args.ptrp = ptrp; args.key = key; args.curp = curp; args.stat = stat; args.done = &done; args.kswapd = current_is_kswapd(); INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker); queue_work(xfs_alloc_wq, &args.work); wait_for_completion(&done); destroy_work_on_stack(&args.work); return args.result; } #else #define xfs_btree_split __xfs_btree_split #endif /* __KERNEL__ */ /* Move the records from a root leaf block to a separate block. */ STATIC void xfs_btree_promote_leaf_iroot( struct xfs_btree_cur *cur, struct xfs_btree_block *block, struct xfs_buf *cbp, union xfs_btree_ptr *cptr, struct xfs_btree_block *cblock) { union xfs_btree_rec *rp; union xfs_btree_rec *crp; union xfs_btree_key *kp; union xfs_btree_ptr *pp; struct xfs_btree_block *broot; int numrecs = xfs_btree_get_numrecs(block); /* Copy the records from the leaf broot into the new child block. */ rp = xfs_btree_rec_addr(cur, 1, block); crp = xfs_btree_rec_addr(cur, 1, cblock); xfs_btree_copy_recs(cur, crp, rp, numrecs); /* * Increment the tree height. * * Trickery here: The amount of memory that we need per record for the * ifork's btree root block may change when we convert the broot from a * leaf to a node block. Free the existing leaf broot so that nobody * thinks we need to migrate node pointers when we realloc the broot * buffer after bumping nlevels. */ cur->bc_ops->broot_realloc(cur, 0); cur->bc_nlevels++; cur->bc_levels[1].ptr = 1; /* * Allocate a new node broot and initialize it to point to the new * child block. */ broot = cur->bc_ops->broot_realloc(cur, 1); xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, cur->bc_nlevels - 1, 1, cur->bc_ino.ip->i_ino); pp = xfs_btree_ptr_addr(cur, 1, broot); kp = xfs_btree_key_addr(cur, 1, broot); xfs_btree_copy_ptrs(cur, pp, cptr, 1); xfs_btree_get_keys(cur, cblock, kp); /* Attach the new block to the cursor and log it. */ xfs_btree_setbuf(cur, 0, cbp); xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); xfs_btree_log_recs(cur, cbp, 1, numrecs); } /* * Move the keys and pointers from a root block to a separate block. * * Since the keyptr size does not change, all we have to do is increase the * tree height, copy the keyptrs to the new internal node (cblock), shrink * the root, and copy the pointers there. */ STATIC int xfs_btree_promote_node_iroot( struct xfs_btree_cur *cur, struct xfs_btree_block *block, int level, struct xfs_buf *cbp, union xfs_btree_ptr *cptr, struct xfs_btree_block *cblock) { union xfs_btree_key *ckp; union xfs_btree_key *kp; union xfs_btree_ptr *cpp; union xfs_btree_ptr *pp; int i; int error; int numrecs = xfs_btree_get_numrecs(block); /* * Increase tree height, adjusting the root block level to match. * We cannot change the root btree node size until we've copied the * block contents to the new child block. */ be16_add_cpu(&block->bb_level, 1); cur->bc_nlevels++; cur->bc_levels[level + 1].ptr = 1; /* * Adjust the root btree record count, then copy the keys from the old * root to the new child block. */ xfs_btree_set_numrecs(block, 1); kp = xfs_btree_key_addr(cur, 1, block); ckp = xfs_btree_key_addr(cur, 1, cblock); xfs_btree_copy_keys(cur, ckp, kp, numrecs); /* Check the pointers and copy them to the new child block. */ pp = xfs_btree_ptr_addr(cur, 1, block); cpp = xfs_btree_ptr_addr(cur, 1, cblock); for (i = 0; i < numrecs; i++) { error = xfs_btree_debug_check_ptr(cur, pp, i, level); if (error) return error; } xfs_btree_copy_ptrs(cur, cpp, pp, numrecs); /* * Set the first keyptr to point to the new child block, then shrink * the memory buffer for the root block. */ error = xfs_btree_debug_check_ptr(cur, cptr, 0, level); if (error) return error; xfs_btree_copy_ptrs(cur, pp, cptr, 1); xfs_btree_get_keys(cur, cblock, kp); cur->bc_ops->broot_realloc(cur, 1); /* Attach the new block to the cursor and log it. */ xfs_btree_setbuf(cur, level, cbp); xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS); xfs_btree_log_keys(cur, cbp, 1, numrecs); xfs_btree_log_ptrs(cur, cbp, 1, numrecs); return 0; } /* * Copy the old inode root contents into a real block and make the * broot point to it. */ int /* error */ xfs_btree_new_iroot( struct xfs_btree_cur *cur, /* btree cursor */ int *logflags, /* logging flags for inode */ int *stat) /* return status - 0 fail */ { struct xfs_buf *cbp; /* buffer for cblock */ struct xfs_btree_block *block; /* btree block */ struct xfs_btree_block *cblock; /* child btree block */ union xfs_btree_ptr aptr; union xfs_btree_ptr nptr; /* new block addr */ int level; /* btree level */ int error; /* error return code */ XFS_BTREE_STATS_INC(cur, newroot); ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); level = cur->bc_nlevels - 1; block = xfs_btree_get_iroot(cur); ASSERT(level > 0 || (cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)); if (level > 0) aptr = *xfs_btree_ptr_addr(cur, 1, block); else aptr.l = cpu_to_be64(XFS_INO_TO_FSB(cur->bc_mp, cur->bc_ino.ip->i_ino)); /* Allocate the new block. If we can't do it, we're toast. Give up. */ error = xfs_btree_alloc_block(cur, &aptr, &nptr, stat); if (error) goto error0; if (*stat == 0) return 0; XFS_BTREE_STATS_INC(cur, alloc); /* Copy the root into a real block. */ error = xfs_btree_get_buf_block(cur, &nptr, &cblock, &cbp); if (error) goto error0; /* * we can't just memcpy() the root in for CRC enabled btree blocks. * In that case have to also ensure the blkno remains correct */ memcpy(cblock, block, xfs_btree_block_len(cur)); if (xfs_has_crc(cur->bc_mp)) { __be64 bno = cpu_to_be64(xfs_buf_daddr(cbp)); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) cblock->bb_u.l.bb_blkno = bno; else cblock->bb_u.s.bb_blkno = bno; } if (level > 0) { error = xfs_btree_promote_node_iroot(cur, block, level, cbp, &nptr, cblock); if (error) goto error0; } else { xfs_btree_promote_leaf_iroot(cur, block, cbp, &nptr, cblock); } *logflags |= XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork); *stat = 1; return 0; error0: return error; } static void xfs_btree_set_root( struct xfs_btree_cur *cur, const union xfs_btree_ptr *ptr, int inc) { if (cur->bc_flags & XFS_BTREE_STAGING) { /* Update the btree root information for a per-AG fake root. */ cur->bc_ag.afake->af_root = be32_to_cpu(ptr->s); cur->bc_ag.afake->af_levels += inc; } else { cur->bc_ops->set_root(cur, ptr, inc); } } /* * Allocate a new root block, fill it in. */ STATIC int /* error */ xfs_btree_new_root( struct xfs_btree_cur *cur, /* btree cursor */ int *stat) /* success/failure */ { struct xfs_btree_block *block; /* one half of the old root block */ struct xfs_buf *bp; /* buffer containing block */ int error; /* error return value */ struct xfs_buf *lbp; /* left buffer pointer */ struct xfs_btree_block *left; /* left btree block */ struct xfs_buf *nbp; /* new (root) buffer */ struct xfs_btree_block *new; /* new (root) btree block */ int nptr; /* new value for key index, 1 or 2 */ struct xfs_buf *rbp; /* right buffer pointer */ struct xfs_btree_block *right; /* right btree block */ union xfs_btree_ptr rptr; union xfs_btree_ptr lptr; XFS_BTREE_STATS_INC(cur, newroot); /* initialise our start point from the cursor */ xfs_btree_init_ptr_from_cur(cur, &rptr); /* Allocate the new block. If we can't do it, we're toast. Give up. */ error = xfs_btree_alloc_block(cur, &rptr, &lptr, stat); if (error) goto error0; if (*stat == 0) goto out0; XFS_BTREE_STATS_INC(cur, alloc); /* Set up the new block. */ error = xfs_btree_get_buf_block(cur, &lptr, &new, &nbp); if (error) goto error0; /* Set the root in the holding structure increasing the level by 1. */ xfs_btree_set_root(cur, &lptr, 1); /* * At the previous root level there are now two blocks: the old root, * and the new block generated when it was split. We don't know which * one the cursor is pointing at, so we set up variables "left" and * "right" for each case. */ block = xfs_btree_get_block(cur, cur->bc_nlevels - 1, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, cur->bc_nlevels - 1, bp); if (error) goto error0; #endif xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB); if (!xfs_btree_ptr_is_null(cur, &rptr)) { /* Our block is left, pick up the right block. */ lbp = bp; xfs_btree_buf_to_ptr(cur, lbp, &lptr); left = block; error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp); if (error) goto error0; bp = rbp; nptr = 1; } else { /* Our block is right, pick up the left block. */ rbp = bp; xfs_btree_buf_to_ptr(cur, rbp, &rptr); right = block; xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB); error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp); if (error) goto error0; bp = lbp; nptr = 2; } /* Fill in the new block's btree header and log it. */ xfs_btree_init_block_cur(cur, nbp, cur->bc_nlevels, 2); xfs_btree_log_block(cur, nbp, XFS_BB_ALL_BITS); ASSERT(!xfs_btree_ptr_is_null(cur, &lptr) && !xfs_btree_ptr_is_null(cur, &rptr)); /* Fill in the key data in the new root. */ if (xfs_btree_get_level(left) > 0) { /* * Get the keys for the left block's keys and put them directly * in the parent block. Do the same for the right block. */ xfs_btree_get_node_keys(cur, left, xfs_btree_key_addr(cur, 1, new)); xfs_btree_get_node_keys(cur, right, xfs_btree_key_addr(cur, 2, new)); } else { /* * Get the keys for the left block's records and put them * directly in the parent block. Do the same for the right * block. */ xfs_btree_get_leaf_keys(cur, left, xfs_btree_key_addr(cur, 1, new)); xfs_btree_get_leaf_keys(cur, right, xfs_btree_key_addr(cur, 2, new)); } xfs_btree_log_keys(cur, nbp, 1, 2); /* Fill in the pointer data in the new root. */ xfs_btree_copy_ptrs(cur, xfs_btree_ptr_addr(cur, 1, new), &lptr, 1); xfs_btree_copy_ptrs(cur, xfs_btree_ptr_addr(cur, 2, new), &rptr, 1); xfs_btree_log_ptrs(cur, nbp, 1, 2); /* Fix up the cursor. */ xfs_btree_setbuf(cur, cur->bc_nlevels, nbp); cur->bc_levels[cur->bc_nlevels].ptr = nptr; cur->bc_nlevels++; ASSERT(cur->bc_nlevels <= cur->bc_maxlevels); *stat = 1; return 0; error0: return error; out0: *stat = 0; return 0; } STATIC int xfs_btree_make_block_unfull( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* btree level */ int numrecs,/* # of recs in block */ int *oindex,/* old tree index */ int *index, /* new tree index */ union xfs_btree_ptr *nptr, /* new btree ptr */ struct xfs_btree_cur **ncur, /* new btree cursor */ union xfs_btree_key *key, /* key of new block */ int *stat) { int error = 0; if (xfs_btree_at_iroot(cur, level)) { struct xfs_inode *ip = cur->bc_ino.ip; if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) { /* A root block that can be made bigger. */ cur->bc_ops->broot_realloc(cur, numrecs + 1); *stat = 1; } else { /* A root block that needs replacing */ int logflags = 0; error = xfs_btree_new_iroot(cur, &logflags, stat); if (error || *stat == 0) return error; xfs_trans_log_inode(cur->bc_tp, ip, logflags); } return 0; } /* First, try shifting an entry to the right neighbor. */ error = xfs_btree_rshift(cur, level, stat); if (error || *stat) return error; /* Next, try shifting an entry to the left neighbor. */ error = xfs_btree_lshift(cur, level, stat); if (error) return error; if (*stat) { *oindex = *index = cur->bc_levels[level].ptr; return 0; } /* * Next, try splitting the current block in half. * * If this works we have to re-set our variables because we * could be in a different block now. */ error = xfs_btree_split(cur, level, nptr, key, ncur, stat); if (error || *stat == 0) return error; *index = cur->bc_levels[level].ptr; return 0; } /* * Insert one record/level. Return information to the caller * allowing the next level up to proceed if necessary. */ STATIC int xfs_btree_insrec( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level to insert record at */ union xfs_btree_ptr *ptrp, /* i/o: block number inserted */ union xfs_btree_rec *rec, /* record to insert */ union xfs_btree_key *key, /* i/o: block key for ptrp */ struct xfs_btree_cur **curp, /* output: new cursor replacing cur */ int *stat) /* success/failure */ { struct xfs_btree_block *block; /* btree block */ struct xfs_buf *bp; /* buffer for block */ union xfs_btree_ptr nptr; /* new block ptr */ struct xfs_btree_cur *ncur = NULL; /* new btree cursor */ union xfs_btree_key nkey; /* new block key */ union xfs_btree_key *lkey; int optr; /* old key/record index */ int ptr; /* key/record index */ int numrecs;/* number of records */ int error; /* error return value */ int i; xfs_daddr_t old_bn; ncur = NULL; lkey = &nkey; /* * If we have an external root pointer, and we've made it to the * root level, allocate a new root block and we're done. */ if (cur->bc_ops->type != XFS_BTREE_TYPE_INODE && level >= cur->bc_nlevels) { error = xfs_btree_new_root(cur, stat); xfs_btree_set_ptr_null(cur, ptrp); return error; } /* If we're off the left edge, return failure. */ ptr = cur->bc_levels[level].ptr; if (ptr == 0) { *stat = 0; return 0; } optr = ptr; XFS_BTREE_STATS_INC(cur, insrec); /* Get pointers to the btree buffer and block. */ block = xfs_btree_get_block(cur, level, &bp); old_bn = bp ? xfs_buf_daddr(bp) : XFS_BUF_DADDR_NULL; numrecs = xfs_btree_get_numrecs(block); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto error0; /* Check that the new entry is being inserted in the right place. */ if (ptr <= numrecs) { if (level == 0) { ASSERT(cur->bc_ops->recs_inorder(cur, rec, xfs_btree_rec_addr(cur, ptr, block))); } else { ASSERT(cur->bc_ops->keys_inorder(cur, key, xfs_btree_key_addr(cur, ptr, block))); } } #endif /* * If the block is full, we can't insert the new entry until we * make the block un-full. */ xfs_btree_set_ptr_null(cur, &nptr); if (numrecs == cur->bc_ops->get_maxrecs(cur, level)) { error = xfs_btree_make_block_unfull(cur, level, numrecs, &optr, &ptr, &nptr, &ncur, lkey, stat); if (error || *stat == 0) goto error0; } /* * The current block may have changed if the block was * previously full and we have just made space in it. */ block = xfs_btree_get_block(cur, level, &bp); numrecs = xfs_btree_get_numrecs(block); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto error0; #endif /* * At this point we know there's room for our new entry in the block * we're pointing at. */ XFS_BTREE_STATS_ADD(cur, moves, numrecs - ptr + 1); if (level > 0) { /* It's a nonleaf. make a hole in the keys and ptrs */ union xfs_btree_key *kp; union xfs_btree_ptr *pp; kp = xfs_btree_key_addr(cur, ptr, block); pp = xfs_btree_ptr_addr(cur, ptr, block); for (i = numrecs - ptr; i >= 0; i--) { error = xfs_btree_debug_check_ptr(cur, pp, i, level); if (error) goto error0; } xfs_btree_shift_keys(cur, kp, 1, numrecs - ptr + 1); xfs_btree_shift_ptrs(cur, pp, 1, numrecs - ptr + 1); error = xfs_btree_debug_check_ptr(cur, ptrp, 0, level); if (error) goto error0; /* Now put the new data in, bump numrecs and log it. */ xfs_btree_copy_keys(cur, kp, key, 1); xfs_btree_copy_ptrs(cur, pp, ptrp, 1); numrecs++; xfs_btree_set_numrecs(block, numrecs); xfs_btree_log_ptrs(cur, bp, ptr, numrecs); xfs_btree_log_keys(cur, bp, ptr, numrecs); #ifdef DEBUG if (ptr < numrecs) { ASSERT(cur->bc_ops->keys_inorder(cur, kp, xfs_btree_key_addr(cur, ptr + 1, block))); } #endif } else { /* It's a leaf. make a hole in the records */ union xfs_btree_rec *rp; rp = xfs_btree_rec_addr(cur, ptr, block); xfs_btree_shift_recs(cur, rp, 1, numrecs - ptr + 1); /* Now put the new data in, bump numrecs and log it. */ xfs_btree_copy_recs(cur, rp, rec, 1); xfs_btree_set_numrecs(block, ++numrecs); xfs_btree_log_recs(cur, bp, ptr, numrecs); #ifdef DEBUG if (ptr < numrecs) { ASSERT(cur->bc_ops->recs_inorder(cur, rp, xfs_btree_rec_addr(cur, ptr + 1, block))); } #endif } /* Log the new number of records in the btree header. */ xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* * Update btree keys to reflect the newly added record or keyptr. * There are three cases here to be aware of. Normally, all we have to * do is walk towards the root, updating keys as necessary. * * If the caller had us target a full block for the insertion, we dealt * with that by calling the _make_block_unfull function. If the * "make unfull" function splits the block, it'll hand us back the key * and pointer of the new block. We haven't yet added the new block to * the next level up, so if we decide to add the new record to the new * block (bp->b_bn != old_bn), we have to update the caller's pointer * so that the caller adds the new block with the correct key. * * However, there is a third possibility-- if the selected block is the * root block of an inode-rooted btree and cannot be expanded further, * the "make unfull" function moves the root block contents to a new * block and updates the root block to point to the new block. In this * case, no block pointer is passed back because the block has already * been added to the btree. In this case, we need to use the regular * key update function, just like the first case. This is critical for * overlapping btrees, because the high key must be updated to reflect * the entire tree, not just the subtree accessible through the first * child of the root (which is now two levels down from the root). */ if (!xfs_btree_ptr_is_null(cur, &nptr) && bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); if (error) goto error0; } /* * Return the new block number, if any. * If there is one, give back a record value and a cursor too. */ *ptrp = nptr; if (!xfs_btree_ptr_is_null(cur, &nptr)) { xfs_btree_copy_keys(cur, key, lkey, 1); *curp = ncur; } *stat = 1; return 0; error0: if (ncur) xfs_btree_del_cursor(ncur, error); return error; } /* * Insert the record at the point referenced by cur. * * A multi-level split of the tree on insert will invalidate the original * cursor. All callers of this function should assume that the cursor is * no longer valid and revalidate it. */ int xfs_btree_insert( struct xfs_btree_cur *cur, int *stat) { int error; /* error return value */ int i; /* result value, 0 for failure */ int level; /* current level number in btree */ union xfs_btree_ptr nptr; /* new block number (split result) */ struct xfs_btree_cur *ncur; /* new cursor (split result) */ struct xfs_btree_cur *pcur; /* previous level's cursor */ union xfs_btree_key bkey; /* key of block to insert */ union xfs_btree_key *key; union xfs_btree_rec rec; /* record to insert */ level = 0; ncur = NULL; pcur = cur; key = &bkey; xfs_btree_set_ptr_null(cur, &nptr); /* Make a key out of the record data to be inserted, and save it. */ cur->bc_ops->init_rec_from_cur(cur, &rec); cur->bc_ops->init_key_from_rec(key, &rec); /* * Loop going up the tree, starting at the leaf level. * Stop when we don't get a split block, that must mean that * the insert is finished with this level. */ do { /* * Insert nrec/nptr into this level of the tree. * Note if we fail, nptr will be null. */ error = xfs_btree_insrec(pcur, level, &nptr, &rec, key, &ncur, &i); if (error) { if (pcur != cur) xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR); goto error0; } if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } level++; /* * See if the cursor we just used is trash. * Can't trash the caller's cursor, but otherwise we should * if ncur is a new cursor or we're about to be done. */ if (pcur != cur && (ncur || xfs_btree_ptr_is_null(cur, &nptr))) { /* Save the state from the cursor before we trash it */ if (cur->bc_ops->update_cursor && !(cur->bc_flags & XFS_BTREE_STAGING)) cur->bc_ops->update_cursor(pcur, cur); cur->bc_nlevels = pcur->bc_nlevels; xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR); } /* If we got a new cursor, switch to it. */ if (ncur) { pcur = ncur; ncur = NULL; } } while (!xfs_btree_ptr_is_null(cur, &nptr)); *stat = i; return 0; error0: return error; } /* Move the records from a child leaf block to the root block. */ STATIC void xfs_btree_demote_leaf_child( struct xfs_btree_cur *cur, struct xfs_btree_block *cblock, int numrecs) { union xfs_btree_rec *rp; union xfs_btree_rec *crp; struct xfs_btree_block *broot; /* * Decrease the tree height. * * Trickery here: The amount of memory that we need per record for the * ifork's btree root block may change when we convert the broot from a * node to a leaf. Free the old node broot so that we can get a fresh * leaf broot. */ cur->bc_ops->broot_realloc(cur, 0); cur->bc_nlevels--; /* * Allocate a new leaf broot and copy the records from the old child. * Detach the old child from the cursor. */ broot = cur->bc_ops->broot_realloc(cur, numrecs); xfs_btree_init_block(cur->bc_mp, broot, cur->bc_ops, 0, numrecs, cur->bc_ino.ip->i_ino); rp = xfs_btree_rec_addr(cur, 1, broot); crp = xfs_btree_rec_addr(cur, 1, cblock); xfs_btree_copy_recs(cur, rp, crp, numrecs); cur->bc_levels[0].bp = NULL; } /* * Move the keyptrs from a child node block to the root block. * * Since the keyptr size does not change, all we have to do is increase the * tree height, copy the keyptrs to the new internal node (cblock), shrink * the root, and copy the pointers there. */ STATIC int xfs_btree_demote_node_child( struct xfs_btree_cur *cur, struct xfs_btree_block *cblock, int level, int numrecs) { struct xfs_btree_block *block; union xfs_btree_key *ckp; union xfs_btree_key *kp; union xfs_btree_ptr *cpp; union xfs_btree_ptr *pp; int i; int error; /* * Adjust the root btree node size and the record count to match the * doomed child so that we can copy the keyptrs ahead of changing the * tree shape. */ block = cur->bc_ops->broot_realloc(cur, numrecs); xfs_btree_set_numrecs(block, numrecs); ASSERT(block->bb_numrecs == cblock->bb_numrecs); /* Copy keys from the doomed block. */ kp = xfs_btree_key_addr(cur, 1, block); ckp = xfs_btree_key_addr(cur, 1, cblock); xfs_btree_copy_keys(cur, kp, ckp, numrecs); /* Copy pointers from the doomed block. */ pp = xfs_btree_ptr_addr(cur, 1, block); cpp = xfs_btree_ptr_addr(cur, 1, cblock); for (i = 0; i < numrecs; i++) { error = xfs_btree_debug_check_ptr(cur, cpp, i, level - 1); if (error) return error; } xfs_btree_copy_ptrs(cur, pp, cpp, numrecs); /* Decrease tree height, adjusting the root block level to match. */ cur->bc_levels[level - 1].bp = NULL; be16_add_cpu(&block->bb_level, -1); cur->bc_nlevels--; return 0; } /* * Try to merge a non-leaf block back into the inode root. * * Note: the killroot names comes from the fact that we're effectively * killing the old root block. But because we can't just delete the * inode we have to copy the single block it was pointing to into the * inode. */ STATIC int xfs_btree_kill_iroot( struct xfs_btree_cur *cur) { struct xfs_inode *ip = cur->bc_ino.ip; struct xfs_btree_block *block; struct xfs_btree_block *cblock; struct xfs_buf *cbp; int level; int numrecs; int error; #ifdef DEBUG union xfs_btree_ptr ptr; #endif ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); ASSERT((cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS) || cur->bc_nlevels > 1); /* * Don't deal with the root block needs to be a leaf case. * We're just going to turn the thing back into extents anyway. */ level = cur->bc_nlevels - 1; if (level == 1 && !(cur->bc_ops->geom_flags & XFS_BTGEO_IROOT_RECORDS)) goto out0; /* If we're already a leaf, jump out. */ if (level == 0) goto out0; /* * Give up if the root has multiple children. */ block = xfs_btree_get_iroot(cur); if (xfs_btree_get_numrecs(block) != 1) goto out0; cblock = xfs_btree_get_block(cur, level - 1, &cbp); numrecs = xfs_btree_get_numrecs(cblock); /* * Only do this if the next level will fit. * Then the data must be copied up to the inode, * instead of freeing the root you free the next level. */ if (numrecs > cur->bc_ops->get_dmaxrecs(cur, level)) goto out0; XFS_BTREE_STATS_INC(cur, killroot); #ifdef DEBUG xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_LEFTSIB); ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB); ASSERT(xfs_btree_ptr_is_null(cur, &ptr)); #endif if (level > 1) { error = xfs_btree_demote_node_child(cur, cblock, level, numrecs); if (error) return error; } else xfs_btree_demote_leaf_child(cur, cblock, numrecs); error = xfs_btree_free_block(cur, cbp); if (error) return error; xfs_trans_log_inode(cur->bc_tp, ip, XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork)); out0: return 0; } /* * Kill the current root node, and replace it with it's only child node. */ STATIC int xfs_btree_kill_root( struct xfs_btree_cur *cur, struct xfs_buf *bp, int level, union xfs_btree_ptr *newroot) { int error; XFS_BTREE_STATS_INC(cur, killroot); /* * Update the root pointer, decreasing the level by 1 and then * free the old root. */ xfs_btree_set_root(cur, newroot, -1); error = xfs_btree_free_block(cur, bp); if (error) return error; cur->bc_levels[level].bp = NULL; cur->bc_levels[level].ra = 0; cur->bc_nlevels--; return 0; } STATIC int xfs_btree_dec_cursor( struct xfs_btree_cur *cur, int level, int *stat) { int error; int i; if (level > 0) { error = xfs_btree_decrement(cur, level, &i); if (error) return error; } *stat = 1; return 0; } /* * Single level of the btree record deletion routine. * Delete record pointed to by cur/level. * Remove the record from its block then rebalance the tree. * Return 0 for error, 1 for done, 2 to go on to the next level. */ STATIC int /* error */ xfs_btree_delrec( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level removing record from */ int *stat) /* fail/done/go-on */ { struct xfs_btree_block *block; /* btree block */ union xfs_btree_ptr cptr; /* current block ptr */ struct xfs_buf *bp; /* buffer for block */ int error; /* error return value */ int i; /* loop counter */ union xfs_btree_ptr lptr; /* left sibling block ptr */ struct xfs_buf *lbp; /* left buffer pointer */ struct xfs_btree_block *left; /* left btree block */ int lrecs = 0; /* left record count */ int ptr; /* key/record index */ union xfs_btree_ptr rptr; /* right sibling block ptr */ struct xfs_buf *rbp; /* right buffer pointer */ struct xfs_btree_block *right; /* right btree block */ struct xfs_btree_block *rrblock; /* right-right btree block */ struct xfs_buf *rrbp; /* right-right buffer pointer */ int rrecs = 0; /* right record count */ struct xfs_btree_cur *tcur; /* temporary btree cursor */ int numrecs; /* temporary numrec count */ tcur = NULL; /* Get the index of the entry being deleted, check for nothing there. */ ptr = cur->bc_levels[level].ptr; if (ptr == 0) { *stat = 0; return 0; } /* Get the buffer & block containing the record or key/ptr. */ block = xfs_btree_get_block(cur, level, &bp); numrecs = xfs_btree_get_numrecs(block); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto error0; #endif /* Fail if we're off the end of the block. */ if (ptr > numrecs) { *stat = 0; return 0; } XFS_BTREE_STATS_INC(cur, delrec); XFS_BTREE_STATS_ADD(cur, moves, numrecs - ptr); /* Excise the entries being deleted. */ if (level > 0) { /* It's a nonleaf. operate on keys and ptrs */ union xfs_btree_key *lkp; union xfs_btree_ptr *lpp; lkp = xfs_btree_key_addr(cur, ptr + 1, block); lpp = xfs_btree_ptr_addr(cur, ptr + 1, block); for (i = 0; i < numrecs - ptr; i++) { error = xfs_btree_debug_check_ptr(cur, lpp, i, level); if (error) goto error0; } if (ptr < numrecs) { xfs_btree_shift_keys(cur, lkp, -1, numrecs - ptr); xfs_btree_shift_ptrs(cur, lpp, -1, numrecs - ptr); xfs_btree_log_keys(cur, bp, ptr, numrecs - 1); xfs_btree_log_ptrs(cur, bp, ptr, numrecs - 1); } } else { /* It's a leaf. operate on records */ if (ptr < numrecs) { xfs_btree_shift_recs(cur, xfs_btree_rec_addr(cur, ptr + 1, block), -1, numrecs - ptr); xfs_btree_log_recs(cur, bp, ptr, numrecs - 1); } } /* * Decrement and log the number of entries in the block. */ xfs_btree_set_numrecs(block, --numrecs); xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* * We're at the root level. First, shrink the root block in-memory. * Try to get rid of the next level down. If we can't then there's * nothing left to do. numrecs was decremented above. */ if (xfs_btree_at_iroot(cur, level)) { cur->bc_ops->broot_realloc(cur, numrecs); error = xfs_btree_kill_iroot(cur); if (error) goto error0; error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; *stat = 1; return 0; } /* * If this is the root level, and there's only one entry left, and it's * NOT the leaf level, then we can get rid of this level. */ if (level == cur->bc_nlevels - 1) { if (numrecs == 1 && level > 0) { union xfs_btree_ptr *pp; /* * pp is still set to the first pointer in the block. * Make it the new root of the btree. */ pp = xfs_btree_ptr_addr(cur, 1, block); error = xfs_btree_kill_root(cur, bp, level, pp); if (error) goto error0; } else if (level > 0) { error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; } *stat = 1; return 0; } /* * If we deleted the leftmost entry in the block, update the * key values above us in the tree. */ if (xfs_btree_needs_key_update(cur, ptr)) { error = xfs_btree_update_keys(cur, level); if (error) goto error0; } /* * If the number of records remaining in the block is at least * the minimum, we're done. */ if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) { error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; return 0; } /* * Otherwise, we have to move some records around to keep the * tree balanced. Look at the left and right sibling blocks to * see if we can re-balance by moving only one record. */ xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB); xfs_btree_get_sibling(cur, block, &lptr, XFS_BB_LEFTSIB); if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) { /* * One child of root, need to get a chance to copy its contents * into the root and delete it. Can't go up to next level, * there's nothing to delete there. */ if (xfs_btree_ptr_is_null(cur, &rptr) && xfs_btree_ptr_is_null(cur, &lptr) && level == cur->bc_nlevels - 2) { error = xfs_btree_kill_iroot(cur); if (!error) error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; return 0; } } ASSERT(!xfs_btree_ptr_is_null(cur, &rptr) || !xfs_btree_ptr_is_null(cur, &lptr)); /* * Duplicate the cursor so our btree manipulations here won't * disrupt the next level up. */ error = xfs_btree_dup_cursor(cur, &tcur); if (error) goto error0; /* * If there's a right sibling, see if it's ok to shift an entry * out of it. */ if (!xfs_btree_ptr_is_null(cur, &rptr)) { /* * Move the temp cursor to the last entry in the next block. * Actually any entry but the first would suffice. */ i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_btree_increment(tcur, level, &i); if (error) goto error0; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } i = xfs_btree_lastrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } /* Grab a pointer to the block. */ right = xfs_btree_get_block(tcur, level, &rbp); #ifdef DEBUG error = xfs_btree_check_block(tcur, right, level, rbp); if (error) goto error0; #endif /* Grab the current block number, for future use. */ xfs_btree_get_sibling(tcur, right, &cptr, XFS_BB_LEFTSIB); /* * If right block is full enough so that removing one entry * won't make it too empty, and left-shifting an entry out * of right to us works, we're done. */ if (xfs_btree_get_numrecs(right) - 1 >= cur->bc_ops->get_minrecs(tcur, level)) { error = xfs_btree_lshift(tcur, level, &i); if (error) goto error0; if (i) { ASSERT(xfs_btree_get_numrecs(block) >= cur->bc_ops->get_minrecs(tcur, level)); xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); tcur = NULL; error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; return 0; } } /* * Otherwise, grab the number of records in right for * future reference, and fix up the temp cursor to point * to our block again (last record). */ rrecs = xfs_btree_get_numrecs(right); if (!xfs_btree_ptr_is_null(cur, &lptr)) { i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_btree_decrement(tcur, level, &i); if (error) goto error0; if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } } } /* * If there's a left sibling, see if it's ok to shift an entry * out of it. */ if (!xfs_btree_ptr_is_null(cur, &lptr)) { /* * Move the temp cursor to the first entry in the * previous block. */ i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } error = xfs_btree_decrement(tcur, level, &i); if (error) goto error0; i = xfs_btree_firstrec(tcur, level); if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) { xfs_btree_mark_sick(cur); error = -EFSCORRUPTED; goto error0; } /* Grab a pointer to the block. */ left = xfs_btree_get_block(tcur, level, &lbp); #ifdef DEBUG error = xfs_btree_check_block(cur, left, level, lbp); if (error) goto error0; #endif /* Grab the current block number, for future use. */ xfs_btree_get_sibling(tcur, left, &cptr, XFS_BB_RIGHTSIB); /* * If left block is full enough so that removing one entry * won't make it too empty, and right-shifting an entry out * of left to us works, we're done. */ if (xfs_btree_get_numrecs(left) - 1 >= cur->bc_ops->get_minrecs(tcur, level)) { error = xfs_btree_rshift(tcur, level, &i); if (error) goto error0; if (i) { ASSERT(xfs_btree_get_numrecs(block) >= cur->bc_ops->get_minrecs(tcur, level)); xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); tcur = NULL; if (level == 0) cur->bc_levels[0].ptr++; *stat = 1; return 0; } } /* * Otherwise, grab the number of records in right for * future reference. */ lrecs = xfs_btree_get_numrecs(left); } /* Delete the temp cursor, we're done with it. */ xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); tcur = NULL; /* If here, we need to do a join to keep the tree balanced. */ ASSERT(!xfs_btree_ptr_is_null(cur, &cptr)); if (!xfs_btree_ptr_is_null(cur, &lptr) && lrecs + xfs_btree_get_numrecs(block) <= cur->bc_ops->get_maxrecs(cur, level)) { /* * Set "right" to be the starting block, * "left" to be the left neighbor. */ rptr = cptr; right = block; rbp = bp; error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp); if (error) goto error0; /* * If that won't work, see if we can join with the right neighbor block. */ } else if (!xfs_btree_ptr_is_null(cur, &rptr) && rrecs + xfs_btree_get_numrecs(block) <= cur->bc_ops->get_maxrecs(cur, level)) { /* * Set "left" to be the starting block, * "right" to be the right neighbor. */ lptr = cptr; left = block; lbp = bp; error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp); if (error) goto error0; /* * Otherwise, we can't fix the imbalance. * Just return. This is probably a logic error, but it's not fatal. */ } else { error = xfs_btree_dec_cursor(cur, level, stat); if (error) goto error0; return 0; } rrecs = xfs_btree_get_numrecs(right); lrecs = xfs_btree_get_numrecs(left); /* * We're now going to join "left" and "right" by moving all the stuff * in "right" to "left" and deleting "right". */ XFS_BTREE_STATS_ADD(cur, moves, rrecs); if (level > 0) { /* It's a non-leaf. Move keys and pointers. */ union xfs_btree_key *lkp; /* left btree key */ union xfs_btree_ptr *lpp; /* left address pointer */ union xfs_btree_key *rkp; /* right btree key */ union xfs_btree_ptr *rpp; /* right address pointer */ lkp = xfs_btree_key_addr(cur, lrecs + 1, left); lpp = xfs_btree_ptr_addr(cur, lrecs + 1, left); rkp = xfs_btree_key_addr(cur, 1, right); rpp = xfs_btree_ptr_addr(cur, 1, right); for (i = 1; i < rrecs; i++) { error = xfs_btree_debug_check_ptr(cur, rpp, i, level); if (error) goto error0; } xfs_btree_copy_keys(cur, lkp, rkp, rrecs); xfs_btree_copy_ptrs(cur, lpp, rpp, rrecs); xfs_btree_log_keys(cur, lbp, lrecs + 1, lrecs + rrecs); xfs_btree_log_ptrs(cur, lbp, lrecs + 1, lrecs + rrecs); } else { /* It's a leaf. Move records. */ union xfs_btree_rec *lrp; /* left record pointer */ union xfs_btree_rec *rrp; /* right record pointer */ lrp = xfs_btree_rec_addr(cur, lrecs + 1, left); rrp = xfs_btree_rec_addr(cur, 1, right); xfs_btree_copy_recs(cur, lrp, rrp, rrecs); xfs_btree_log_recs(cur, lbp, lrecs + 1, lrecs + rrecs); } XFS_BTREE_STATS_INC(cur, join); /* * Fix up the number of records and right block pointer in the * surviving block, and log it. */ xfs_btree_set_numrecs(left, lrecs + rrecs); xfs_btree_get_sibling(cur, right, &cptr, XFS_BB_RIGHTSIB); xfs_btree_set_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB); xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB); /* If there is a right sibling, point it to the remaining block. */ xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB); if (!xfs_btree_ptr_is_null(cur, &cptr)) { error = xfs_btree_read_buf_block(cur, &cptr, 0, &rrblock, &rrbp); if (error) goto error0; xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB); xfs_btree_log_block(cur, rrbp, XFS_BB_LEFTSIB); } /* Free the deleted block. */ error = xfs_btree_free_block(cur, rbp); if (error) goto error0; /* * If we joined with the left neighbor, set the buffer in the * cursor to the left block, and fix up the index. */ if (bp != lbp) { cur->bc_levels[level].bp = lbp; cur->bc_levels[level].ptr += lrecs; cur->bc_levels[level].ra = 0; } /* * If we joined with the right neighbor and there's a level above * us, increment the cursor at that level. */ else if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE || level + 1 < cur->bc_nlevels) { error = xfs_btree_increment(cur, level + 1, &i); if (error) goto error0; } /* * Readjust the ptr at this level if it's not a leaf, since it's * still pointing at the deletion point, which makes the cursor * inconsistent. If this makes the ptr 0, the caller fixes it up. * We can't use decrement because it would change the next level up. */ if (level > 0) cur->bc_levels[level].ptr--; /* * We combined blocks, so we have to update the parent keys if the * btree supports overlapped intervals. However, * bc_levels[level + 1].ptr points to the old block so that the caller * knows which record to delete. Therefore, the caller must be savvy * enough to call updkeys for us if we return stat == 2. The other * exit points from this function don't require deletions further up * the tree, so they can call updkeys directly. */ /* Return value means the next level up has something to do. */ *stat = 2; return 0; error0: if (tcur) xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR); return error; } /* * Delete the record pointed to by cur. * The cursor refers to the place where the record was (could be inserted) * when the operation returns. */ int /* error */ xfs_btree_delete( struct xfs_btree_cur *cur, int *stat) /* success/failure */ { int error; /* error return value */ int level; int i; bool joined = false; /* * Go up the tree, starting at leaf level. * * If 2 is returned then a join was done; go to the next level. * Otherwise we are done. */ for (level = 0, i = 2; i == 2; level++) { error = xfs_btree_delrec(cur, level, &i); if (error) goto error0; if (i == 2) joined = true; } /* * If we combined blocks as part of deleting the record, delrec won't * have updated the parent high keys so we have to do that here. */ if (joined && (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) { error = xfs_btree_updkeys_force(cur, 0); if (error) goto error0; } if (i == 0) { for (level = 1; level < cur->bc_nlevels; level++) { if (cur->bc_levels[level].ptr == 0) { error = xfs_btree_decrement(cur, level, &i); if (error) goto error0; break; } } } *stat = i; return 0; error0: return error; } /* * Get the data from the pointed-to record. */ int /* error */ xfs_btree_get_rec( struct xfs_btree_cur *cur, /* btree cursor */ union xfs_btree_rec **recp, /* output: btree record */ int *stat) /* output: success/failure */ { struct xfs_btree_block *block; /* btree block */ struct xfs_buf *bp; /* buffer pointer */ int ptr; /* record number */ #ifdef DEBUG int error; /* error return value */ #endif ptr = cur->bc_levels[0].ptr; block = xfs_btree_get_block(cur, 0, &bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, 0, bp); if (error) return error; #endif /* * Off the right end or left end, return failure. */ if (ptr > xfs_btree_get_numrecs(block) || ptr <= 0) { *stat = 0; return 0; } /* * Point to the record and extract its data. */ *recp = xfs_btree_rec_addr(cur, ptr, block); *stat = 1; return 0; } /* Visit a block in a btree. */ STATIC int xfs_btree_visit_block( struct xfs_btree_cur *cur, int level, xfs_btree_visit_blocks_fn fn, void *data) { struct xfs_btree_block *block; struct xfs_buf *bp; union xfs_btree_ptr rptr, bufptr; int error; /* do right sibling readahead */ xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA); block = xfs_btree_get_block(cur, level, &bp); /* process the block */ error = fn(cur, level, data); if (error) return error; /* now read rh sibling block for next iteration */ xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB); if (xfs_btree_ptr_is_null(cur, &rptr)) return -ENOENT; /* * We only visit blocks once in this walk, so we have to avoid the * internal xfs_btree_lookup_get_block() optimisation where it will * return the same block without checking if the right sibling points * back to us and creates a cyclic reference in the btree. */ xfs_btree_buf_to_ptr(cur, bp, &bufptr); if (xfs_btree_ptrs_equal(cur, &rptr, &bufptr)) { xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return xfs_btree_lookup_get_block(cur, level, &rptr, &block); } /* Visit every block in a btree. */ int xfs_btree_visit_blocks( struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data) { union xfs_btree_ptr lptr; int level; struct xfs_btree_block *block = NULL; int error = 0; xfs_btree_init_ptr_from_cur(cur, &lptr); /* for each level */ for (level = cur->bc_nlevels - 1; level >= 0; level--) { /* grab the left hand block */ error = xfs_btree_lookup_get_block(cur, level, &lptr, &block); if (error) return error; /* readahead the left most block for the next level down */ if (level > 0) { union xfs_btree_ptr *ptr; ptr = xfs_btree_ptr_addr(cur, 1, block); xfs_btree_readahead_ptr(cur, ptr, 1); /* save for the next iteration of the loop */ xfs_btree_copy_ptrs(cur, &lptr, ptr, 1); if (!(flags & XFS_BTREE_VISIT_LEAVES)) continue; } else if (!(flags & XFS_BTREE_VISIT_RECORDS)) { continue; } /* for each buffer in the level */ do { error = xfs_btree_visit_block(cur, level, fn, data); } while (!error); if (error != -ENOENT) return error; } return 0; } /* * Change the owner of a btree. * * The mechanism we use here is ordered buffer logging. Because we don't know * how many buffers were are going to need to modify, we don't really want to * have to make transaction reservations for the worst case of every buffer in a * full size btree as that may be more space that we can fit in the log.... * * We do the btree walk in the most optimal manner possible - we have sibling * pointers so we can just walk all the blocks on each level from left to right * in a single pass, and then move to the next level and do the same. We can * also do readahead on the sibling pointers to get IO moving more quickly, * though for slow disks this is unlikely to make much difference to performance * as the amount of CPU work we have to do before moving to the next block is * relatively small. * * For each btree block that we load, modify the owner appropriately, set the * buffer as an ordered buffer and log it appropriately. We need to ensure that * we mark the region we change dirty so that if the buffer is relogged in * a subsequent transaction the changes we make here as an ordered buffer are * correctly relogged in that transaction. If we are in recovery context, then * just queue the modified buffer as delayed write buffer so the transaction * recovery completion writes the changes to disk. */ struct xfs_btree_block_change_owner_info { uint64_t new_owner; struct list_head *buffer_list; }; static int xfs_btree_block_change_owner( struct xfs_btree_cur *cur, int level, void *data) { struct xfs_btree_block_change_owner_info *bbcoi = data; struct xfs_btree_block *block; struct xfs_buf *bp; /* modify the owner */ block = xfs_btree_get_block(cur, level, &bp); if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner)) return 0; block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner); } else { if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner)) return 0; block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner); } /* * If the block is a root block hosted in an inode, we might not have a * buffer pointer here and we shouldn't attempt to log the change as the * information is already held in the inode and discarded when the root * block is formatted into the on-disk inode fork. We still change it, * though, so everything is consistent in memory. */ if (!bp) { ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE); ASSERT(level == cur->bc_nlevels - 1); return 0; } if (cur->bc_tp) { if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) { xfs_btree_log_block(cur, bp, XFS_BB_OWNER); return -EAGAIN; } } else { xfs_buf_delwri_queue(bp, bbcoi->buffer_list); } return 0; } int xfs_btree_change_owner( struct xfs_btree_cur *cur, uint64_t new_owner, struct list_head *buffer_list) { struct xfs_btree_block_change_owner_info bbcoi; bbcoi.new_owner = new_owner; bbcoi.buffer_list = buffer_list; return xfs_btree_visit_blocks(cur, xfs_btree_block_change_owner, XFS_BTREE_VISIT_ALL, &bbcoi); } /* Verify the v5 fields of a long-format btree block. */ xfs_failaddr_t xfs_btree_fsblock_v5hdr_verify( struct xfs_buf *bp, uint64_t owner) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); if (!xfs_has_crc(mp)) return __this_address; if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (block->bb_u.l.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp))) return __this_address; if (owner != XFS_RMAP_OWN_UNKNOWN && be64_to_cpu(block->bb_u.l.bb_owner) != owner) return __this_address; return NULL; } /* Verify a long-format btree block. */ xfs_failaddr_t xfs_btree_fsblock_verify( struct xfs_buf *bp, unsigned int max_recs) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_fsblock_t fsb; xfs_failaddr_t fa; ASSERT(!xfs_buftarg_is_mem(bp->b_target)); /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; /* sibling pointer verification */ fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_leftsib); if (!fa) fa = xfs_btree_check_fsblock_siblings(mp, fsb, block->bb_u.l.bb_rightsib); return fa; } /* Verify an in-memory btree block. */ xfs_failaddr_t xfs_btree_memblock_verify( struct xfs_buf *bp, unsigned int max_recs) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_buftarg *btp = bp->b_target; xfs_failaddr_t fa; xfbno_t bno; ASSERT(xfs_buftarg_is_mem(bp->b_target)); /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; /* sibling pointer verification */ bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp)); fa = xfs_btree_check_memblock_siblings(btp, bno, block->bb_u.l.bb_leftsib); if (fa) return fa; fa = xfs_btree_check_memblock_siblings(btp, bno, block->bb_u.l.bb_rightsib); if (fa) return fa; return NULL; } /** * xfs_btree_agblock_v5hdr_verify() -- verify the v5 fields of a short-format * btree block * * @bp: buffer containing the btree block */ xfs_failaddr_t xfs_btree_agblock_v5hdr_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; if (!xfs_has_crc(mp)) return __this_address; if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) return __this_address; if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp))) return __this_address; if (pag && be32_to_cpu(block->bb_u.s.bb_owner) != pag_agno(pag)) return __this_address; return NULL; } /** * xfs_btree_agblock_verify() -- verify a short-format btree block * * @bp: buffer containing the btree block * @max_recs: maximum records allowed in this btree node */ xfs_failaddr_t xfs_btree_agblock_verify( struct xfs_buf *bp, unsigned int max_recs) { struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_agblock_t agbno; xfs_failaddr_t fa; ASSERT(!xfs_buftarg_is_mem(bp->b_target)); /* numrecs verification */ if (be16_to_cpu(block->bb_numrecs) > max_recs) return __this_address; /* sibling pointer verification */ agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp)); fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno, block->bb_u.s.bb_leftsib); if (!fa) fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno, block->bb_u.s.bb_rightsib); return fa; } /* * For the given limits on leaf and keyptr records per block, calculate the * height of the tree needed to index the number of leaf records. */ unsigned int xfs_btree_compute_maxlevels( const unsigned int *limits, unsigned long long records) { unsigned long long level_blocks = howmany_64(records, limits[0]); unsigned int height = 1; while (level_blocks > 1) { level_blocks = howmany_64(level_blocks, limits[1]); height++; } return height; } /* * For the given limits on leaf and keyptr records per block, calculate the * number of blocks needed to index the given number of leaf records. */ unsigned long long xfs_btree_calc_size( const unsigned int *limits, unsigned long long records) { unsigned long long level_blocks = howmany_64(records, limits[0]); unsigned long long blocks = level_blocks; while (level_blocks > 1) { level_blocks = howmany_64(level_blocks, limits[1]); blocks += level_blocks; } return blocks; } /* * Given a number of available blocks for the btree to consume with records and * pointers, calculate the height of the tree needed to index all the records * that space can hold based on the number of pointers each interior node * holds. * * We start by assuming a single level tree consumes a single block, then track * the number of blocks each node level consumes until we no longer have space * to store the next node level. At this point, we are indexing all the leaf * blocks in the space, and there's no more free space to split the tree any * further. That's our maximum btree height. */ unsigned int xfs_btree_space_to_height( const unsigned int *limits, unsigned long long leaf_blocks) { /* * The root btree block can have fewer than minrecs pointers in it * because the tree might not be big enough to require that amount of * fanout. Hence it has a minimum size of 2 pointers, not limits[1]. */ unsigned long long node_blocks = 2; unsigned long long blocks_left = leaf_blocks - 1; unsigned int height = 1; if (leaf_blocks < 1) return 0; while (node_blocks < blocks_left) { blocks_left -= node_blocks; node_blocks *= limits[1]; height++; } return height; } /* * Query a regular btree for all records overlapping a given interval. * Start with a LE lookup of the key of low_rec and return all records * until we find a record with a key greater than the key of high_rec. */ STATIC int xfs_btree_simple_query_range( struct xfs_btree_cur *cur, const union xfs_btree_key *low_key, const union xfs_btree_key *high_key, xfs_btree_query_range_fn fn, void *priv) { union xfs_btree_rec *recp; union xfs_btree_key rec_key; int stat; bool firstrec = true; int error; ASSERT(cur->bc_ops->init_high_key_from_rec); ASSERT(cur->bc_ops->cmp_two_keys); /* * Find the leftmost record. The btree cursor must be set * to the low record used to generate low_key. */ stat = 0; error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat); if (error) goto out; /* Nothing? See if there's anything to the right. */ if (!stat) { error = xfs_btree_increment(cur, 0, &stat); if (error) goto out; } while (stat) { /* Find the record. */ error = xfs_btree_get_rec(cur, &recp, &stat); if (error || !stat) break; /* Skip if low_key > high_key(rec). */ if (firstrec) { cur->bc_ops->init_high_key_from_rec(&rec_key, recp); firstrec = false; if (xfs_btree_keycmp_gt(cur, low_key, &rec_key)) goto advloop; } /* Stop if low_key(rec) > high_key. */ cur->bc_ops->init_key_from_rec(&rec_key, recp); if (xfs_btree_keycmp_gt(cur, &rec_key, high_key)) break; /* Callback */ error = fn(cur, recp, priv); if (error) break; advloop: /* Move on to the next record. */ error = xfs_btree_increment(cur, 0, &stat); if (error) break; } out: return error; } /* * Query an overlapped interval btree for all records overlapping a given * interval. This function roughly follows the algorithm given in * "Interval Trees" of _Introduction to Algorithms_, which is section * 14.3 in the 2nd and 3rd editions. * * First, generate keys for the low and high records passed in. * * For any leaf node, generate the high and low keys for the record. * If the record keys overlap with the query low/high keys, pass the * record to the function iterator. * * For any internal node, compare the low and high keys of each * pointer against the query low/high keys. If there's an overlap, * follow the pointer. * * As an optimization, we stop scanning a block when we find a low key * that is greater than the query's high key. */ STATIC int xfs_btree_overlapped_query_range( struct xfs_btree_cur *cur, const union xfs_btree_key *low_key, const union xfs_btree_key *high_key, xfs_btree_query_range_fn fn, void *priv) { union xfs_btree_ptr ptr; union xfs_btree_ptr *pp; union xfs_btree_key rec_key; union xfs_btree_key rec_hkey; union xfs_btree_key *lkp; union xfs_btree_key *hkp; union xfs_btree_rec *recp; struct xfs_btree_block *block; int level; struct xfs_buf *bp; int i; int error; /* Load the root of the btree. */ level = cur->bc_nlevels - 1; xfs_btree_init_ptr_from_cur(cur, &ptr); error = xfs_btree_lookup_get_block(cur, level, &ptr, &block); if (error) return error; xfs_btree_get_block(cur, level, &bp); trace_xfs_btree_overlapped_query_range(cur, level, bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto out; #endif cur->bc_levels[level].ptr = 1; while (level < cur->bc_nlevels) { block = xfs_btree_get_block(cur, level, &bp); /* End of node, pop back towards the root. */ if (cur->bc_levels[level].ptr > be16_to_cpu(block->bb_numrecs)) { pop_up: if (level < cur->bc_nlevels - 1) cur->bc_levels[level + 1].ptr++; level++; continue; } if (level == 0) { /* Handle a leaf node. */ recp = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr, block); cur->bc_ops->init_high_key_from_rec(&rec_hkey, recp); cur->bc_ops->init_key_from_rec(&rec_key, recp); /* * If (query's high key < record's low key), then there * are no more interesting records in this block. Pop * up to the leaf level to find more record blocks. * * If (record's high key >= query's low key) and * (query's high key >= record's low key), then * this record overlaps the query range; callback. */ if (xfs_btree_keycmp_lt(cur, high_key, &rec_key)) goto pop_up; if (xfs_btree_keycmp_ge(cur, &rec_hkey, low_key)) { error = fn(cur, recp, priv); if (error) break; } cur->bc_levels[level].ptr++; continue; } /* Handle an internal node. */ lkp = xfs_btree_key_addr(cur, cur->bc_levels[level].ptr, block); hkp = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr, block); pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block); /* * If (query's high key < pointer's low key), then there are no * more interesting keys in this block. Pop up one leaf level * to continue looking for records. * * If (pointer's high key >= query's low key) and * (query's high key >= pointer's low key), then * this record overlaps the query range; follow pointer. */ if (xfs_btree_keycmp_lt(cur, high_key, lkp)) goto pop_up; if (xfs_btree_keycmp_ge(cur, hkp, low_key)) { level--; error = xfs_btree_lookup_get_block(cur, level, pp, &block); if (error) goto out; xfs_btree_get_block(cur, level, &bp); trace_xfs_btree_overlapped_query_range(cur, level, bp); #ifdef DEBUG error = xfs_btree_check_block(cur, block, level, bp); if (error) goto out; #endif cur->bc_levels[level].ptr = 1; continue; } cur->bc_levels[level].ptr++; } out: /* * If we don't end this function with the cursor pointing at a record * block, a subsequent non-error cursor deletion will not release * node-level buffers, causing a buffer leak. This is quite possible * with a zero-results range query, so release the buffers if we * failed to return any results. */ if (cur->bc_levels[0].bp == NULL) { for (i = 0; i < cur->bc_nlevels; i++) { if (cur->bc_levels[i].bp) { xfs_trans_brelse(cur->bc_tp, cur->bc_levels[i].bp); cur->bc_levels[i].bp = NULL; cur->bc_levels[i].ptr = 0; cur->bc_levels[i].ra = 0; } } } return error; } static inline void xfs_btree_key_from_irec( struct xfs_btree_cur *cur, union xfs_btree_key *key, const union xfs_btree_irec *irec) { union xfs_btree_rec rec; cur->bc_rec = *irec; cur->bc_ops->init_rec_from_cur(cur, &rec); cur->bc_ops->init_key_from_rec(key, &rec); } /* * Query a btree for all records overlapping a given interval of keys. The * supplied function will be called with each record found; return one of the * XFS_BTREE_QUERY_RANGE_{CONTINUE,ABORT} values or the usual negative error * code. This function returns -ECANCELED, zero, or a negative error code. */ int xfs_btree_query_range( struct xfs_btree_cur *cur, const union xfs_btree_irec *low_rec, const union xfs_btree_irec *high_rec, xfs_btree_query_range_fn fn, void *priv) { union xfs_btree_key low_key; union xfs_btree_key high_key; /* Find the keys of both ends of the interval. */ xfs_btree_key_from_irec(cur, &high_key, high_rec); xfs_btree_key_from_irec(cur, &low_key, low_rec); /* Enforce low key <= high key. */ if (!xfs_btree_keycmp_le(cur, &low_key, &high_key)) return -EINVAL; if (!(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv); return xfs_btree_overlapped_query_range(cur, &low_key, &high_key, fn, priv); } /* Query a btree for all records. */ int xfs_btree_query_all( struct xfs_btree_cur *cur, xfs_btree_query_range_fn fn, void *priv) { union xfs_btree_key low_key; union xfs_btree_key high_key; memset(&cur->bc_rec, 0, sizeof(cur->bc_rec)); memset(&low_key, 0, sizeof(low_key)); memset(&high_key, 0xFF, sizeof(high_key)); return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv); } static int xfs_btree_count_blocks_helper( struct xfs_btree_cur *cur, int level, void *data) { xfs_filblks_t *blocks = data; (*blocks)++; return 0; } /* Count the blocks in a btree and return the result in *blocks. */ int xfs_btree_count_blocks( struct xfs_btree_cur *cur, xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, XFS_BTREE_VISIT_ALL, blocks); } /* Compare two btree pointers. */ int xfs_btree_cmp_two_ptrs( struct xfs_btree_cur *cur, const union xfs_btree_ptr *a, const union xfs_btree_ptr *b) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return cmp_int(be64_to_cpu(a->l), be64_to_cpu(b->l)); return cmp_int(be32_to_cpu(a->s), be32_to_cpu(b->s)); } struct xfs_btree_has_records { /* Keys for the start and end of the range we want to know about. */ union xfs_btree_key start_key; union xfs_btree_key end_key; /* Mask for key comparisons, if desired. */ const union xfs_btree_key *key_mask; /* Highest record key we've seen so far. */ union xfs_btree_key high_key; enum xbtree_recpacking outcome; }; STATIC int xfs_btree_has_records_helper( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { union xfs_btree_key rec_key; union xfs_btree_key rec_high_key; struct xfs_btree_has_records *info = priv; enum xbtree_key_contig key_contig; cur->bc_ops->init_key_from_rec(&rec_key, rec); if (info->outcome == XBTREE_RECPACKING_EMPTY) { info->outcome = XBTREE_RECPACKING_SPARSE; /* * If the first record we find does not overlap the start key, * then there is a hole at the start of the search range. * Classify this as sparse and stop immediately. */ if (xfs_btree_masked_keycmp_lt(cur, &info->start_key, &rec_key, info->key_mask)) return -ECANCELED; } else { /* * If a subsequent record does not overlap with the any record * we've seen so far, there is a hole in the middle of the * search range. Classify this as sparse and stop. * If the keys overlap and this btree does not allow overlap, * signal corruption. */ key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key, &rec_key, info->key_mask); if (key_contig == XBTREE_KEY_OVERLAP && !(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) return -EFSCORRUPTED; if (key_contig == XBTREE_KEY_GAP) return -ECANCELED; } /* * If high_key(rec) is larger than any other high key we've seen, * remember it for later. */ cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec); if (xfs_btree_masked_keycmp_gt(cur, &rec_high_key, &info->high_key, info->key_mask)) info->high_key = rec_high_key; /* struct copy */ return 0; } /* * Scan part of the keyspace of a btree and tell us if that keyspace does not * map to any records; is fully mapped to records; or is partially mapped to * records. This is the btree record equivalent to determining if a file is * sparse. * * For most btree types, the record scan should use all available btree key * fields to compare the keys encountered. These callers should pass NULL for * @mask. However, some callers (e.g. scanning physical space in the rmapbt) * want to ignore some part of the btree record keyspace when performing the * comparison. These callers should pass in a union xfs_btree_key object with * the fields that *should* be a part of the comparison set to any nonzero * value, and the rest zeroed. */ int xfs_btree_has_records( struct xfs_btree_cur *cur, const union xfs_btree_irec *low, const union xfs_btree_irec *high, const union xfs_btree_key *mask, enum xbtree_recpacking *outcome) { struct xfs_btree_has_records info = { .outcome = XBTREE_RECPACKING_EMPTY, .key_mask = mask, }; int error; /* Not all btrees support this operation. */ if (!cur->bc_ops->keys_contiguous) { ASSERT(0); return -EOPNOTSUPP; } xfs_btree_key_from_irec(cur, &info.start_key, low); xfs_btree_key_from_irec(cur, &info.end_key, high); error = xfs_btree_query_range(cur, low, high, xfs_btree_has_records_helper, &info); if (error == -ECANCELED) goto out; if (error) return error; if (info.outcome == XBTREE_RECPACKING_EMPTY) goto out; /* * If the largest high_key(rec) we saw during the walk is greater than * the end of the search range, classify this as full. Otherwise, * there is a hole at the end of the search range. */ if (xfs_btree_masked_keycmp_ge(cur, &info.high_key, &info.end_key, mask)) info.outcome = XBTREE_RECPACKING_FULL; out: *outcome = info.outcome; return 0; } /* Are there more records in this btree? */ bool xfs_btree_has_more_records( struct xfs_btree_cur *cur) { struct xfs_btree_block *block; struct xfs_buf *bp; block = xfs_btree_get_block(cur, 0, &bp); /* There are still records in this block. */ if (cur->bc_levels[0].ptr < xfs_btree_get_numrecs(block)) return true; /* There are more record blocks. */ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) return block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK); else return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK); } /* Set up all the btree cursor caches. */ int __init xfs_btree_init_cur_caches(void) { int error; error = xfs_allocbt_init_cur_cache(); if (error) return error; error = xfs_inobt_init_cur_cache(); if (error) goto err; error = xfs_bmbt_init_cur_cache(); if (error) goto err; error = xfs_rmapbt_init_cur_cache(); if (error) goto err; error = xfs_refcountbt_init_cur_cache(); if (error) goto err; error = xfs_rtrmapbt_init_cur_cache(); if (error) goto err; error = xfs_rtrefcountbt_init_cur_cache(); if (error) goto err; return 0; err: xfs_btree_destroy_cur_caches(); return error; } /* Destroy all the btree cursor caches, if they've been allocated. */ void xfs_btree_destroy_cur_caches(void) { xfs_allocbt_destroy_cur_cache(); xfs_inobt_destroy_cur_cache(); xfs_bmbt_destroy_cur_cache(); xfs_rmapbt_destroy_cur_cache(); xfs_refcountbt_destroy_cur_cache(); xfs_rtrmapbt_destroy_cur_cache(); xfs_rtrefcountbt_destroy_cur_cache(); } /* Move the btree cursor before the first record. */ int xfs_btree_goto_left_edge( struct xfs_btree_cur *cur) { int stat = 0; int error; memset(&cur->bc_rec, 0, sizeof(cur->bc_rec)); error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat); if (error) return error; if (!stat) return 0; error = xfs_btree_decrement(cur, 0, &stat); if (error) return error; if (stat != 0) { ASSERT(0); xfs_btree_mark_sick(cur); return -EFSCORRUPTED; } return 0; } /* Allocate a block for an inode-rooted metadata btree. */ int xfs_btree_alloc_metafile_block( struct xfs_btree_cur *cur, const union xfs_btree_ptr *start, union xfs_btree_ptr *new, int *stat) { struct xfs_alloc_arg args = { .mp = cur->bc_mp, .tp = cur->bc_tp, .resv = XFS_AG_RESV_METAFILE, .minlen = 1, .maxlen = 1, .prod = 1, }; struct xfs_inode *ip = cur->bc_ino.ip; int error; ASSERT(xfs_is_metadir_inode(ip)); xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, cur->bc_ino.whichfork); error = xfs_alloc_vextent_start_ag(&args, XFS_INO_TO_FSB(cur->bc_mp, ip->i_ino)); if (error) return error; if (args.fsbno == NULLFSBLOCK) { *stat = 0; return 0; } ASSERT(args.len == 1); xfs_metafile_resv_alloc_space(ip, &args); new->l = cpu_to_be64(args.fsbno); *stat = 1; return 0; } /* Free a block from an inode-rooted metadata btree. */ int xfs_btree_free_metafile_block( struct xfs_btree_cur *cur, struct xfs_buf *bp) { struct xfs_owner_info oinfo; struct xfs_mount *mp = cur->bc_mp; struct xfs_inode *ip = cur->bc_ino.ip; struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); int error; ASSERT(xfs_is_metadir_inode(ip)); xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); error = xfs_free_extent_later(tp, fsbno, 1, &oinfo, XFS_AG_RESV_METAFILE, 0); if (error) return error; xfs_metafile_resv_free_space(ip, tp, 1); return 0; } |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018, 2021-2025 Intel Corporation */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS #include <linux/rtnetlink.h> #include <net/cfg80211.h> #include "core.h" #include "trace.h" static inline int rdev_suspend(struct cfg80211_registered_device *rdev, struct cfg80211_wowlan *wowlan) { int ret; trace_rdev_suspend(&rdev->wiphy, wowlan); ret = rdev->ops->suspend(&rdev->wiphy, wowlan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_resume(struct cfg80211_registered_device *rdev) { int ret; trace_rdev_resume(&rdev->wiphy); ret = rdev->ops->resume(&rdev->wiphy); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev, bool enabled) { trace_rdev_set_wakeup(&rdev->wiphy, enabled); rdev->ops->set_wakeup(&rdev->wiphy, enabled); trace_rdev_return_void(&rdev->wiphy); } static inline struct wireless_dev *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct wireless_dev *ret; trace_rdev_add_virtual_intf(&rdev->wiphy, name, type); ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type, type, params); trace_rdev_return_wdev(&rdev->wiphy, ret); return ret; } static inline int rdev_del_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_del_virtual_intf(&rdev->wiphy, wdev); ret = rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_virtual_intf(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { int ret; trace_rdev_change_virtual_intf(&rdev->wiphy, dev, type); ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params) { int ret; trace_rdev_add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params->mode); ret = rdev->ops->add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params*)) { int ret; trace_rdev_get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, cookie, callback); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr) { int ret; trace_rdev_del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool unicast, bool multicast) { int ret; trace_rdev_set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); ret = rdev->ops->set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) { int ret; trace_rdev_start_ap(&rdev->wiphy, dev, settings); ret = rdev->ops->start_ap(&rdev->wiphy, dev, settings); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_beacon(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_update *info) { int ret; trace_rdev_change_beacon(&rdev->wiphy, dev, info); ret = rdev->ops->change_beacon(&rdev->wiphy, dev, info); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id) { int ret; trace_rdev_stop_ap(&rdev->wiphy, dev, link_id); ret = rdev->ops->stop_ap(&rdev->wiphy, dev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_add_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->add_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct station_del_parameters *params) { int ret; trace_rdev_del_station(&rdev->wiphy, dev, params); ret = rdev->ops->del_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_change_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->change_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_station(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_get_station(&rdev->wiphy, dev, mac); ret = rdev->ops->get_station(&rdev->wiphy, dev, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_dump_station(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_dump_station(&rdev->wiphy, dev, idx, mac); ret = rdev->ops->dump_station(&rdev->wiphy, dev, idx, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_add_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_add_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst) { int ret; trace_rdev_del_mpath(&rdev->wiphy, dev, dst); ret = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_change_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpp(&rdev->wiphy, dev, dst, mpp); ret = rdev->ops->get_mpp(&rdev->wiphy, dev, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop); ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpp(&rdev->wiphy, dev, idx, dst, mpp); ret = rdev->ops->dump_mpp(&rdev->wiphy, dev, idx, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct mesh_config *conf) { int ret; trace_rdev_get_mesh_config(&rdev->wiphy, dev); ret = rdev->ops->get_mesh_config(&rdev->wiphy, dev, conf); trace_rdev_return_int_mesh_config(&rdev->wiphy, ret, conf); return ret; } static inline int rdev_update_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { int ret; trace_rdev_update_mesh_config(&rdev->wiphy, dev, mask, nconf); ret = rdev->ops->update_mesh_config(&rdev->wiphy, dev, mask, nconf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { int ret; trace_rdev_join_mesh(&rdev->wiphy, dev, conf, setup); ret = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_mesh(&rdev->wiphy, dev); ret = rdev->ops->leave_mesh(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ocb_setup *setup) { int ret; trace_rdev_join_ocb(&rdev->wiphy, dev, setup); ret = rdev->ops->join_ocb(&rdev->wiphy, dev, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ocb(&rdev->wiphy, dev); ret = rdev->ops->leave_ocb(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_bss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct bss_parameters *params) { int ret; trace_rdev_change_bss(&rdev->wiphy, dev, params); ret = rdev->ops->change_bss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_inform_bss(struct cfg80211_registered_device *rdev, struct cfg80211_bss *bss, const struct cfg80211_bss_ies *ies, void *drv_data) { trace_rdev_inform_bss(&rdev->wiphy, bss); if (rdev->ops->inform_bss) rdev->ops->inform_bss(&rdev->wiphy, bss, ies, drv_data); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_txq_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_txq_params *params) { int ret; trace_rdev_set_txq_params(&rdev->wiphy, dev, params); ret = rdev->ops->set_txq_params(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_libertas_set_mesh_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan) { int ret; trace_rdev_libertas_set_mesh_channel(&rdev->wiphy, dev, chan); ret = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, dev, chan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_monitor_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_monitor_channel(&rdev->wiphy, dev, chandef); ret = rdev->ops->set_monitor_channel(&rdev->wiphy, dev, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_scan(struct cfg80211_registered_device *rdev, struct cfg80211_scan_request_int *request) { int ret; if (WARN_ON_ONCE(!request->req.n_ssids && request->req.ssids)) return -EINVAL; trace_rdev_scan(&rdev->wiphy, request); ret = rdev->ops->scan(&rdev->wiphy, &request->req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_scan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_abort_scan(&rdev->wiphy, wdev); rdev->ops->abort_scan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_auth_request *req) { int ret; trace_rdev_auth(&rdev->wiphy, dev, req); ret = rdev->ops->auth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_assoc_request *req) { int ret; trace_rdev_assoc(&rdev->wiphy, dev, req); ret = rdev->ops->assoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_deauth_request *req) { int ret; trace_rdev_deauth(&rdev->wiphy, dev, req); ret = rdev->ops->deauth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_disassoc_request *req) { int ret; trace_rdev_disassoc(&rdev->wiphy, dev, req); ret = rdev->ops->disassoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme) { int ret; trace_rdev_connect(&rdev->wiphy, dev, sme); ret = rdev->ops->connect(&rdev->wiphy, dev, sme); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_connect_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme, u32 changed) { int ret; trace_rdev_update_connect_params(&rdev->wiphy, dev, sme, changed); ret = rdev->ops->update_connect_params(&rdev->wiphy, dev, sme, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason_code) { int ret; trace_rdev_disconnect(&rdev->wiphy, dev, reason_code); ret = rdev->ops->disconnect(&rdev->wiphy, dev, reason_code); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ibss_params *params) { int ret; trace_rdev_join_ibss(&rdev->wiphy, dev, params); ret = rdev->ops->join_ibss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ibss(&rdev->wiphy, dev); ret = rdev->ops->leave_ibss(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, int radio_idx, u32 changed) { int ret = -EOPNOTSUPP; trace_rdev_set_wiphy_params(&rdev->wiphy, radio_idx, changed); if (rdev->ops->set_wiphy_params) ret = rdev->ops->set_wiphy_params(&rdev->wiphy, radio_idx, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, int radio_idx, enum nl80211_tx_power_setting type, int mbm) { int ret; trace_rdev_set_tx_power(&rdev->wiphy, wdev, radio_idx, type, mbm); ret = rdev->ops->set_tx_power(&rdev->wiphy, wdev, radio_idx, type, mbm); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, int radio_idx, unsigned int link_id, int *dbm) { int ret; trace_rdev_get_tx_power(&rdev->wiphy, wdev, radio_idx, link_id); ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, radio_idx, link_id, dbm); trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm); return ret; } static inline int rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, struct net_device *dev, const bool enabled) { int ret; trace_rdev_set_multicast_to_unicast(&rdev->wiphy, dev, enabled); ret = rdev->ops->set_multicast_to_unicast(&rdev->wiphy, dev, enabled); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_txq_stats(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats) { int ret; trace_rdev_get_txq_stats(&rdev->wiphy, wdev); ret = rdev->ops->get_txq_stats(&rdev->wiphy, wdev, txqstats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) { trace_rdev_rfkill_poll(&rdev->wiphy); rdev->ops->rfkill_poll(&rdev->wiphy); trace_rdev_return_void(&rdev->wiphy); } #ifdef CONFIG_NL80211_TESTMODE static inline int rdev_testmode_cmd(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, void *data, int len) { int ret; trace_rdev_testmode_cmd(&rdev->wiphy, wdev); ret = rdev->ops->testmode_cmd(&rdev->wiphy, wdev, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_testmode_dump(struct cfg80211_registered_device *rdev, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { int ret; trace_rdev_testmode_dump(&rdev->wiphy); ret = rdev->ops->testmode_dump(&rdev->wiphy, skb, cb, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } #endif static inline int rdev_set_bitrate_mask(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask) { int ret; trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_dump_survey(struct cfg80211_registered_device *rdev, struct net_device *netdev, int idx, struct survey_info *info) { int ret; trace_rdev_dump_survey(&rdev->wiphy, netdev, idx); ret = rdev->ops->dump_survey(&rdev->wiphy, netdev, idx, info); if (ret < 0) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_survey_info(&rdev->wiphy, ret, info); return ret; } static inline int rdev_set_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_set_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->set_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_del_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->del_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_flush_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev) { int ret; trace_rdev_flush_pmksa(&rdev->wiphy, netdev); ret = rdev->ops->flush_pmksa(&rdev->wiphy, netdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, u64 *cookie) { int ret; trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration); ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, duration, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); ret = rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_mgmt_tx_params *params, u64 *cookie) { int ret; trace_rdev_mgmt_tx(&rdev->wiphy, wdev, params); ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, params, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev, struct net_device *dev, const void *buf, size_t len, const u8 *dest, __be16 proto, const bool noencrypt, int link, u64 *cookie) { int ret; trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link); ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link, cookie); if (cookie) trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); else trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx_cancel_wait(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); ret = rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_power_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, bool enabled, int timeout) { int ret; trace_rdev_set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); ret = rdev->ops->set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { int ret; trace_rdev_set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); ret = rdev->ops->set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_range_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 low, s32 high) { int ret; trace_rdev_set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); ret = rdev->ops->set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_txe_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 rate, u32 pkts, u32 intvl) { int ret; trace_rdev_set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); ret = rdev->ops->set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_update_mgmt_frame_registrations(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct mgmt_frame_regs *upd) { might_sleep(); trace_rdev_update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); if (rdev->ops->update_mgmt_frame_registrations) rdev->ops->update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_antenna(struct cfg80211_registered_device *rdev, int radio_idx, u32 tx_ant, u32 rx_ant) { int ret; trace_rdev_set_antenna(&rdev->wiphy, radio_idx, tx_ant, rx_ant); ret = rdev->ops->set_antenna(&rdev->wiphy, -1, tx_ant, rx_ant); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_antenna(struct cfg80211_registered_device *rdev, int radio_idx, u32 *tx_ant, u32 *rx_ant) { int ret; trace_rdev_get_antenna(&rdev->wiphy, radio_idx); ret = rdev->ops->get_antenna(&rdev->wiphy, radio_idx, tx_ant, rx_ant); if (ret) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_tx_rx(&rdev->wiphy, ret, *tx_ant, *rx_ant); return ret; } static inline int rdev_sched_scan_start(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_sched_scan_request *request) { int ret; trace_rdev_sched_scan_start(&rdev->wiphy, dev, request->reqid); ret = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_sched_scan_stop(struct cfg80211_registered_device *rdev, struct net_device *dev, u64 reqid) { int ret; trace_rdev_sched_scan_stop(&rdev->wiphy, dev, reqid); ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev, reqid); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) { int ret; trace_rdev_set_rekey_data(&rdev->wiphy, dev); ret = rdev->ops->set_rekey_data(&rdev->wiphy, dev, data); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_oper(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, enum nl80211_tdls_operation oper) { int ret; trace_rdev_tdls_oper(&rdev->wiphy, dev, peer, oper); ret = rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, oper); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_client(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u64 *cookie) { int ret; trace_rdev_probe_client(&rdev->wiphy, dev, peer); ret = rdev->ops->probe_client(&rdev->wiphy, dev, peer, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 noack_map) { int ret; trace_rdev_set_noack_map(&rdev->wiphy, dev, noack_map); ret = rdev->ops->set_noack_map(&rdev->wiphy, dev, noack_map); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_get_channel(&rdev->wiphy, wdev, link_id); ret = rdev->ops->get_channel(&rdev->wiphy, wdev, link_id, chandef); trace_rdev_return_chandef(&rdev->wiphy, ret, chandef); return ret; } static inline int rdev_start_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_start_p2p_device(&rdev->wiphy, wdev); ret = rdev->ops->start_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_p2p_device(&rdev->wiphy, wdev); rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { int ret; trace_rdev_start_nan(&rdev->wiphy, wdev, conf); ret = rdev->ops->start_nan(&rdev->wiphy, wdev, conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_nan(&rdev->wiphy, wdev); rdev->ops->stop_nan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { int ret; trace_rdev_add_nan_func(&rdev->wiphy, wdev, nan_func); ret = rdev->ops->add_nan_func(&rdev->wiphy, wdev, nan_func); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { trace_rdev_del_nan_func(&rdev->wiphy, wdev, cookie); rdev->ops->del_nan_func(&rdev->wiphy, wdev, cookie); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_nan_change_conf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { int ret; trace_rdev_nan_change_conf(&rdev->wiphy, wdev, conf, changes); if (rdev->ops->nan_change_conf) ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf, changes); else ret = -EOPNOTSUPP; trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) { int ret; trace_rdev_set_mac_acl(&rdev->wiphy, dev, params); ret = rdev->ops->set_mac_acl(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_ft_ies(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie) { int ret; trace_rdev_update_ft_ies(&rdev->wiphy, dev, ftie); ret = rdev->ops->update_ft_ies(&rdev->wiphy, dev, ftie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_crit_proto_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_crit_proto_id protocol, u16 duration) { int ret; trace_rdev_crit_proto_start(&rdev->wiphy, wdev, protocol, duration); ret = rdev->ops->crit_proto_start(&rdev->wiphy, wdev, protocol, duration); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_crit_proto_stop(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_crit_proto_stop(&rdev->wiphy, wdev); rdev->ops->crit_proto_stop(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_csa_settings *params) { int ret; trace_rdev_channel_switch(&rdev->wiphy, dev, params); ret = rdev->ops->channel_switch(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_qos_map *qos_map) { int ret = -EOPNOTSUPP; if (rdev->ops->set_qos_map) { trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map); ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map); trace_rdev_return_int(&rdev->wiphy, ret); } return ret; } static inline int rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer, u8 user_prio, u16 admitted_time) { int ret = -EOPNOTSUPP; trace_rdev_add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); if (rdev->ops->add_tx_ts) ret = rdev->ops->add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer) { int ret = -EOPNOTSUPP; trace_rdev_del_tx_ts(&rdev->wiphy, dev, tsid, peer); if (rdev->ops->del_tx_ts) ret = rdev->ops->del_tx_ts(&rdev->wiphy, dev, tsid, peer); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr, u8 oper_class, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); ret = rdev->ops->tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_tdls_cancel_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr) { trace_rdev_tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); rdev->ops->tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_radar_detection(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms, int link_id) { int ret = -EOPNOTSUPP; trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms, link_id); if (rdev->ops->start_radar_detection) ret = rdev->ops->start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_end_cac(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id) { trace_rdev_end_cac(&rdev->wiphy, dev, link_id); if (rdev->ops->end_cac) rdev->ops->end_cac(&rdev->wiphy, dev, link_id); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, int mcast_rate[NUM_NL80211_BANDS]) { int ret = -EOPNOTSUPP; trace_rdev_set_mcast_rate(&rdev->wiphy, dev, mcast_rate); if (rdev->ops->set_mcast_rate) ret = rdev->ops->set_mcast_rate(&rdev->wiphy, dev, mcast_rate); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_coalesce(struct cfg80211_registered_device *rdev, struct cfg80211_coalesce *coalesce) { int ret = -EOPNOTSUPP; trace_rdev_set_coalesce(&rdev->wiphy, coalesce); if (rdev->ops->set_coalesce) ret = rdev->ops->set_coalesce(&rdev->wiphy, coalesce); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_pmk_conf *pmk_conf) { int ret = -EOPNOTSUPP; trace_rdev_set_pmk(&rdev->wiphy, dev, pmk_conf); if (rdev->ops->set_pmk) ret = rdev->ops->set_pmk(&rdev->wiphy, dev, pmk_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *aa) { int ret = -EOPNOTSUPP; trace_rdev_del_pmk(&rdev->wiphy, dev, aa); if (rdev->ops->del_pmk) ret = rdev->ops->del_pmk(&rdev->wiphy, dev, aa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_external_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_external_auth_params *params) { int ret = -EOPNOTSUPP; trace_rdev_external_auth(&rdev->wiphy, dev, params); if (rdev->ops->external_auth) ret = rdev->ops->external_auth(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_ftm_responder_stats(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats) { int ret = -EOPNOTSUPP; trace_rdev_get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); if (rdev->ops->get_ftm_responder_stats) ret = rdev->ops->get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { int ret = -EOPNOTSUPP; trace_rdev_start_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->start_pmsr) ret = rdev->ops->start_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { trace_rdev_abort_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->abort_pmsr) rdev->ops->abort_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_update_owe_info(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_owe_info *oweinfo) { int ret = -EOPNOTSUPP; trace_rdev_update_owe_info(&rdev->wiphy, dev, oweinfo); if (rdev->ops->update_owe_info) ret = rdev->ops->update_owe_info(&rdev->wiphy, dev, oweinfo); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *dest, const void *buf, size_t len) { int ret; trace_rdev_probe_mesh_link(&rdev->wiphy, dev, dest, buf, len); ret = rdev->ops->probe_mesh_link(&rdev->wiphy, dev, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_tid_config *tid_conf) { int ret; trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u8 tids) { int ret; trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev, struct cfg80211_sar_specs *sar) { int ret; trace_rdev_set_sar_specs(&rdev->wiphy, sar); ret = rdev->ops->set_sar_specs(&rdev->wiphy, sar); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_color_change(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_color_change_settings *params) { int ret; trace_rdev_color_change(&rdev->wiphy, dev, params); ret = rdev->ops->color_change(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_fils_aad(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_fils_aad *fils_aad) { int ret = -EOPNOTSUPP; trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); if (rdev->ops->set_fils_aad) ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_radar_background(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_radar_background(wiphy, chandef); if (rdev->ops->set_radar_background) ret = rdev->ops->set_radar_background(wiphy, chandef); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_add_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { int ret = 0; trace_rdev_add_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->add_intf_link) ret = rdev->ops->add_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { trace_rdev_del_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->del_intf_link) rdev->ops->del_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_add_link_station(&rdev->wiphy, dev, params); if (rdev->ops->add_link_station) ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mod_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_mod_link_station(&rdev->wiphy, dev, params); if (rdev->ops->mod_link_station) ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_del_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_del_link_station(&rdev->wiphy, dev, params); if (rdev->ops->del_link_station) ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_hw_timestamp(wiphy, dev, hwts); if (rdev->ops->set_hw_timestamp) ret = rdev->ops->set_hw_timestamp(wiphy, dev, hwts); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_set_ttlm(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ttlm_params *params) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_ttlm(wiphy, dev, params); if (rdev->ops->set_ttlm) ret = rdev->ops->set_ttlm(wiphy, dev, params); trace_rdev_return_int(wiphy, ret); return ret; } static inline u32 rdev_get_radio_mask(struct cfg80211_registered_device *rdev, struct net_device *dev) { struct wiphy *wiphy = &rdev->wiphy; if (!rdev->ops->get_radio_mask) return 0; return rdev->ops->get_radio_mask(wiphy, dev); } static inline int rdev_assoc_ml_reconf(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ml_reconf_req *req) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_assoc_ml_reconf(wiphy, dev, req); if (rdev->ops->assoc_ml_reconf) ret = rdev->ops->assoc_ml_reconf(wiphy, dev, req); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_set_epcs(struct cfg80211_registered_device *rdev, struct net_device *dev, bool val) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_epcs(wiphy, dev, val); if (rdev->ops->set_epcs) ret = rdev->ops->set_epcs(wiphy, dev, val); trace_rdev_return_int(wiphy, ret); return ret; } #endif /* __CFG80211_RDEV_OPS */ |
| 311 311 311 311 311 | 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 | // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #include "zstd_ldm.h" #include "../common/debug.h" #include <linux/xxhash.h> #include "zstd_fast.h" /* ZSTD_fillHashTable() */ #include "zstd_double_fast.h" /* ZSTD_fillDoubleHashTable() */ #include "zstd_ldm_geartab.h" #define LDM_BUCKET_SIZE_LOG 4 #define LDM_MIN_MATCH_LENGTH 64 #define LDM_HASH_RLOG 7 typedef struct { U64 rolling; U64 stopMask; } ldmRollingHashState_t; /* ZSTD_ldm_gear_init(): * * Initializes the rolling hash state such that it will honor the * settings in params. */ static void ZSTD_ldm_gear_init(ldmRollingHashState_t* state, ldmParams_t const* params) { unsigned maxBitsInMask = MIN(params->minMatchLength, 64); unsigned hashRateLog = params->hashRateLog; state->rolling = ~(U32)0; /* The choice of the splitting criterion is subject to two conditions: * 1. it has to trigger on average every 2^(hashRateLog) bytes; * 2. ideally, it has to depend on a window of minMatchLength bytes. * * In the gear hash algorithm, bit n depends on the last n bytes; * so in order to obtain a good quality splitting criterion it is * preferable to use bits with high weight. * * To match condition 1 we use a mask with hashRateLog bits set * and, because of the previous remark, we make sure these bits * have the highest possible weight while still respecting * condition 2. */ if (hashRateLog > 0 && hashRateLog <= maxBitsInMask) { state->stopMask = (((U64)1 << hashRateLog) - 1) << (maxBitsInMask - hashRateLog); } else { /* In this degenerate case we simply honor the hash rate. */ state->stopMask = ((U64)1 << hashRateLog) - 1; } } /* ZSTD_ldm_gear_reset() * Feeds [data, data + minMatchLength) into the hash without registering any * splits. This effectively resets the hash state. This is used when skipping * over data, either at the beginning of a block, or skipping sections. */ static void ZSTD_ldm_gear_reset(ldmRollingHashState_t* state, BYTE const* data, size_t minMatchLength) { U64 hash = state->rolling; size_t n = 0; #define GEAR_ITER_ONCE() do { \ hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \ n += 1; \ } while (0) while (n + 3 < minMatchLength) { GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); } while (n < minMatchLength) { GEAR_ITER_ONCE(); } #undef GEAR_ITER_ONCE } /* ZSTD_ldm_gear_feed(): * * Registers in the splits array all the split points found in the first * size bytes following the data pointer. This function terminates when * either all the data has been processed or LDM_BATCH_SIZE splits are * present in the splits array. * * Precondition: The splits array must not be full. * Returns: The number of bytes processed. */ static size_t ZSTD_ldm_gear_feed(ldmRollingHashState_t* state, BYTE const* data, size_t size, size_t* splits, unsigned* numSplits) { size_t n; U64 hash, mask; hash = state->rolling; mask = state->stopMask; n = 0; #define GEAR_ITER_ONCE() do { \ hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \ n += 1; \ if (UNLIKELY((hash & mask) == 0)) { \ splits[*numSplits] = n; \ *numSplits += 1; \ if (*numSplits == LDM_BATCH_SIZE) \ goto done; \ } \ } while (0) while (n + 3 < size) { GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); } while (n < size) { GEAR_ITER_ONCE(); } #undef GEAR_ITER_ONCE done: state->rolling = hash; return n; } void ZSTD_ldm_adjustParameters(ldmParams_t* params, const ZSTD_compressionParameters* cParams) { params->windowLog = cParams->windowLog; ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX); DEBUGLOG(4, "ZSTD_ldm_adjustParameters"); if (params->hashRateLog == 0) { if (params->hashLog > 0) { /* if params->hashLog is set, derive hashRateLog from it */ assert(params->hashLog <= ZSTD_HASHLOG_MAX); if (params->windowLog > params->hashLog) { params->hashRateLog = params->windowLog - params->hashLog; } } else { assert(1 <= (int)cParams->strategy && (int)cParams->strategy <= 9); /* mapping from [fast, rate7] to [btultra2, rate4] */ params->hashRateLog = 7 - (cParams->strategy/3); } } if (params->hashLog == 0) { params->hashLog = BOUNDED(ZSTD_HASHLOG_MIN, params->windowLog - params->hashRateLog, ZSTD_HASHLOG_MAX); } if (params->minMatchLength == 0) { params->minMatchLength = LDM_MIN_MATCH_LENGTH; if (cParams->strategy >= ZSTD_btultra) params->minMatchLength /= 2; } if (params->bucketSizeLog==0) { assert(1 <= (int)cParams->strategy && (int)cParams->strategy <= 9); params->bucketSizeLog = BOUNDED(LDM_BUCKET_SIZE_LOG, (U32)cParams->strategy, ZSTD_LDM_BUCKETSIZELOG_MAX); } params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog); } size_t ZSTD_ldm_getTableSize(ldmParams_t params) { size_t const ldmHSize = ((size_t)1) << params.hashLog; size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog); size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog); size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize) + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t)); return params.enableLdm == ZSTD_ps_enable ? totalSize : 0; } size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize) { return params.enableLdm == ZSTD_ps_enable ? (maxChunkSize / params.minMatchLength) : 0; } /* ZSTD_ldm_getBucket() : * Returns a pointer to the start of the bucket associated with hash. */ static ldmEntry_t* ZSTD_ldm_getBucket( const ldmState_t* ldmState, size_t hash, U32 const bucketSizeLog) { return ldmState->hashTable + (hash << bucketSizeLog); } /* ZSTD_ldm_insertEntry() : * Insert the entry with corresponding hash into the hash table */ static void ZSTD_ldm_insertEntry(ldmState_t* ldmState, size_t const hash, const ldmEntry_t entry, U32 const bucketSizeLog) { BYTE* const pOffset = ldmState->bucketOffsets + hash; unsigned const offset = *pOffset; *(ZSTD_ldm_getBucket(ldmState, hash, bucketSizeLog) + offset) = entry; *pOffset = (BYTE)((offset + 1) & ((1u << bucketSizeLog) - 1)); } /* ZSTD_ldm_countBackwardsMatch() : * Returns the number of bytes that match backwards before pIn and pMatch. * * We count only bytes where pMatch >= pBase and pIn >= pAnchor. */ static size_t ZSTD_ldm_countBackwardsMatch( const BYTE* pIn, const BYTE* pAnchor, const BYTE* pMatch, const BYTE* pMatchBase) { size_t matchLength = 0; while (pIn > pAnchor && pMatch > pMatchBase && pIn[-1] == pMatch[-1]) { pIn--; pMatch--; matchLength++; } return matchLength; } /* ZSTD_ldm_countBackwardsMatch_2segments() : * Returns the number of bytes that match backwards from pMatch, * even with the backwards match spanning 2 different segments. * * On reaching `pMatchBase`, start counting from mEnd */ static size_t ZSTD_ldm_countBackwardsMatch_2segments( const BYTE* pIn, const BYTE* pAnchor, const BYTE* pMatch, const BYTE* pMatchBase, const BYTE* pExtDictStart, const BYTE* pExtDictEnd) { size_t matchLength = ZSTD_ldm_countBackwardsMatch(pIn, pAnchor, pMatch, pMatchBase); if (pMatch - matchLength != pMatchBase || pMatchBase == pExtDictStart) { /* If backwards match is entirely in the extDict or prefix, immediately return */ return matchLength; } DEBUGLOG(7, "ZSTD_ldm_countBackwardsMatch_2segments: found 2-parts backwards match (length in prefix==%zu)", matchLength); matchLength += ZSTD_ldm_countBackwardsMatch(pIn - matchLength, pAnchor, pExtDictEnd, pExtDictStart); DEBUGLOG(7, "final backwards match length = %zu", matchLength); return matchLength; } /* ZSTD_ldm_fillFastTables() : * * Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies. * This is similar to ZSTD_loadDictionaryContent. * * The tables for the other strategies are filled within their * block compressors. */ static size_t ZSTD_ldm_fillFastTables(ZSTD_MatchState_t* ms, void const* end) { const BYTE* const iend = (const BYTE*)end; switch(ms->cParams.strategy) { case ZSTD_fast: ZSTD_fillHashTable(ms, iend, ZSTD_dtlm_fast, ZSTD_tfp_forCCtx); break; case ZSTD_dfast: #ifndef ZSTD_EXCLUDE_DFAST_BLOCK_COMPRESSOR ZSTD_fillDoubleHashTable(ms, iend, ZSTD_dtlm_fast, ZSTD_tfp_forCCtx); #else assert(0); /* shouldn't be called: cparams should've been adjusted. */ #endif break; case ZSTD_greedy: case ZSTD_lazy: case ZSTD_lazy2: case ZSTD_btlazy2: case ZSTD_btopt: case ZSTD_btultra: case ZSTD_btultra2: break; default: assert(0); /* not possible : not a valid strategy id */ } return 0; } void ZSTD_ldm_fillHashTable( ldmState_t* ldmState, const BYTE* ip, const BYTE* iend, ldmParams_t const* params) { U32 const minMatchLength = params->minMatchLength; U32 const bucketSizeLog = params->bucketSizeLog; U32 const hBits = params->hashLog - bucketSizeLog; BYTE const* const base = ldmState->window.base; BYTE const* const istart = ip; ldmRollingHashState_t hashState; size_t* const splits = ldmState->splitIndices; unsigned numSplits; DEBUGLOG(5, "ZSTD_ldm_fillHashTable"); ZSTD_ldm_gear_init(&hashState, params); while (ip < iend) { size_t hashed; unsigned n; numSplits = 0; hashed = ZSTD_ldm_gear_feed(&hashState, ip, (size_t)(iend - ip), splits, &numSplits); for (n = 0; n < numSplits; n++) { if (ip + splits[n] >= istart + minMatchLength) { BYTE const* const split = ip + splits[n] - minMatchLength; U64 const xxhash = xxh64(split, minMatchLength, 0); U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); ldmEntry_t entry; entry.offset = (U32)(split - base); entry.checksum = (U32)(xxhash >> 32); ZSTD_ldm_insertEntry(ldmState, hash, entry, params->bucketSizeLog); } } ip += hashed; } } /* ZSTD_ldm_limitTableUpdate() : * * Sets cctx->nextToUpdate to a position corresponding closer to anchor * if it is far way * (after a long match, only update tables a limited amount). */ static void ZSTD_ldm_limitTableUpdate(ZSTD_MatchState_t* ms, const BYTE* anchor) { U32 const curr = (U32)(anchor - ms->window.base); if (curr > ms->nextToUpdate + 1024) { ms->nextToUpdate = curr - MIN(512, curr - ms->nextToUpdate - 1024); } } static ZSTD_ALLOW_POINTER_OVERFLOW_ATTR size_t ZSTD_ldm_generateSequences_internal( ldmState_t* ldmState, RawSeqStore_t* rawSeqStore, ldmParams_t const* params, void const* src, size_t srcSize) { /* LDM parameters */ int const extDict = ZSTD_window_hasExtDict(ldmState->window); U32 const minMatchLength = params->minMatchLength; U32 const entsPerBucket = 1U << params->bucketSizeLog; U32 const hBits = params->hashLog - params->bucketSizeLog; /* Prefix and extDict parameters */ U32 const dictLimit = ldmState->window.dictLimit; U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit; BYTE const* const base = ldmState->window.base; BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL; BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL; BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL; BYTE const* const lowPrefixPtr = base + dictLimit; /* Input bounds */ BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; BYTE const* const ilimit = iend - HASH_READ_SIZE; /* Input positions */ BYTE const* anchor = istart; BYTE const* ip = istart; /* Rolling hash state */ ldmRollingHashState_t hashState; /* Arrays for staged-processing */ size_t* const splits = ldmState->splitIndices; ldmMatchCandidate_t* const candidates = ldmState->matchCandidates; unsigned numSplits; if (srcSize < minMatchLength) return iend - anchor; /* Initialize the rolling hash state with the first minMatchLength bytes */ ZSTD_ldm_gear_init(&hashState, params); ZSTD_ldm_gear_reset(&hashState, ip, minMatchLength); ip += minMatchLength; while (ip < ilimit) { size_t hashed; unsigned n; numSplits = 0; hashed = ZSTD_ldm_gear_feed(&hashState, ip, ilimit - ip, splits, &numSplits); for (n = 0; n < numSplits; n++) { BYTE const* const split = ip + splits[n] - minMatchLength; U64 const xxhash = xxh64(split, minMatchLength, 0); U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); candidates[n].split = split; candidates[n].hash = hash; candidates[n].checksum = (U32)(xxhash >> 32); candidates[n].bucket = ZSTD_ldm_getBucket(ldmState, hash, params->bucketSizeLog); PREFETCH_L1(candidates[n].bucket); } for (n = 0; n < numSplits; n++) { size_t forwardMatchLength = 0, backwardMatchLength = 0, bestMatchLength = 0, mLength; U32 offset; BYTE const* const split = candidates[n].split; U32 const checksum = candidates[n].checksum; U32 const hash = candidates[n].hash; ldmEntry_t* const bucket = candidates[n].bucket; ldmEntry_t const* cur; ldmEntry_t const* bestEntry = NULL; ldmEntry_t newEntry; newEntry.offset = (U32)(split - base); newEntry.checksum = checksum; /* If a split point would generate a sequence overlapping with * the previous one, we merely register it in the hash table and * move on */ if (split < anchor) { ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); continue; } for (cur = bucket; cur < bucket + entsPerBucket; cur++) { size_t curForwardMatchLength, curBackwardMatchLength, curTotalMatchLength; if (cur->checksum != checksum || cur->offset <= lowestIndex) { continue; } if (extDict) { BYTE const* const curMatchBase = cur->offset < dictLimit ? dictBase : base; BYTE const* const pMatch = curMatchBase + cur->offset; BYTE const* const matchEnd = cur->offset < dictLimit ? dictEnd : iend; BYTE const* const lowMatchPtr = cur->offset < dictLimit ? dictStart : lowPrefixPtr; curForwardMatchLength = ZSTD_count_2segments(split, pMatch, iend, matchEnd, lowPrefixPtr); if (curForwardMatchLength < minMatchLength) { continue; } curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch_2segments( split, anchor, pMatch, lowMatchPtr, dictStart, dictEnd); } else { /* !extDict */ BYTE const* const pMatch = base + cur->offset; curForwardMatchLength = ZSTD_count(split, pMatch, iend); if (curForwardMatchLength < minMatchLength) { continue; } curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch(split, anchor, pMatch, lowPrefixPtr); } curTotalMatchLength = curForwardMatchLength + curBackwardMatchLength; if (curTotalMatchLength > bestMatchLength) { bestMatchLength = curTotalMatchLength; forwardMatchLength = curForwardMatchLength; backwardMatchLength = curBackwardMatchLength; bestEntry = cur; } } /* No match found -- insert an entry into the hash table * and process the next candidate match */ if (bestEntry == NULL) { ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); continue; } /* Match found */ offset = (U32)(split - base) - bestEntry->offset; mLength = forwardMatchLength + backwardMatchLength; { rawSeq* const seq = rawSeqStore->seq + rawSeqStore->size; /* Out of sequence storage */ if (rawSeqStore->size == rawSeqStore->capacity) return ERROR(dstSize_tooSmall); seq->litLength = (U32)(split - backwardMatchLength - anchor); seq->matchLength = (U32)mLength; seq->offset = offset; rawSeqStore->size++; } /* Insert the current entry into the hash table --- it must be * done after the previous block to avoid clobbering bestEntry */ ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); anchor = split + forwardMatchLength; /* If we find a match that ends after the data that we've hashed * then we have a repeating, overlapping, pattern. E.g. all zeros. * If one repetition of the pattern matches our `stopMask` then all * repetitions will. We don't need to insert them all into out table, * only the first one. So skip over overlapping matches. * This is a major speed boost (20x) for compressing a single byte * repeated, when that byte ends up in the table. */ if (anchor > ip + hashed) { ZSTD_ldm_gear_reset(&hashState, anchor - minMatchLength, minMatchLength); /* Continue the outer loop at anchor (ip + hashed == anchor). */ ip = anchor - hashed; break; } } ip += hashed; } return iend - anchor; } /*! ZSTD_ldm_reduceTable() : * reduce table indexes by `reducerValue` */ static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size, U32 const reducerValue) { U32 u; for (u = 0; u < size; u++) { if (table[u].offset < reducerValue) table[u].offset = 0; else table[u].offset -= reducerValue; } } size_t ZSTD_ldm_generateSequences( ldmState_t* ldmState, RawSeqStore_t* sequences, ldmParams_t const* params, void const* src, size_t srcSize) { U32 const maxDist = 1U << params->windowLog; BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; size_t const kMaxChunkSize = 1 << 20; size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0); size_t chunk; size_t leftoverSize = 0; assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize); /* Check that ZSTD_window_update() has been called for this chunk prior * to passing it to this function. */ assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); /* The input could be very large (in zstdmt), so it must be broken up into * chunks to enforce the maximum distance and handle overflow correction. */ assert(sequences->pos <= sequences->size); assert(sequences->size <= sequences->capacity); for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) { BYTE const* const chunkStart = istart + chunk * kMaxChunkSize; size_t const remaining = (size_t)(iend - chunkStart); BYTE const *const chunkEnd = (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize; size_t const chunkSize = chunkEnd - chunkStart; size_t newLeftoverSize; size_t const prevSize = sequences->size; assert(chunkStart < iend); /* 1. Perform overflow correction if necessary. */ if (ZSTD_window_needOverflowCorrection(ldmState->window, 0, maxDist, ldmState->loadedDictEnd, chunkStart, chunkEnd)) { U32 const ldmHSize = 1U << params->hashLog; U32 const correction = ZSTD_window_correctOverflow( &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart); ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction); /* invalidate dictionaries on overflow correction */ ldmState->loadedDictEnd = 0; } /* 2. We enforce the maximum offset allowed. * * kMaxChunkSize should be small enough that we don't lose too much of * the window through early invalidation. * TODO: * Test the chunk size. * * Try invalidation after the sequence generation and test the * offset against maxDist directly. * * NOTE: Because of dictionaries + sequence splitting we MUST make sure * that any offset used is valid at the END of the sequence, since it may * be split into two sequences. This condition holds when using * ZSTD_window_enforceMaxDist(), but if we move to checking offsets * against maxDist directly, we'll have to carefully handle that case. */ ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL); /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */ newLeftoverSize = ZSTD_ldm_generateSequences_internal( ldmState, sequences, params, chunkStart, chunkSize); if (ZSTD_isError(newLeftoverSize)) return newLeftoverSize; /* 4. We add the leftover literals from previous iterations to the first * newly generated sequence, or add the `newLeftoverSize` if none are * generated. */ /* Prepend the leftover literals from the last call */ if (prevSize < sequences->size) { sequences->seq[prevSize].litLength += (U32)leftoverSize; leftoverSize = newLeftoverSize; } else { assert(newLeftoverSize == chunkSize); leftoverSize += chunkSize; } } return 0; } void ZSTD_ldm_skipSequences(RawSeqStore_t* rawSeqStore, size_t srcSize, U32 const minMatch) { while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) { rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos; if (srcSize <= seq->litLength) { /* Skip past srcSize literals */ seq->litLength -= (U32)srcSize; return; } srcSize -= seq->litLength; seq->litLength = 0; if (srcSize < seq->matchLength) { /* Skip past the first srcSize of the match */ seq->matchLength -= (U32)srcSize; if (seq->matchLength < minMatch) { /* The match is too short, omit it */ if (rawSeqStore->pos + 1 < rawSeqStore->size) { seq[1].litLength += seq[0].matchLength; } rawSeqStore->pos++; } return; } srcSize -= seq->matchLength; seq->matchLength = 0; rawSeqStore->pos++; } } /* * If the sequence length is longer than remaining then the sequence is split * between this block and the next. * * Returns the current sequence to handle, or if the rest of the block should * be literals, it returns a sequence with offset == 0. */ static rawSeq maybeSplitSequence(RawSeqStore_t* rawSeqStore, U32 const remaining, U32 const minMatch) { rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos]; assert(sequence.offset > 0); /* Likely: No partial sequence */ if (remaining >= sequence.litLength + sequence.matchLength) { rawSeqStore->pos++; return sequence; } /* Cut the sequence short (offset == 0 ==> rest is literals). */ if (remaining <= sequence.litLength) { sequence.offset = 0; } else if (remaining < sequence.litLength + sequence.matchLength) { sequence.matchLength = remaining - sequence.litLength; if (sequence.matchLength < minMatch) { sequence.offset = 0; } } /* Skip past `remaining` bytes for the future sequences. */ ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch); return sequence; } void ZSTD_ldm_skipRawSeqStoreBytes(RawSeqStore_t* rawSeqStore, size_t nbBytes) { U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes); while (currPos && rawSeqStore->pos < rawSeqStore->size) { rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos]; if (currPos >= currSeq.litLength + currSeq.matchLength) { currPos -= currSeq.litLength + currSeq.matchLength; rawSeqStore->pos++; } else { rawSeqStore->posInSequence = currPos; break; } } if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) { rawSeqStore->posInSequence = 0; } } size_t ZSTD_ldm_blockCompress(RawSeqStore_t* rawSeqStore, ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], ZSTD_ParamSwitch_e useRowMatchFinder, void const* src, size_t srcSize) { const ZSTD_compressionParameters* const cParams = &ms->cParams; unsigned const minMatch = cParams->minMatch; ZSTD_BlockCompressor_f const blockCompressor = ZSTD_selectBlockCompressor(cParams->strategy, useRowMatchFinder, ZSTD_matchState_dictMode(ms)); /* Input bounds */ BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; /* Input positions */ BYTE const* ip = istart; DEBUGLOG(5, "ZSTD_ldm_blockCompress: srcSize=%zu", srcSize); /* If using opt parser, use LDMs only as candidates rather than always accepting them */ if (cParams->strategy >= ZSTD_btopt) { size_t lastLLSize; ms->ldmSeqStore = rawSeqStore; lastLLSize = blockCompressor(ms, seqStore, rep, src, srcSize); ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore, srcSize); return lastLLSize; } assert(rawSeqStore->pos <= rawSeqStore->size); assert(rawSeqStore->size <= rawSeqStore->capacity); /* Loop through each sequence and apply the block compressor to the literals */ while (rawSeqStore->pos < rawSeqStore->size && ip < iend) { /* maybeSplitSequence updates rawSeqStore->pos */ rawSeq const sequence = maybeSplitSequence(rawSeqStore, (U32)(iend - ip), minMatch); /* End signal */ if (sequence.offset == 0) break; assert(ip + sequence.litLength + sequence.matchLength <= iend); /* Fill tables for block compressor */ ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); /* Run the block compressor */ DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength); { int i; size_t const newLitLength = blockCompressor(ms, seqStore, rep, ip, sequence.litLength); ip += sequence.litLength; /* Update the repcodes */ for (i = ZSTD_REP_NUM - 1; i > 0; i--) rep[i] = rep[i-1]; rep[0] = sequence.offset; /* Store the sequence */ ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend, OFFSET_TO_OFFBASE(sequence.offset), sequence.matchLength); ip += sequence.matchLength; } } /* Fill the tables for the block compressor */ ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); /* Compress the last literals */ return blockCompressor(ms, seqStore, rep, ip, iend - ip); } |
| 14 14 1 13 12 1 13 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hpfs/inode.c * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * inode VFS functions */ #include <linux/slab.h> #include <linux/user_namespace.h> #include "hpfs_fn.h" void hpfs_init_inode(struct inode *i) { struct super_block *sb = i->i_sb; struct hpfs_inode_info *hpfs_inode = hpfs_i(i); i->i_uid = hpfs_sb(sb)->sb_uid; i->i_gid = hpfs_sb(sb)->sb_gid; i->i_mode = hpfs_sb(sb)->sb_mode; i->i_size = -1; i->i_blocks = -1; hpfs_inode->i_dno = 0; hpfs_inode->i_n_secs = 0; hpfs_inode->i_file_sec = 0; hpfs_inode->i_disk_sec = 0; hpfs_inode->i_dpos = 0; hpfs_inode->i_dsubdno = 0; hpfs_inode->i_ea_mode = 0; hpfs_inode->i_ea_uid = 0; hpfs_inode->i_ea_gid = 0; hpfs_inode->i_ea_size = 0; hpfs_inode->i_rddir_off = NULL; hpfs_inode->i_dirty = 0; inode_set_ctime(i, 0, 0); inode_set_mtime(i, 0, 0); inode_set_atime(i, 0, 0); } void hpfs_read_inode(struct inode *i) { struct buffer_head *bh; struct fnode *fnode; struct super_block *sb = i->i_sb; struct hpfs_inode_info *hpfs_inode = hpfs_i(i); void *ea; int ea_size; if (!(fnode = hpfs_map_fnode(sb, i->i_ino, &bh))) { /*i->i_mode |= S_IFREG; i->i_mode &= ~0111; i->i_op = &hpfs_file_iops; i->i_fop = &hpfs_file_ops; clear_nlink(i);*/ make_bad_inode(i); return; } if (hpfs_sb(i->i_sb)->sb_eas) { if ((ea = hpfs_get_ea(i->i_sb, fnode, "UID", &ea_size))) { if (ea_size == 2) { i_uid_write(i, le16_to_cpu(*(__le16*)ea)); hpfs_inode->i_ea_uid = 1; } kfree(ea); } if ((ea = hpfs_get_ea(i->i_sb, fnode, "GID", &ea_size))) { if (ea_size == 2) { i_gid_write(i, le16_to_cpu(*(__le16*)ea)); hpfs_inode->i_ea_gid = 1; } kfree(ea); } if ((ea = hpfs_get_ea(i->i_sb, fnode, "SYMLINK", &ea_size))) { kfree(ea); i->i_mode = S_IFLNK | 0777; i->i_op = &page_symlink_inode_operations; inode_nohighmem(i); i->i_data.a_ops = &hpfs_symlink_aops; set_nlink(i, 1); i->i_size = ea_size; i->i_blocks = 1; brelse(bh); return; } if ((ea = hpfs_get_ea(i->i_sb, fnode, "MODE", &ea_size))) { int rdev = 0; umode_t mode = hpfs_sb(sb)->sb_mode; if (ea_size == 2) { mode = le16_to_cpu(*(__le16*)ea); hpfs_inode->i_ea_mode = 1; } kfree(ea); i->i_mode = mode; if (S_ISBLK(mode) || S_ISCHR(mode)) { if ((ea = hpfs_get_ea(i->i_sb, fnode, "DEV", &ea_size))) { if (ea_size == 4) rdev = le32_to_cpu(*(__le32*)ea); kfree(ea); } } if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { brelse(bh); set_nlink(i, 1); i->i_size = 0; i->i_blocks = 1; init_special_inode(i, mode, new_decode_dev(rdev)); return; } } } if (fnode_is_dir(fnode)) { int n_dnodes, n_subdirs; i->i_mode |= S_IFDIR; i->i_op = &hpfs_dir_iops; i->i_fop = &hpfs_dir_ops; hpfs_inode->i_parent_dir = le32_to_cpu(fnode->up); hpfs_inode->i_dno = le32_to_cpu(fnode->u.external[0].disk_secno); if (hpfs_sb(sb)->sb_chk >= 2) { struct buffer_head *bh0; if (hpfs_map_fnode(sb, hpfs_inode->i_parent_dir, &bh0)) brelse(bh0); } n_dnodes = 0; n_subdirs = 0; hpfs_count_dnodes(i->i_sb, hpfs_inode->i_dno, &n_dnodes, &n_subdirs, NULL); i->i_blocks = 4 * n_dnodes; i->i_size = 2048 * n_dnodes; set_nlink(i, 2 + n_subdirs); } else { i->i_mode |= S_IFREG; if (!hpfs_inode->i_ea_mode) i->i_mode &= ~0111; i->i_op = &hpfs_file_iops; i->i_fop = &hpfs_file_ops; set_nlink(i, 1); i->i_size = le32_to_cpu(fnode->file_size); i->i_blocks = ((i->i_size + 511) >> 9) + 1; i->i_data.a_ops = &hpfs_aops; hpfs_i(i)->mmu_private = i->i_size; } brelse(bh); } static void hpfs_write_inode_ea(struct inode *i, struct fnode *fnode) { struct hpfs_inode_info *hpfs_inode = hpfs_i(i); /*if (le32_to_cpu(fnode->acl_size_l) || le16_to_cpu(fnode->acl_size_s)) { Some unknown structures like ACL may be in fnode, we'd better not overwrite them hpfs_error(i->i_sb, "fnode %08x has some unknown HPFS386 structures", i->i_ino); } else*/ if (hpfs_sb(i->i_sb)->sb_eas >= 2) { __le32 ea; if (!uid_eq(i->i_uid, hpfs_sb(i->i_sb)->sb_uid) || hpfs_inode->i_ea_uid) { ea = cpu_to_le32(i_uid_read(i)); hpfs_set_ea(i, fnode, "UID", (char*)&ea, 2); hpfs_inode->i_ea_uid = 1; } if (!gid_eq(i->i_gid, hpfs_sb(i->i_sb)->sb_gid) || hpfs_inode->i_ea_gid) { ea = cpu_to_le32(i_gid_read(i)); hpfs_set_ea(i, fnode, "GID", (char *)&ea, 2); hpfs_inode->i_ea_gid = 1; } if (!S_ISLNK(i->i_mode)) if ((i->i_mode != ((hpfs_sb(i->i_sb)->sb_mode & ~(S_ISDIR(i->i_mode) ? 0 : 0111)) | (S_ISDIR(i->i_mode) ? S_IFDIR : S_IFREG)) && i->i_mode != ((hpfs_sb(i->i_sb)->sb_mode & ~(S_ISDIR(i->i_mode) ? 0222 : 0333)) | (S_ISDIR(i->i_mode) ? S_IFDIR : S_IFREG))) || hpfs_inode->i_ea_mode) { ea = cpu_to_le32(i->i_mode); /* sick, but legal */ hpfs_set_ea(i, fnode, "MODE", (char *)&ea, 2); hpfs_inode->i_ea_mode = 1; } if (S_ISBLK(i->i_mode) || S_ISCHR(i->i_mode)) { ea = cpu_to_le32(new_encode_dev(i->i_rdev)); hpfs_set_ea(i, fnode, "DEV", (char *)&ea, 4); } } } void hpfs_write_inode(struct inode *i) { struct hpfs_inode_info *hpfs_inode = hpfs_i(i); struct inode *parent; if (i->i_ino == hpfs_sb(i->i_sb)->sb_root) return; if (hpfs_inode->i_rddir_off && !icount_read(i)) { if (*hpfs_inode->i_rddir_off) pr_err("write_inode: some position still there\n"); kfree(hpfs_inode->i_rddir_off); hpfs_inode->i_rddir_off = NULL; } if (!i->i_nlink) { return; } parent = iget_locked(i->i_sb, hpfs_inode->i_parent_dir); if (parent) { hpfs_inode->i_dirty = 0; if (inode_state_read_once(parent) & I_NEW) { hpfs_init_inode(parent); hpfs_read_inode(parent); unlock_new_inode(parent); } hpfs_write_inode_nolock(i); iput(parent); } } void hpfs_write_inode_nolock(struct inode *i) { struct hpfs_inode_info *hpfs_inode = hpfs_i(i); struct buffer_head *bh; struct fnode *fnode; struct quad_buffer_head qbh; struct hpfs_dirent *de; if (i->i_ino == hpfs_sb(i->i_sb)->sb_root) return; if (!(fnode = hpfs_map_fnode(i->i_sb, i->i_ino, &bh))) return; if (i->i_ino != hpfs_sb(i->i_sb)->sb_root && i->i_nlink) { if (!(de = map_fnode_dirent(i->i_sb, i->i_ino, fnode, &qbh))) { brelse(bh); return; } } else de = NULL; if (S_ISREG(i->i_mode)) { fnode->file_size = cpu_to_le32(i->i_size); if (de) de->file_size = cpu_to_le32(i->i_size); } else if (S_ISDIR(i->i_mode)) { fnode->file_size = cpu_to_le32(0); if (de) de->file_size = cpu_to_le32(0); } hpfs_write_inode_ea(i, fnode); if (de) { de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_mtime_sec(i))); de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_atime_sec(i))); de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime_sec(i))); de->read_only = !(i->i_mode & 0222); de->ea_size = cpu_to_le32(hpfs_inode->i_ea_size); hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); } if (S_ISDIR(i->i_mode)) { if ((de = map_dirent(i, hpfs_inode->i_dno, "\001\001", 2, NULL, &qbh))) { de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_mtime_sec(i))); de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_atime_sec(i))); de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime_sec(i))); de->read_only = !(i->i_mode & 0222); de->ea_size = cpu_to_le32(/*hpfs_inode->i_ea_size*/0); de->file_size = cpu_to_le32(0); hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); } else hpfs_error(i->i_sb, "directory %08lx doesn't have '.' entry", (unsigned long)i->i_ino); } mark_buffer_dirty(bh); brelse(bh); } int hpfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error = -EINVAL; hpfs_lock(inode->i_sb); if (inode->i_ino == hpfs_sb(inode->i_sb)->sb_root) goto out_unlock; if ((attr->ia_valid & ATTR_UID) && from_kuid(&init_user_ns, attr->ia_uid) >= 0x10000) goto out_unlock; if ((attr->ia_valid & ATTR_GID) && from_kgid(&init_user_ns, attr->ia_gid) >= 0x10000) goto out_unlock; if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) goto out_unlock; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) goto out_unlock; if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size != i_size_read(inode)) { error = inode_newsize_ok(inode, attr->ia_size); if (error) goto out_unlock; truncate_setsize(inode, attr->ia_size); hpfs_truncate(inode); } setattr_copy(&nop_mnt_idmap, inode, attr); hpfs_write_inode(inode); out_unlock: hpfs_unlock(inode->i_sb); return error; } void hpfs_write_if_changed(struct inode *inode) { struct hpfs_inode_info *hpfs_inode = hpfs_i(inode); if (hpfs_inode->i_dirty) hpfs_write_inode(inode); } void hpfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (!inode->i_nlink) { hpfs_lock(inode->i_sb); hpfs_remove_fnode(inode->i_sb, inode->i_ino); hpfs_unlock(inode->i_sb); } } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Asynchronous Compression operations * * Copyright (c) 2016, Intel Corporation * Authors: Weigang Li <weigang.li@intel.com> * Giovanni Cabiddu <giovanni.cabiddu@intel.com> */ #include <crypto/internal/acompress.h> #include <crypto/scatterwalk.h> #include <linux/cryptouser.h> #include <linux/cpumask.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/scatterlist.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/workqueue.h> #include <net/netlink.h> #include "compress.h" struct crypto_scomp; enum { ACOMP_WALK_SLEEP = 1 << 0, ACOMP_WALK_SRC_LINEAR = 1 << 1, ACOMP_WALK_DST_LINEAR = 1 << 2, }; static const struct crypto_type crypto_acomp_type; static void acomp_reqchain_done(void *data, int err); static inline struct acomp_alg *__crypto_acomp_alg(struct crypto_alg *alg) { return container_of(alg, struct acomp_alg, calg.base); } static inline struct acomp_alg *crypto_acomp_alg(struct crypto_acomp *tfm) { return __crypto_acomp_alg(crypto_acomp_tfm(tfm)->__crt_alg); } static int __maybe_unused crypto_acomp_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_acomp racomp; memset(&racomp, 0, sizeof(racomp)); strscpy(racomp.type, "acomp", sizeof(racomp.type)); return nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, sizeof(racomp), &racomp); } static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_acomp_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : acomp\n"); } static void crypto_acomp_exit_tfm(struct crypto_tfm *tfm) { struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm); struct acomp_alg *alg = crypto_acomp_alg(acomp); if (alg->exit) alg->exit(acomp); if (acomp_is_async(acomp)) crypto_free_acomp(crypto_acomp_fb(acomp)); } static int crypto_acomp_init_tfm(struct crypto_tfm *tfm) { struct crypto_acomp *acomp = __crypto_acomp_tfm(tfm); struct acomp_alg *alg = crypto_acomp_alg(acomp); struct crypto_acomp *fb = NULL; int err; if (tfm->__crt_alg->cra_type != &crypto_acomp_type) return crypto_init_scomp_ops_async(tfm); if (acomp_is_async(acomp)) { fb = crypto_alloc_acomp(crypto_acomp_alg_name(acomp), 0, CRYPTO_ALG_ASYNC); if (IS_ERR(fb)) return PTR_ERR(fb); err = -EINVAL; if (crypto_acomp_reqsize(fb) > MAX_SYNC_COMP_REQSIZE) goto out_free_fb; tfm->fb = crypto_acomp_tfm(fb); } acomp->compress = alg->compress; acomp->decompress = alg->decompress; acomp->reqsize = alg->base.cra_reqsize; acomp->base.exit = crypto_acomp_exit_tfm; if (!alg->init) return 0; err = alg->init(acomp); if (err) goto out_free_fb; return 0; out_free_fb: crypto_free_acomp(fb); return err; } static unsigned int crypto_acomp_extsize(struct crypto_alg *alg) { int extsize = crypto_alg_extsize(alg); if (alg->cra_type != &crypto_acomp_type) extsize += sizeof(struct crypto_scomp *); return extsize; } static const struct crypto_type crypto_acomp_type = { .extsize = crypto_acomp_extsize, .init_tfm = crypto_acomp_init_tfm, #ifdef CONFIG_PROC_FS .show = crypto_acomp_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_acomp_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_ACOMPRESS_MASK, .type = CRYPTO_ALG_TYPE_ACOMPRESS, .tfmsize = offsetof(struct crypto_acomp, base), .algsize = offsetof(struct acomp_alg, base), }; struct crypto_acomp *crypto_alloc_acomp(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_acomp_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_acomp); struct crypto_acomp *crypto_alloc_acomp_node(const char *alg_name, u32 type, u32 mask, int node) { return crypto_alloc_tfm_node(alg_name, &crypto_acomp_type, type, mask, node); } EXPORT_SYMBOL_GPL(crypto_alloc_acomp_node); static void acomp_save_req(struct acomp_req *req, crypto_completion_t cplt) { struct acomp_req_chain *state = &req->chain; state->compl = req->base.complete; state->data = req->base.data; req->base.complete = cplt; req->base.data = state; } static void acomp_restore_req(struct acomp_req *req) { struct acomp_req_chain *state = req->base.data; req->base.complete = state->compl; req->base.data = state->data; } static void acomp_reqchain_virt(struct acomp_req *req) { struct acomp_req_chain *state = &req->chain; unsigned int slen = req->slen; unsigned int dlen = req->dlen; if (state->flags & CRYPTO_ACOMP_REQ_SRC_VIRT) acomp_request_set_src_dma(req, state->src, slen); if (state->flags & CRYPTO_ACOMP_REQ_DST_VIRT) acomp_request_set_dst_dma(req, state->dst, dlen); } static void acomp_virt_to_sg(struct acomp_req *req) { struct acomp_req_chain *state = &req->chain; state->flags = req->base.flags & (CRYPTO_ACOMP_REQ_SRC_VIRT | CRYPTO_ACOMP_REQ_DST_VIRT); if (acomp_request_src_isvirt(req)) { unsigned int slen = req->slen; const u8 *svirt = req->svirt; state->src = svirt; sg_init_one(&state->ssg, svirt, slen); acomp_request_set_src_sg(req, &state->ssg, slen); } if (acomp_request_dst_isvirt(req)) { unsigned int dlen = req->dlen; u8 *dvirt = req->dvirt; state->dst = dvirt; sg_init_one(&state->dsg, dvirt, dlen); acomp_request_set_dst_sg(req, &state->dsg, dlen); } } static int acomp_do_nondma(struct acomp_req *req, bool comp) { ACOMP_FBREQ_ON_STACK(fbreq, req); int err; if (comp) err = crypto_acomp_compress(fbreq); else err = crypto_acomp_decompress(fbreq); req->dlen = fbreq->dlen; return err; } static int acomp_do_one_req(struct acomp_req *req, bool comp) { if (acomp_request_isnondma(req)) return acomp_do_nondma(req, comp); acomp_virt_to_sg(req); return comp ? crypto_acomp_reqtfm(req)->compress(req) : crypto_acomp_reqtfm(req)->decompress(req); } static int acomp_reqchain_finish(struct acomp_req *req, int err) { acomp_reqchain_virt(req); acomp_restore_req(req); return err; } static void acomp_reqchain_done(void *data, int err) { struct acomp_req *req = data; crypto_completion_t compl; compl = req->chain.compl; data = req->chain.data; if (err == -EINPROGRESS) goto notify; err = acomp_reqchain_finish(req, err); notify: compl(data, err); } static int acomp_do_req_chain(struct acomp_req *req, bool comp) { int err; acomp_save_req(req, acomp_reqchain_done); err = acomp_do_one_req(req, comp); if (err == -EBUSY || err == -EINPROGRESS) return err; return acomp_reqchain_finish(req, err); } int crypto_acomp_compress(struct acomp_req *req) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); if (acomp_req_on_stack(req) && acomp_is_async(tfm)) return -EAGAIN; if (crypto_acomp_req_virt(tfm) || acomp_request_issg(req)) return crypto_acomp_reqtfm(req)->compress(req); return acomp_do_req_chain(req, true); } EXPORT_SYMBOL_GPL(crypto_acomp_compress); int crypto_acomp_decompress(struct acomp_req *req) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); if (acomp_req_on_stack(req) && acomp_is_async(tfm)) return -EAGAIN; if (crypto_acomp_req_virt(tfm) || acomp_request_issg(req)) return crypto_acomp_reqtfm(req)->decompress(req); return acomp_do_req_chain(req, false); } EXPORT_SYMBOL_GPL(crypto_acomp_decompress); void comp_prepare_alg(struct comp_alg_common *alg) { struct crypto_alg *base = &alg->base; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; } int crypto_register_acomp(struct acomp_alg *alg) { struct crypto_alg *base = &alg->calg.base; comp_prepare_alg(&alg->calg); base->cra_type = &crypto_acomp_type; base->cra_flags |= CRYPTO_ALG_TYPE_ACOMPRESS; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_acomp); void crypto_unregister_acomp(struct acomp_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_acomp); int crypto_register_acomps(struct acomp_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_acomp(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_acomp(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_acomps); void crypto_unregister_acomps(struct acomp_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_acomp(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_acomps); static void acomp_stream_workfn(struct work_struct *work) { struct crypto_acomp_streams *s = container_of(work, struct crypto_acomp_streams, stream_work); struct crypto_acomp_stream __percpu *streams = s->streams; int cpu; for_each_cpu(cpu, &s->stream_want) { struct crypto_acomp_stream *ps; void *ctx; ps = per_cpu_ptr(streams, cpu); if (ps->ctx) continue; ctx = s->alloc_ctx(); if (IS_ERR(ctx)) break; spin_lock_bh(&ps->lock); ps->ctx = ctx; spin_unlock_bh(&ps->lock); cpumask_clear_cpu(cpu, &s->stream_want); } } void crypto_acomp_free_streams(struct crypto_acomp_streams *s) { struct crypto_acomp_stream __percpu *streams = s->streams; void (*free_ctx)(void *); int i; s->streams = NULL; if (!streams) return; cancel_work_sync(&s->stream_work); free_ctx = s->free_ctx; for_each_possible_cpu(i) { struct crypto_acomp_stream *ps = per_cpu_ptr(streams, i); if (!ps->ctx) continue; free_ctx(ps->ctx); } free_percpu(streams); } EXPORT_SYMBOL_GPL(crypto_acomp_free_streams); int crypto_acomp_alloc_streams(struct crypto_acomp_streams *s) { struct crypto_acomp_stream __percpu *streams; struct crypto_acomp_stream *ps; unsigned int i; void *ctx; if (s->streams) return 0; streams = alloc_percpu(struct crypto_acomp_stream); if (!streams) return -ENOMEM; ctx = s->alloc_ctx(); if (IS_ERR(ctx)) { free_percpu(streams); return PTR_ERR(ctx); } i = cpumask_first(cpu_possible_mask); ps = per_cpu_ptr(streams, i); ps->ctx = ctx; for_each_possible_cpu(i) { ps = per_cpu_ptr(streams, i); spin_lock_init(&ps->lock); } s->streams = streams; INIT_WORK(&s->stream_work, acomp_stream_workfn); return 0; } EXPORT_SYMBOL_GPL(crypto_acomp_alloc_streams); struct crypto_acomp_stream *crypto_acomp_lock_stream_bh( struct crypto_acomp_streams *s) __acquires(stream) { struct crypto_acomp_stream __percpu *streams = s->streams; int cpu = raw_smp_processor_id(); struct crypto_acomp_stream *ps; ps = per_cpu_ptr(streams, cpu); spin_lock_bh(&ps->lock); if (likely(ps->ctx)) return ps; spin_unlock(&ps->lock); cpumask_set_cpu(cpu, &s->stream_want); schedule_work(&s->stream_work); ps = per_cpu_ptr(streams, cpumask_first(cpu_possible_mask)); spin_lock(&ps->lock); return ps; } EXPORT_SYMBOL_GPL(crypto_acomp_lock_stream_bh); void acomp_walk_done_src(struct acomp_walk *walk, int used) { walk->slen -= used; if ((walk->flags & ACOMP_WALK_SRC_LINEAR)) scatterwalk_advance(&walk->in, used); else scatterwalk_done_src(&walk->in, used); if ((walk->flags & ACOMP_WALK_SLEEP)) cond_resched(); } EXPORT_SYMBOL_GPL(acomp_walk_done_src); void acomp_walk_done_dst(struct acomp_walk *walk, int used) { walk->dlen -= used; if ((walk->flags & ACOMP_WALK_DST_LINEAR)) scatterwalk_advance(&walk->out, used); else scatterwalk_done_dst(&walk->out, used); if ((walk->flags & ACOMP_WALK_SLEEP)) cond_resched(); } EXPORT_SYMBOL_GPL(acomp_walk_done_dst); int acomp_walk_next_src(struct acomp_walk *walk) { unsigned int slen = walk->slen; unsigned int max = UINT_MAX; if (!preempt_model_preemptible() && (walk->flags & ACOMP_WALK_SLEEP)) max = PAGE_SIZE; if ((walk->flags & ACOMP_WALK_SRC_LINEAR)) { walk->in.__addr = (void *)(((u8 *)walk->in.sg) + walk->in.offset); return min(slen, max); } return slen ? scatterwalk_next(&walk->in, slen) : 0; } EXPORT_SYMBOL_GPL(acomp_walk_next_src); int acomp_walk_next_dst(struct acomp_walk *walk) { unsigned int dlen = walk->dlen; unsigned int max = UINT_MAX; if (!preempt_model_preemptible() && (walk->flags & ACOMP_WALK_SLEEP)) max = PAGE_SIZE; if ((walk->flags & ACOMP_WALK_DST_LINEAR)) { walk->out.__addr = (void *)(((u8 *)walk->out.sg) + walk->out.offset); return min(dlen, max); } return dlen ? scatterwalk_next(&walk->out, dlen) : 0; } EXPORT_SYMBOL_GPL(acomp_walk_next_dst); int acomp_walk_virt(struct acomp_walk *__restrict walk, struct acomp_req *__restrict req, bool atomic) { struct scatterlist *src = req->src; struct scatterlist *dst = req->dst; walk->slen = req->slen; walk->dlen = req->dlen; if (!walk->slen || !walk->dlen) return -EINVAL; walk->flags = 0; if ((req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) && !atomic) walk->flags |= ACOMP_WALK_SLEEP; if ((req->base.flags & CRYPTO_ACOMP_REQ_SRC_VIRT)) walk->flags |= ACOMP_WALK_SRC_LINEAR; if ((req->base.flags & CRYPTO_ACOMP_REQ_DST_VIRT)) walk->flags |= ACOMP_WALK_DST_LINEAR; if ((walk->flags & ACOMP_WALK_SRC_LINEAR)) { walk->in.sg = (void *)req->svirt; walk->in.offset = 0; } else scatterwalk_start(&walk->in, src); if ((walk->flags & ACOMP_WALK_DST_LINEAR)) { walk->out.sg = (void *)req->dvirt; walk->out.offset = 0; } else scatterwalk_start(&walk->out, dst); return 0; } EXPORT_SYMBOL_GPL(acomp_walk_virt); struct acomp_req *acomp_request_clone(struct acomp_req *req, size_t total, gfp_t gfp) { struct acomp_req *nreq; nreq = container_of(crypto_request_clone(&req->base, total, gfp), struct acomp_req, base); if (nreq == req) return req; if (req->src == &req->chain.ssg) nreq->src = &nreq->chain.ssg; if (req->dst == &req->chain.dsg) nreq->dst = &nreq->chain.dsg; return nreq; } EXPORT_SYMBOL_GPL(acomp_request_clone); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Asynchronous compression type"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> struct ip_tunnel_info; #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_IPV4 4 /* IPv4 in IPv6 */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; /* * Jumbo payload option, as described in RFC 2675 2. */ struct hop_jumbo_hdr { u8 nexthdr; u8 hdrlen; u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ u8 tlv_len; /* 4 */ __be32 jumbo_payload_len; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _field = (field); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, _field, _val); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, _field, _val);\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, _val); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, _val);\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __u16 gso_size; __s8 dontfrag; struct ipv6_txoptions *opt; }; static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; sockcm_init(&ipc6->sockc, sk); } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } #if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } #endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct sock *sk); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); static inline struct ipv6_txoptions * ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { if (!opt) return NULL; return __ipv6_fixup_options(opt_space, opt); } bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); /* This helper is specialized for BIG TCP needs. * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. * It assumes headers are already in skb->head. * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there. */ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) { const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) return 0; if (skb_network_offset(skb) + sizeof(struct ipv6hdr) + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) return 0; nhdr = ipv6_hdr(skb); if (nhdr->nexthdr != NEXTHDR_HOP) return 0; jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || jhdr->nexthdr != IPPROTO_TCP) return 0; return jhdr->nexthdr; } /* Return 0 if HBH header is successfully removed * Or if HBH removal is unnecessary (packet is not big TCP) * Return error to indicate dropping the packet */ static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb) { const int hophdr_len = sizeof(struct hop_jumbo_hdr); int nexthdr = ipv6_has_hopopt_jumbo(skb); struct ipv6hdr *h6; if (!nexthdr) return 0; if (skb_cow_head(skb, 0)) return -1; /* Remove the HBH header. * Layout: [Ethernet header][IPv6 header][HBH][L4 Header] */ memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb), skb_network_header(skb) - skb_mac_header(skb) + sizeof(struct ipv6hdr)); __skb_pull(skb, hophdr_len); skb->network_header += hophdr_len; skb->mac_header += hophdr_len; h6 = ipv6_hdr(skb); h6->nexthdr = nexthdr; return 0; } static inline bool ipv6_accept_ra(const struct inet6_dev *idev) { s32 accept_ra = READ_ONCE(idev->cnf.accept_ra); /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return READ_ONCE(idev->cnf.forwarding) ? accept_ra == 2 : accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { return jhash2((__force const u32 *)a->s6_addr32, ARRAY_SIZE(a->s6_addr32), initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = READ_ONCE(np->mcast_hops); else hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (net->ipv6.sysctl.flowlabel_state_ranges) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { switch (net->ipv6.sysctl.auto_flowlabels) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return net->ipv6.sysctl.multipath_hash_fields; } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline dscp_t ip6_dscp(__be32 flowinfo) { return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr_p, struct in6_addr *saddr); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); /* * socket options (ipv6_sockglue.c) */ DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); /* * reassembly.c */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); void ac6_proc_exit(struct net *net); int raw6_proc_init(void); void raw6_proc_exit(void); int tcp6_proc_init(struct net *net); void tcp6_proc_exit(struct net *net); int udp6_proc_init(struct net *net); void udp6_proc_exit(struct net *net); int udplite6_proc_init(void); void udplite6_proc_exit(void); int ipv6_misc_proc_init(void); void ipv6_misc_proc_exit(void); int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); #else static inline int ac6_proc_init(struct net *net) { return 0; } static inline void ac6_proc_exit(struct net *net) { } static inline int snmp6_register_dev(struct inet6_dev *idev) { return 0; } static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); size_t ipv6_icmp_sysctl_table_size(void); struct ctl_table *ipv6_route_sysctl_init(struct net *net); size_t ipv6_route_sysctl_table_size(struct net *net); int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); static inline int ip6_sock_set_v6only(struct sock *sk) { if (inet_sk(sk)->inet_num) return -EINVAL; lock_sock(sk); sk->sk_ipv6only = true; release_sock(sk); return 0; } static inline void ip6_sock_set_recverr(struct sock *sk) { inet6_set_bit(RECVERR6, sk); } #define IPV6_PREFER_SRC_MASK (IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBLIC | \ IPV6_PREFER_SRC_COA) static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val) { unsigned int prefmask = ~IPV6_PREFER_SRC_MASK; unsigned int pref = 0; /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ switch (val & (IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { case IPV6_PREFER_SRC_PUBLIC: pref |= IPV6_PREFER_SRC_PUBLIC; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_TMP: pref |= IPV6_PREFER_SRC_TMP; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_PUBTMP_DEFAULT: prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case 0: break; default: return -EINVAL; } /* check HOME/COA conflicts */ switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) { case IPV6_PREFER_SRC_HOME: prefmask &= ~IPV6_PREFER_SRC_COA; break; case IPV6_PREFER_SRC_COA: pref |= IPV6_PREFER_SRC_COA; break; case 0: break; default: return -EINVAL; } /* check CGA/NONCGA conflicts */ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { case IPV6_PREFER_SRC_CGA: case IPV6_PREFER_SRC_NONCGA: case 0: break; default: return -EINVAL; } WRITE_ONCE(inet6_sk(sk)->srcprefs, (READ_ONCE(inet6_sk(sk)->srcprefs) & prefmask) | pref); return 0; } static inline void ip6_sock_set_recvpktinfo(struct sock *sk) { lock_sock(sk); inet6_sk(sk)->rxopt.bits.rxinfo = true; release_sock(sk); } #define IPV6_ADDR_WORDS 4 static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) { cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); } static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) { be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); } #endif /* _NET_IPV6_H */ |
| 36 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/nfs_fs.h * * Copyright (C) 1992 Rick Sladkey * * OS-specific nfs filesystem definitions and declarations */ #ifndef _LINUX_NFS_FS_H #define _LINUX_NFS_FS_H #include <uapi/linux/nfs_fs.h> /* * Enable dprintk() debugging support for nfs client. */ #ifdef CONFIG_NFS_DEBUG # define NFS_DEBUG #endif #include <linux/in.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/rwsem.h> #include <linux/wait.h> #include <linux/sunrpc/debug.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/clnt.h> #ifdef CONFIG_NFS_FSCACHE #include <linux/netfs.h> #endif #include <linux/nfs.h> #include <linux/nfs2.h> #include <linux/nfs3.h> #include <linux/nfs4.h> #include <linux/nfs_xdr.h> #include <linux/nfs_fs_sb.h> #include <linux/mempool.h> /* * These are the default for number of transports to different server IPs */ #define NFS_MAX_TRANSPORTS 16 /* * Size of the NFS directory verifier */ #define NFS_DIR_VERIFIER_SIZE 2 /* * NFSv3/v4 Access mode cache entry */ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; kuid_t fsuid; kgid_t fsgid; struct group_info *group_info; u64 timestamp; __u32 mask; struct rcu_head rcu_head; }; struct nfs_lock_context { refcount_t count; struct list_head list; struct nfs_open_context *open_context; fl_owner_t lockowner; atomic_t io_count; struct rcu_head rcu_head; }; struct nfs_file_localio { struct nfsd_file __rcu *ro_file; struct nfsd_file __rcu *rw_file; struct list_head list; void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */ }; static inline void nfs_localio_file_init(struct nfs_file_localio *nfl) { #if IS_ENABLED(CONFIG_NFS_LOCALIO) nfl->ro_file = NULL; nfl->rw_file = NULL; INIT_LIST_HEAD(&nfl->list); nfl->nfs_uuid = NULL; #endif } struct nfs4_state; struct nfs_open_context { struct nfs_lock_context lock_context; fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; int error; unsigned long flags; #define NFS_CONTEXT_BAD (2) #define NFS_CONTEXT_UNLOCK (3) #define NFS_CONTEXT_FILE_OPEN (4) struct nfs4_threshold *mdsthreshold; struct list_head list; struct rcu_head rcu_head; struct nfs_file_localio nfl; }; struct nfs_open_dir_context { struct list_head list; atomic_t cache_hits; atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; bool force_clear; bool eof; struct rcu_head rcu_head; }; /* * NFSv4 delegation */ struct nfs_delegation; struct posix_acl; struct nfs4_xattr_cache; /* * nfs fs inode data in memory */ struct nfs_inode { /* * The 64bit 'inode number' */ __u64 fileid; /* * NFS file handle */ struct nfs_fh fh; /* * Various flags */ unsigned long flags; /* atomic bit ops */ unsigned long cache_validity; /* bit mask */ /* * NFS Attributes not included in struct inode */ struct timespec64 btime; /* * read_cache_jiffies is when we started read-caching this inode. * attrtimeo is for how long the cached information is assumed * to be valid. A successful attribute revalidation doubles * attrtimeo (up to acregmax/acdirmax), a failure resets it to * acregmin/acdirmin. * * We need to revalidate the cached attrs for this inode if * * jiffies - read_cache_jiffies >= attrtimeo * * Please note the comparison is greater than or equal * so that zero timeout values can be specified. */ unsigned long read_cache_jiffies; unsigned long attrtimeo; unsigned long attrtimeo_timestamp; unsigned long attr_gencount; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; union { /* Directory */ struct { /* "Generation counter" for the attribute cache. * This is bumped whenever we update the metadata * on the server. */ unsigned long cache_change_attribute; /* * This is the cookie verifier used for NFSv3 readdir * operations */ __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; /* Readers: in-flight sillydelete RPC calls */ /* Writers: rmdir */ struct rw_semaphore rmdir_sem; }; /* Regular file */ struct { atomic_long_t nrequests; atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; }; }; /* Open contexts for shared mmap writes */ struct list_head open_files; /* Keep track of out-of-order replies. * The ooo array contains start/end pairs of * numbers from the changeid sequence when * the inode's iversion has been updated. * It also contains end/start pair (i.e. reverse order) * of sections of the changeid sequence that have * been seen in replies from the server. * Normally these should match and when both * A:B and B:A are found in ooo, they are both removed. * And if a reply with A:B causes an iversion update * of A:B, then neither are added. * When a reply has pre_change that doesn't match * iversion, then the changeid pair and any consequent * change in iversion ARE added. Later replies * might fill in the gaps, or possibly a gap is caused * by a change from another client. * When a file or directory is opened, if the ooo table * is not empty, then we assume the gaps were due to * another client and we invalidate the cached data. * * We can only track a limited number of concurrent gaps. * Currently that limit is 16. * We allocate the table on demand. If there is insufficient * memory, then we probably cannot cache the file anyway * so there is no loss. */ struct { int cnt; struct { u64 start, end; } gap[16]; } *ooo; #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ struct list_head open_states; struct nfs_delegation __rcu *delegation; struct rw_semaphore rwsem; /* pNFS layout information */ struct pnfs_layout_hdr *layout; #endif /* CONFIG_NFS_V4*/ /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif union { struct inode vfs_inode; #ifdef CONFIG_NFS_FSCACHE struct netfs_inode netfs; /* netfs context and VFS inode */ #endif }; }; struct nfs4_copy_state { struct list_head copies; struct list_head src_copies; nfs4_stateid stateid; struct completion completion; uint64_t count; struct nfs_writeverf verf; int error; int flags; struct nfs4_state *parent_src_state; struct nfs4_state *parent_dst_state; }; /* * Access bit flags */ #define NFS_ACCESS_READ 0x0001 #define NFS_ACCESS_LOOKUP 0x0002 #define NFS_ACCESS_MODIFY 0x0004 #define NFS_ACCESS_EXTEND 0x0008 #define NFS_ACCESS_DELETE 0x0010 #define NFS_ACCESS_EXECUTE 0x0020 #define NFS_ACCESS_XAREAD 0x0040 #define NFS_ACCESS_XAWRITE 0x0080 #define NFS_ACCESS_XALIST 0x0100 /* * Cache validity bit flags */ #define NFS_INO_INVALID_DATA BIT(1) /* cached data is invalid */ #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ #define NFS_INO_INVALID_CTIME BIT(9) /* cached ctime is invalid */ #define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ #define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ #define NFS_INO_DATA_INVAL_DEFER \ BIT(13) /* Deferred cache invalidation */ #define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ #define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */ #define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */ #define NFS_INO_INVALID_BTIME BIT(18) /* cached btime is invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ | NFS_INO_INVALID_MTIME \ | NFS_INO_INVALID_BTIME \ | NFS_INO_INVALID_SIZE \ | NFS_INO_INVALID_NLINK \ | NFS_INO_INVALID_MODE \ | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* * Bit offsets in flags field */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ #define NFS_INO_ODIRECT (12) /* I/O setting is O_DIRECT */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { return container_of(inode, struct nfs_inode, vfs_inode); } static inline struct nfs_server *NFS_SB(const struct super_block *s) { return (struct nfs_server *)(s->s_fs_info); } static inline struct nfs_fh *NFS_FH(const struct inode *inode) { return &NFS_I(inode)->fh; } static inline struct nfs_server *NFS_SERVER(const struct inode *inode) { return NFS_SB(inode->i_sb); } static inline struct rpc_clnt *NFS_CLIENT(const struct inode *inode) { return NFS_SERVER(inode)->client; } static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode) { return NFS_SERVER(inode)->nfs_client->rpc_ops; } static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); return S_ISDIR(inode->i_mode) ? nfss->acdirmin : nfss->acregmin; } static inline unsigned NFS_MAXATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); return S_ISDIR(inode->i_mode) ? nfss->acdirmax : nfss->acregmax; } static inline int NFS_STALE(const struct inode *inode) { return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; } static inline void set_nfs_fileid(struct inode *inode, __u64 fileid) { NFS_I(inode)->fileid = fileid; } static inline void nfs_mark_for_revalidate(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } /** * nfs_save_change_attribute - Returns the inode attribute change cookie * @dir - pointer to parent directory inode * The "cache change attribute" is updated when we need to revalidate * our dentry cache after a directory was seen to change on the server. */ static inline unsigned long nfs_save_change_attribute(struct inode *dir) { return NFS_I(dir)->cache_change_attribute; } /* * linux/fs/nfs/inode.c */ extern int nfs_sync_mapping(struct address_space *mapping); extern void nfs_zap_mapping(struct inode *inode, struct address_space *mapping); extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct mnt_idmap *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp); extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); extern void nfs_file_clear_open_context(struct file *flip); extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx); extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); extern u64 nfs_compat_user_ino64(u64 fileid); extern void nfs_fattr_init(struct nfs_fattr *fattr); extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); static inline void nfs4_label_free(struct nfs4_label *label) { #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (label) { kfree(label->label); kfree(label); } #endif } static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { if (fattr) nfs4_label_free(fattr->label); kfree(fattr); } extern struct nfs_fh *nfs_alloc_fhandle(void); static inline void nfs_free_fhandle(const struct nfs_fh *fh) { kfree(fh); } #ifdef NFS_DEBUG extern u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh); static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh) { return _nfs_display_fhandle_hash(fh); } extern void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption); #define nfs_display_fhandle(fh, caption) \ do { \ if (unlikely(nfs_debug & NFSDBG_FACILITY)) \ _nfs_display_fhandle(fh, caption); \ } while (0) #else static inline u32 nfs_display_fhandle_hash(const struct nfs_fh *fh) { return 0; } static inline void nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { } #endif /* * linux/fs/nfs/nfsroot.c */ extern int nfs_root_data(char **root_device, char **root_data); /*__init*/ /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern __be32 root_nfs_parse_addr(char *name); /*__init*/ /* * linux/fs/nfs/file.c */ extern const struct file_operations nfs_file_operations; #if IS_ENABLED(CONFIG_NFS_V4) extern const struct file_operations nfs4_file_operations; #endif /* CONFIG_NFS_V4 */ extern const struct address_space_operations nfs_file_aops; extern const struct address_space_operations nfs_dir_aops; static inline struct nfs_open_context *nfs_file_open_context(struct file *filp) { return filp->private_data; } static inline const struct cred *nfs_file_cred(struct file *file) { if (file != NULL) { struct nfs_open_context *ctx = nfs_file_open_context(file); if (ctx) return ctx->cred; } return NULL; } /* * linux/fs/nfs/direct.c */ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c */ extern const struct file_operations nfs_dir_operations; extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); #if IS_ENABLED(CONFIG_NFS_V4) extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block); extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, struct file *file, unsigned int open_flags, umode_t mode); /* * linux/fs/nfs/symlink.c */ extern const struct inode_operations nfs_symlink_inode_operations; /* * linux/fs/nfs/sysctl.c */ #ifdef CONFIG_SYSCTL extern int nfs_register_sysctl(void); extern void nfs_unregister_sysctl(void); #else #define nfs_register_sysctl() 0 #define nfs_unregister_sysctl() do { } while(0) #endif /* * linux/fs/nfs/namespace.c */ extern const struct inode_operations nfs_mountpoint_inode_operations; extern const struct inode_operations nfs_referral_inode_operations; extern int nfs_mountpoint_expiry_timeout; extern void nfs_release_automount_timer(void); /* * linux/fs/nfs/unlink.c */ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *); /* * linux/fs/nfs/write.c */ extern int nfs_congestion_kb; extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct folio *folio); extern int nfs_update_folio(struct file *file, struct folio *folio, unsigned int offset, unsigned int count); /* * Try to write back everything synchronously (but check the * return value!) */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; return false; } /* * linux/fs/nfs/read.c */ int nfs_read_folio(struct file *, struct folio *); void nfs_readahead(struct readahead_control *); /* * inline functions */ static inline loff_t nfs_size_to_loff_t(__u64 size) { return min_t(u64, size, OFFSET_MAX); } static inline ino_t nfs_fileid_to_ino_t(u64 fileid) { ino_t ino = (ino_t) fileid; if (sizeof(ino_t) < sizeof(u64)) ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8; return ino; } static inline void nfs_ooo_clear(struct nfs_inode *nfsi) { nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; kfree(nfsi->ooo); nfsi->ooo = NULL; } static inline bool nfs_ooo_test(struct nfs_inode *nfsi) { return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || (nfsi->ooo && nfsi->ooo->cnt > 0); } #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. * If it is opened *before* we decide to unlink, we will silly-rename * instead. If it is opened *after*, then we need to create or will fail. * If we allow the two to race, we could end up with a file that is open * but deleted on the server resulting in ESTALE. * So use ->d_fsdata to record when the unlink is happening * and block dentry revalidation while it is set. */ #define NFS_FSDATA_BLOCKED ((void*)1) # undef ifdebug # ifdef NFS_DEBUG # define ifdebug(fac) if (unlikely(nfs_debug & NFSDBG_##fac)) # define NFS_IFDEBUG(x) x # else # define ifdebug(fac) if (0) # define NFS_IFDEBUG(x) # endif #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * AEAD: Authenticated Encryption with Associated Data * * This file provides API support for AEAD algorithms. * * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/aead.h> #include <linux/cryptouser.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/string_choices.h> #include <net/netlink.h> #include "internal.h" static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key, unsigned int keylen) { unsigned long alignmask = crypto_aead_alignmask(tfm); int ret; u8 *buffer, *alignbuffer; unsigned long absize; absize = keylen + alignmask; buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = crypto_aead_alg(tfm)->setkey(tfm, alignbuffer, keylen); kfree_sensitive(buffer); return ret; } int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen) { unsigned long alignmask = crypto_aead_alignmask(tfm); int err; if ((unsigned long)key & alignmask) err = setkey_unaligned(tfm, key, keylen); else err = crypto_aead_alg(tfm)->setkey(tfm, key, keylen); if (unlikely(err)) { crypto_aead_set_flags(tfm, CRYPTO_TFM_NEED_KEY); return err; } crypto_aead_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); return 0; } EXPORT_SYMBOL_GPL(crypto_aead_setkey); int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize) { int err; if ((!authsize && crypto_aead_maxauthsize(tfm)) || authsize > crypto_aead_maxauthsize(tfm)) return -EINVAL; if (crypto_aead_alg(tfm)->setauthsize) { err = crypto_aead_alg(tfm)->setauthsize(tfm, authsize); if (err) return err; } tfm->authsize = authsize; return 0; } EXPORT_SYMBOL_GPL(crypto_aead_setauthsize); int crypto_aead_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_aead_alg(aead)->encrypt(req); } EXPORT_SYMBOL_GPL(crypto_aead_encrypt); int crypto_aead_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (req->cryptlen < crypto_aead_authsize(aead)) return -EINVAL; return crypto_aead_alg(aead)->decrypt(req); } EXPORT_SYMBOL_GPL(crypto_aead_decrypt); static void crypto_aead_exit_tfm(struct crypto_tfm *tfm) { struct crypto_aead *aead = __crypto_aead_cast(tfm); struct aead_alg *alg = crypto_aead_alg(aead); alg->exit(aead); } static int crypto_aead_init_tfm(struct crypto_tfm *tfm) { struct crypto_aead *aead = __crypto_aead_cast(tfm); struct aead_alg *alg = crypto_aead_alg(aead); crypto_aead_set_flags(aead, CRYPTO_TFM_NEED_KEY); aead->authsize = alg->maxauthsize; if (alg->exit) aead->base.exit = crypto_aead_exit_tfm; if (alg->init) return alg->init(aead); return 0; } static int __maybe_unused crypto_aead_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_aead raead; struct aead_alg *aead = container_of(alg, struct aead_alg, base); memset(&raead, 0, sizeof(raead)); strscpy(raead.type, "aead", sizeof(raead.type)); strscpy(raead.geniv, "<none>", sizeof(raead.geniv)); raead.blocksize = alg->cra_blocksize; raead.maxauthsize = aead->maxauthsize; raead.ivsize = aead->ivsize; return nla_put(skb, CRYPTOCFGA_REPORT_AEAD, sizeof(raead), &raead); } static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg) { struct aead_alg *aead = container_of(alg, struct aead_alg, base); seq_printf(m, "type : aead\n"); seq_printf(m, "async : %s\n", str_yes_no(alg->cra_flags & CRYPTO_ALG_ASYNC)); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "ivsize : %u\n", aead->ivsize); seq_printf(m, "maxauthsize : %u\n", aead->maxauthsize); seq_printf(m, "geniv : <none>\n"); } static void crypto_aead_free_instance(struct crypto_instance *inst) { struct aead_instance *aead = aead_instance(inst); aead->free(aead); } static const struct crypto_type crypto_aead_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_aead_init_tfm, .free = crypto_aead_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_aead_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_aead_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_AEAD, .tfmsize = offsetof(struct crypto_aead, base), .algsize = offsetof(struct aead_alg, base), }; int crypto_grab_aead(struct crypto_aead_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_aead_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_aead); struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_aead_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_aead); int crypto_has_aead(const char *alg_name, u32 type, u32 mask) { return crypto_type_has_alg(alg_name, &crypto_aead_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_has_aead); static int aead_prepare_alg(struct aead_alg *alg) { struct crypto_alg *base = &alg->base; if (max3(alg->maxauthsize, alg->ivsize, alg->chunksize) > PAGE_SIZE / 8) return -EINVAL; if (!alg->chunksize) alg->chunksize = base->cra_blocksize; base->cra_type = &crypto_aead_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_AEAD; return 0; } int crypto_register_aead(struct aead_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = aead_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_aead); void crypto_unregister_aead(struct aead_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_aead); int crypto_register_aeads(struct aead_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_aead(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_aead(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_aeads); void crypto_unregister_aeads(struct aead_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_aead(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_aeads); int aead_register_instance(struct crypto_template *tmpl, struct aead_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = aead_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, aead_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(aead_register_instance); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Authenticated Encryption with Associated Data (AEAD)"); |
| 2 2 1 1 2 1 1 20 20 4 13 3 4 1 2 1 1 1 2 1 2 1 1 1 1 2 13 1 4 5 6 2 8 8 2 5 7 4 1 2 3 1 2 8 1 2 1 4 3 1 1 9 1 1 1 35 23 11 2 2 2 2 2 15 2 17 17 36 36 36 36 36 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/fs_context.c * * Copyright (C) 1992 Rick Sladkey * Conversion to new mount api Copyright (C) David Howells * * NFS mount handling. * * Split from fs/nfs/super.c by David Howells <dhowells@redhat.com> */ #include <linux/compat.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <net/handshake.h> #include "nfs.h" #include "internal.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_MOUNT #if IS_ENABLED(CONFIG_NFS_V3) #define NFS_DEFAULT_VERSION 3 #else #define NFS_DEFAULT_VERSION 2 #endif #define NFS_MAX_CONNECTIONS 16 enum nfs_param { Opt_ac, Opt_acdirmax, Opt_acdirmin, Opt_acl, Opt_acregmax, Opt_acregmin, Opt_actimeo, Opt_addr, Opt_bg, Opt_bsize, Opt_clientaddr, Opt_cto, Opt_alignwrite, Opt_fatal_neterrors, Opt_fg, Opt_fscache, Opt_fscache_flag, Opt_hard, Opt_intr, Opt_local_lock, Opt_lock, Opt_lookupcache, Opt_migration, Opt_minorversion, Opt_mountaddr, Opt_mounthost, Opt_mountport, Opt_mountproto, Opt_mountvers, Opt_namelen, Opt_nconnect, Opt_max_connect, Opt_port, Opt_posix, Opt_proto, Opt_rdirplus, Opt_rdirplus_none, Opt_rdirplus_force, Opt_rdma, Opt_resvport, Opt_retrans, Opt_retry, Opt_rsize, Opt_sec, Opt_sharecache, Opt_sloppy, Opt_soft, Opt_softerr, Opt_softreval, Opt_source, Opt_tcp, Opt_timeo, Opt_trunkdiscovery, Opt_udp, Opt_v, Opt_vers, Opt_wsize, Opt_write, Opt_xprtsec, Opt_cert_serial, Opt_privkey_serial, }; enum { Opt_fatal_neterrors_default, Opt_fatal_neterrors_enetunreach, Opt_fatal_neterrors_none, }; static const struct constant_table nfs_param_enums_fatal_neterrors[] = { { "default", Opt_fatal_neterrors_default }, { "ENETDOWN:ENETUNREACH", Opt_fatal_neterrors_enetunreach }, { "ENETUNREACH:ENETDOWN", Opt_fatal_neterrors_enetunreach }, { "none", Opt_fatal_neterrors_none }, {} }; enum { Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_none, Opt_local_lock_posix, }; static const struct constant_table nfs_param_enums_local_lock[] = { { "all", Opt_local_lock_all }, { "flock", Opt_local_lock_flock }, { "posix", Opt_local_lock_posix }, { "none", Opt_local_lock_none }, {} }; enum { Opt_lookupcache_all, Opt_lookupcache_none, Opt_lookupcache_positive, }; static const struct constant_table nfs_param_enums_lookupcache[] = { { "all", Opt_lookupcache_all }, { "none", Opt_lookupcache_none }, { "pos", Opt_lookupcache_positive }, { "positive", Opt_lookupcache_positive }, {} }; enum { Opt_write_lazy, Opt_write_eager, Opt_write_wait, }; static const struct constant_table nfs_param_enums_write[] = { { "lazy", Opt_write_lazy }, { "eager", Opt_write_eager }, { "wait", Opt_write_wait }, {} }; static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag_no("ac", Opt_ac), fsparam_u32 ("acdirmax", Opt_acdirmax), fsparam_u32 ("acdirmin", Opt_acdirmin), fsparam_flag_no("acl", Opt_acl), fsparam_u32 ("acregmax", Opt_acregmax), fsparam_u32 ("acregmin", Opt_acregmin), fsparam_u32 ("actimeo", Opt_actimeo), fsparam_string("addr", Opt_addr), fsparam_flag ("bg", Opt_bg), fsparam_u32 ("bsize", Opt_bsize), fsparam_string("clientaddr", Opt_clientaddr), fsparam_flag_no("cto", Opt_cto), fsparam_flag_no("alignwrite", Opt_alignwrite), fsparam_enum("fatal_neterrors", Opt_fatal_neterrors, nfs_param_enums_fatal_neterrors), fsparam_flag ("fg", Opt_fg), fsparam_flag_no("fsc", Opt_fscache_flag), fsparam_string("fsc", Opt_fscache), fsparam_flag ("hard", Opt_hard), __fsparam(NULL, "intr", Opt_intr, fs_param_neg_with_no|fs_param_deprecated, NULL), fsparam_enum ("local_lock", Opt_local_lock, nfs_param_enums_local_lock), fsparam_flag_no("lock", Opt_lock), fsparam_enum ("lookupcache", Opt_lookupcache, nfs_param_enums_lookupcache), fsparam_flag_no("migration", Opt_migration), fsparam_u32 ("minorversion", Opt_minorversion), fsparam_string("mountaddr", Opt_mountaddr), fsparam_string("mounthost", Opt_mounthost), fsparam_u32 ("mountport", Opt_mountport), fsparam_string("mountproto", Opt_mountproto), fsparam_u32 ("mountvers", Opt_mountvers), fsparam_u32 ("namlen", Opt_namelen), fsparam_u32 ("nconnect", Opt_nconnect), fsparam_u32 ("max_connect", Opt_max_connect), fsparam_string("nfsvers", Opt_vers), fsparam_u32 ("port", Opt_port), fsparam_flag_no("posix", Opt_posix), fsparam_string("proto", Opt_proto), fsparam_flag_no("rdirplus", Opt_rdirplus), // rdirplus|nordirplus fsparam_string("rdirplus", Opt_rdirplus), // rdirplus=... fsparam_flag ("rdma", Opt_rdma), fsparam_flag_no("resvport", Opt_resvport), fsparam_u32 ("retrans", Opt_retrans), fsparam_string("retry", Opt_retry), fsparam_u32 ("rsize", Opt_rsize), fsparam_string("sec", Opt_sec), fsparam_flag_no("sharecache", Opt_sharecache), fsparam_flag ("sloppy", Opt_sloppy), fsparam_flag ("soft", Opt_soft), fsparam_flag ("softerr", Opt_softerr), fsparam_flag ("softreval", Opt_softreval), fsparam_string("source", Opt_source), fsparam_flag ("tcp", Opt_tcp), fsparam_u32 ("timeo", Opt_timeo), fsparam_flag_no("trunkdiscovery", Opt_trunkdiscovery), fsparam_flag ("udp", Opt_udp), fsparam_flag ("v2", Opt_v), fsparam_flag ("v3", Opt_v), fsparam_flag ("v4", Opt_v), fsparam_flag ("v4.0", Opt_v), fsparam_flag ("v4.1", Opt_v), fsparam_flag ("v4.2", Opt_v), fsparam_string("vers", Opt_vers), fsparam_enum ("write", Opt_write, nfs_param_enums_write), fsparam_u32 ("wsize", Opt_wsize), fsparam_string("xprtsec", Opt_xprtsec), fsparam_s32("cert_serial", Opt_cert_serial), fsparam_s32("privkey_serial", Opt_privkey_serial), {} }; enum { Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0, Opt_vers_4_1, Opt_vers_4_2, }; static const struct constant_table nfs_vers_tokens[] = { { "2", Opt_vers_2 }, { "3", Opt_vers_3 }, { "4", Opt_vers_4 }, { "4.0", Opt_vers_4_0 }, { "4.1", Opt_vers_4_1 }, { "4.2", Opt_vers_4_2 }, {} }; enum { Opt_xprt_rdma, Opt_xprt_rdma6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_udp, Opt_xprt_udp6, nr__Opt_xprt }; static const struct constant_table nfs_xprt_protocol_tokens[] = { { "rdma", Opt_xprt_rdma }, { "rdma6", Opt_xprt_rdma6 }, { "tcp", Opt_xprt_tcp }, { "tcp6", Opt_xprt_tcp6 }, { "udp", Opt_xprt_udp }, { "udp6", Opt_xprt_udp6 }, {} }; enum { Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p, Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp, Opt_sec_none, Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp, Opt_sec_sys, nr__Opt_sec }; static const struct constant_table nfs_secflavor_tokens[] = { { "krb5", Opt_sec_krb5 }, { "krb5i", Opt_sec_krb5i }, { "krb5p", Opt_sec_krb5p }, { "lkey", Opt_sec_lkey }, { "lkeyi", Opt_sec_lkeyi }, { "lkeyp", Opt_sec_lkeyp }, { "none", Opt_sec_none }, { "null", Opt_sec_none }, { "spkm3", Opt_sec_spkm }, { "spkm3i", Opt_sec_spkmi }, { "spkm3p", Opt_sec_spkmp }, { "sys", Opt_sec_sys }, {} }; enum { Opt_xprtsec_none, Opt_xprtsec_tls, Opt_xprtsec_mtls, nr__Opt_xprtsec }; static const struct constant_table nfs_xprtsec_policies[] = { { "none", Opt_xprtsec_none }, { "tls", Opt_xprtsec_tls }, { "mtls", Opt_xprtsec_mtls }, {} }; static const struct constant_table nfs_rdirplus_tokens[] = { { "none", Opt_rdirplus_none }, { "force", Opt_rdirplus_force }, {} }; /* * Sanity-check a server address provided by the mount command. * * Address family must be initialized, and address must not be * the ANY address for that family. */ static int nfs_verify_server_address(struct sockaddr_storage *addr) { switch (addr->ss_family) { case AF_INET: { struct sockaddr_in *sa = (struct sockaddr_in *)addr; return sa->sin_addr.s_addr != htonl(INADDR_ANY); } case AF_INET6: { struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; return !ipv6_addr_any(sa); } } return 0; } #ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx) { return true; } #else static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx) { if (ctx->version == 4) return true; return false; } #endif /* * Sanity check the NFS transport protocol. */ static int nfs_validate_transport_protocol(struct fs_context *fc, struct nfs_fs_context *ctx) { switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_UDP: if (nfs_server_transport_udp_invalid(ctx)) goto out_invalid_transport_udp; break; case XPRT_TRANSPORT_TCP: case XPRT_TRANSPORT_RDMA: break; default: ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; } if (ctx->xprtsec.policy != RPC_XPRTSEC_NONE) switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_TCP: ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP_TLS; break; default: goto out_invalid_xprtsec_policy; } return 0; out_invalid_transport_udp: return nfs_invalf(fc, "NFS: Unsupported transport protocol udp"); out_invalid_xprtsec_policy: return nfs_invalf(fc, "NFS: Transport does not support xprtsec"); } /* * For text based NFSv2/v3 mounts, the mount protocol transport default * settings should depend upon the specified NFS transport. */ static void nfs_set_mount_transport_protocol(struct nfs_fs_context *ctx) { if (ctx->mount_server.protocol == XPRT_TRANSPORT_UDP || ctx->mount_server.protocol == XPRT_TRANSPORT_TCP) return; switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_UDP: ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; break; case XPRT_TRANSPORT_TCP: case XPRT_TRANSPORT_RDMA: ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; } } /* * Add 'flavor' to 'auth_info' if not already present. * Returns true if 'flavor' ends up in the list, false otherwise */ static int nfs_auth_info_add(struct fs_context *fc, struct nfs_auth_info *auth_info, rpc_authflavor_t flavor) { unsigned int i; unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors); /* make sure this flavor isn't already in the list */ for (i = 0; i < auth_info->flavor_len; i++) { if (flavor == auth_info->flavors[i]) return 0; } if (auth_info->flavor_len + 1 >= max_flavor_len) return nfs_invalf(fc, "NFS: too many sec= flavors"); auth_info->flavors[auth_info->flavor_len++] = flavor; return 0; } /* * Parse the value of the 'sec=' option. */ static int nfs_parse_security_flavors(struct fs_context *fc, struct fs_parameter *param) { struct nfs_fs_context *ctx = nfs_fc2context(fc); rpc_authflavor_t pseudoflavor; char *string = param->string, *p; int ret; trace_nfs_mount_assign(param->key, string); while ((p = strsep(&string, ":")) != NULL) { if (!*p) continue; switch (lookup_constant(nfs_secflavor_tokens, p, -1)) { case Opt_sec_none: pseudoflavor = RPC_AUTH_NULL; break; case Opt_sec_sys: pseudoflavor = RPC_AUTH_UNIX; break; case Opt_sec_krb5: pseudoflavor = RPC_AUTH_GSS_KRB5; break; case Opt_sec_krb5i: pseudoflavor = RPC_AUTH_GSS_KRB5I; break; case Opt_sec_krb5p: pseudoflavor = RPC_AUTH_GSS_KRB5P; break; case Opt_sec_lkey: pseudoflavor = RPC_AUTH_GSS_LKEY; break; case Opt_sec_lkeyi: pseudoflavor = RPC_AUTH_GSS_LKEYI; break; case Opt_sec_lkeyp: pseudoflavor = RPC_AUTH_GSS_LKEYP; break; case Opt_sec_spkm: pseudoflavor = RPC_AUTH_GSS_SPKM; break; case Opt_sec_spkmi: pseudoflavor = RPC_AUTH_GSS_SPKMI; break; case Opt_sec_spkmp: pseudoflavor = RPC_AUTH_GSS_SPKMP; break; default: return nfs_invalf(fc, "NFS: sec=%s option not recognized", p); } ret = nfs_auth_info_add(fc, &ctx->auth_info, pseudoflavor); if (ret < 0) return ret; } return 0; } static int nfs_parse_xprtsec_policy(struct fs_context *fc, struct fs_parameter *param) { struct nfs_fs_context *ctx = nfs_fc2context(fc); trace_nfs_mount_assign(param->key, param->string); switch (lookup_constant(nfs_xprtsec_policies, param->string, -1)) { case Opt_xprtsec_none: ctx->xprtsec.policy = RPC_XPRTSEC_NONE; break; case Opt_xprtsec_tls: ctx->xprtsec.policy = RPC_XPRTSEC_TLS_ANON; break; case Opt_xprtsec_mtls: ctx->xprtsec.policy = RPC_XPRTSEC_TLS_X509; break; default: return nfs_invalf(fc, "NFS: Unrecognized transport security policy"); } return 0; } static int nfs_parse_version_string(struct fs_context *fc, const char *string) { struct nfs_fs_context *ctx = nfs_fc2context(fc); ctx->flags &= ~NFS_MOUNT_VER3; switch (lookup_constant(nfs_vers_tokens, string, -1)) { case Opt_vers_2: ctx->version = 2; break; case Opt_vers_3: ctx->flags |= NFS_MOUNT_VER3; ctx->version = 3; break; case Opt_vers_4: /* Backward compatibility option. In future, * the mount program should always supply * a NFSv4 minor version number. */ ctx->version = 4; break; case Opt_vers_4_0: ctx->version = 4; ctx->minorversion = 0; break; case Opt_vers_4_1: ctx->version = 4; ctx->minorversion = 1; break; case Opt_vers_4_2: ctx->version = 4; ctx->minorversion = 2; break; default: return nfs_invalf(fc, "NFS: Unsupported NFS version"); } return 0; } #ifdef CONFIG_KEYS static int nfs_tls_key_verify(key_serial_t key_id) { struct key *key = key_lookup(key_id); int error = 0; if (IS_ERR(key)) { pr_err("key id %08x not found\n", key_id); return PTR_ERR(key); } if (test_bit(KEY_FLAG_REVOKED, &key->flags) || test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { pr_err("key id %08x revoked\n", key_id); error = -EKEYREVOKED; } key_put(key); return error; } #else static inline int nfs_tls_key_verify(key_serial_t key_id) { return -ENOENT; } #endif /* CONFIG_KEYS */ /* * Parse a single mount parameter. */ static int nfs_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct nfs_fs_context *ctx = nfs_fc2context(fc); unsigned short protofamily, mountfamily; unsigned int len; int ret, opt; trace_nfs_mount_option(param); opt = fs_parse(fc, nfs_fs_parameters, param, &result); if (opt < 0) return (opt == -ENOPARAM && ctx->sloppy) ? 1 : opt; if (fc->security) ctx->has_sec_mnt_opts = 1; switch (opt) { case Opt_source: if (fc->source) return nfs_invalf(fc, "NFS: Multiple sources not supported"); fc->source = param->string; param->string = NULL; break; /* * boolean options: foo/nofoo */ case Opt_soft: ctx->flags |= NFS_MOUNT_SOFT; ctx->flags &= ~NFS_MOUNT_SOFTERR; break; case Opt_softerr: ctx->flags |= NFS_MOUNT_SOFTERR | NFS_MOUNT_SOFTREVAL; ctx->flags &= ~NFS_MOUNT_SOFT; break; case Opt_hard: ctx->flags &= ~(NFS_MOUNT_SOFT | NFS_MOUNT_SOFTERR | NFS_MOUNT_SOFTREVAL); break; case Opt_softreval: if (result.negated) ctx->flags &= ~NFS_MOUNT_SOFTREVAL; else ctx->flags |= NFS_MOUNT_SOFTREVAL; break; case Opt_posix: if (result.negated) ctx->flags &= ~NFS_MOUNT_POSIX; else ctx->flags |= NFS_MOUNT_POSIX; break; case Opt_cto: if (result.negated) ctx->flags |= NFS_MOUNT_NOCTO; else ctx->flags &= ~NFS_MOUNT_NOCTO; break; case Opt_trunkdiscovery: if (result.negated) ctx->flags &= ~NFS_MOUNT_TRUNK_DISCOVERY; else ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; break; case Opt_alignwrite: if (result.negated) ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE; else ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE; break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; else ctx->flags &= ~NFS_MOUNT_NOAC; break; case Opt_lock: if (result.negated) { ctx->lock_status = NFS_LOCK_NOLOCK; ctx->flags |= NFS_MOUNT_NONLM; ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } else { ctx->lock_status = NFS_LOCK_LOCK; ctx->flags &= ~NFS_MOUNT_NONLM; ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } break; case Opt_udp: ctx->flags &= ~NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_tcp: case Opt_rdma: ctx->flags |= NFS_MOUNT_TCP; /* for side protocols */ ret = xprt_find_transport_ident(param->key); if (ret < 0) goto out_bad_transport; ctx->nfs_server.protocol = ret; break; case Opt_acl: if (result.negated) ctx->flags |= NFS_MOUNT_NOACL; else ctx->flags &= ~NFS_MOUNT_NOACL; break; case Opt_rdirplus: if (result.negated) { ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS; ctx->flags |= NFS_MOUNT_NORDIRPLUS; } else if (!param->string) { ctx->flags &= ~(NFS_MOUNT_NORDIRPLUS | NFS_MOUNT_FORCE_RDIRPLUS); } else { switch (lookup_constant(nfs_rdirplus_tokens, param->string, -1)) { case Opt_rdirplus_none: ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS; ctx->flags |= NFS_MOUNT_NORDIRPLUS; break; case Opt_rdirplus_force: ctx->flags &= ~NFS_MOUNT_NORDIRPLUS; ctx->flags |= NFS_MOUNT_FORCE_RDIRPLUS; break; default: goto out_invalid_value; } } break; case Opt_sharecache: if (result.negated) ctx->flags |= NFS_MOUNT_UNSHARED; else ctx->flags &= ~NFS_MOUNT_UNSHARED; break; case Opt_resvport: if (result.negated) ctx->flags |= NFS_MOUNT_NORESVPORT; else ctx->flags &= ~NFS_MOUNT_NORESVPORT; break; case Opt_fscache_flag: if (result.negated) ctx->options &= ~NFS_OPTION_FSCACHE; else ctx->options |= NFS_OPTION_FSCACHE; kfree(ctx->fscache_uniq); ctx->fscache_uniq = NULL; break; case Opt_fscache: trace_nfs_mount_assign(param->key, param->string); ctx->options |= NFS_OPTION_FSCACHE; kfree(ctx->fscache_uniq); ctx->fscache_uniq = param->string; param->string = NULL; break; case Opt_migration: if (result.negated) ctx->options &= ~NFS_OPTION_MIGRATION; else ctx->options |= NFS_OPTION_MIGRATION; break; /* * options that take numeric values */ case Opt_port: if (result.uint_32 > USHRT_MAX) goto out_of_bounds; ctx->nfs_server.port = result.uint_32; break; case Opt_rsize: ctx->rsize = result.uint_32; break; case Opt_wsize: ctx->wsize = result.uint_32; break; case Opt_bsize: ctx->bsize = result.uint_32; break; case Opt_timeo: if (result.uint_32 < 1 || result.uint_32 > INT_MAX) goto out_of_bounds; ctx->timeo = result.uint_32; break; case Opt_retrans: if (result.uint_32 > INT_MAX) goto out_of_bounds; ctx->retrans = result.uint_32; break; case Opt_acregmin: ctx->acregmin = result.uint_32; break; case Opt_acregmax: ctx->acregmax = result.uint_32; break; case Opt_acdirmin: ctx->acdirmin = result.uint_32; break; case Opt_acdirmax: ctx->acdirmax = result.uint_32; break; case Opt_actimeo: ctx->acregmin = result.uint_32; ctx->acregmax = result.uint_32; ctx->acdirmin = result.uint_32; ctx->acdirmax = result.uint_32; break; case Opt_namelen: ctx->namlen = result.uint_32; break; case Opt_mountport: if (result.uint_32 > USHRT_MAX) goto out_of_bounds; ctx->mount_server.port = result.uint_32; break; case Opt_mountvers: if (result.uint_32 < NFS_MNT_VERSION || result.uint_32 > NFS_MNT3_VERSION) goto out_of_bounds; ctx->mount_server.version = result.uint_32; break; case Opt_minorversion: if (result.uint_32 > NFS4_MAX_MINOR_VERSION) goto out_of_bounds; ctx->minorversion = result.uint_32; break; /* * options that take text values */ case Opt_v: ret = nfs_parse_version_string(fc, param->key + 1); if (ret < 0) return ret; break; case Opt_vers: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); ret = nfs_parse_version_string(fc, param->string); if (ret < 0) return ret; break; case Opt_sec: ret = nfs_parse_security_flavors(fc, param); if (ret < 0) return ret; break; case Opt_xprtsec: ret = nfs_parse_xprtsec_policy(fc, param); if (ret < 0) return ret; break; case Opt_cert_serial: ret = nfs_tls_key_verify(result.int_32); if (ret < 0) return ret; ctx->xprtsec.cert_serial = result.int_32; break; case Opt_privkey_serial: ret = nfs_tls_key_verify(result.int_32); if (ret < 0) return ret; ctx->xprtsec.privkey_serial = result.int_32; break; case Opt_proto: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); protofamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: protofamily = AF_INET6; fallthrough; case Opt_xprt_udp: ctx->flags &= ~NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: protofamily = AF_INET6; fallthrough; case Opt_xprt_tcp: ctx->flags |= NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; break; case Opt_xprt_rdma6: protofamily = AF_INET6; fallthrough; case Opt_xprt_rdma: /* vector side protocols to TCP */ ctx->flags |= NFS_MOUNT_TCP; ret = xprt_find_transport_ident(param->string); if (ret < 0) goto out_bad_transport; ctx->nfs_server.protocol = ret; break; default: goto out_bad_transport; } ctx->protofamily = protofamily; break; case Opt_mountproto: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); mountfamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: mountfamily = AF_INET6; fallthrough; case Opt_xprt_udp: ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: mountfamily = AF_INET6; fallthrough; case Opt_xprt_tcp: ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; break; case Opt_xprt_rdma: /* not used for side protocols */ default: goto out_bad_transport; } ctx->mountfamily = mountfamily; break; case Opt_addr: trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address)); if (len == 0) goto out_invalid_address; ctx->nfs_server.addrlen = len; break; case Opt_clientaddr: trace_nfs_mount_assign(param->key, param->string); kfree(ctx->client_address); ctx->client_address = param->string; param->string = NULL; break; case Opt_mounthost: trace_nfs_mount_assign(param->key, param->string); kfree(ctx->mount_server.hostname); ctx->mount_server.hostname = param->string; param->string = NULL; break; case Opt_mountaddr: trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->mount_server.address, sizeof(ctx->mount_server._address)); if (len == 0) goto out_invalid_address; ctx->mount_server.addrlen = len; break; case Opt_nconnect: trace_nfs_mount_assign(param->key, param->string); if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_CONNECTIONS) goto out_of_bounds; ctx->nfs_server.nconnect = result.uint_32; break; case Opt_max_connect: trace_nfs_mount_assign(param->key, param->string); if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_TRANSPORTS) goto out_of_bounds; ctx->nfs_server.max_connect = result.uint_32; break; case Opt_fatal_neterrors: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_fatal_neterrors_default: if (fc->net_ns != &init_net) ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; else ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL; break; case Opt_fatal_neterrors_enetunreach: ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; break; case Opt_fatal_neterrors_none: ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL; break; default: goto out_invalid_value; } break; case Opt_lookupcache: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_lookupcache_all: ctx->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE); break; case Opt_lookupcache_positive: ctx->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE; ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG; break; case Opt_lookupcache_none: ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE; break; default: goto out_invalid_value; } break; case Opt_local_lock: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_local_lock_all: ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); break; case Opt_local_lock_flock: ctx->flags |= NFS_MOUNT_LOCAL_FLOCK; break; case Opt_local_lock_posix: ctx->flags |= NFS_MOUNT_LOCAL_FCNTL; break; case Opt_local_lock_none: ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); break; default: goto out_invalid_value; } break; case Opt_write: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_write_lazy: ctx->flags &= ~(NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT); break; case Opt_write_eager: ctx->flags |= NFS_MOUNT_WRITE_EAGER; ctx->flags &= ~NFS_MOUNT_WRITE_WAIT; break; case Opt_write_wait: ctx->flags |= NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT; break; default: goto out_invalid_value; } break; /* * Special options */ case Opt_sloppy: ctx->sloppy = true; break; } return 0; out_invalid_value: return nfs_invalf(fc, "NFS: Bad mount option value specified"); out_invalid_address: return nfs_invalf(fc, "NFS: Bad IP address specified"); out_of_bounds: return nfs_invalf(fc, "NFS: Value for '%s' out of range", param->key); out_bad_transport: return nfs_invalf(fc, "NFS: Unrecognized transport protocol"); } /* * Split fc->source into "hostname:export_path". * * The leftmost colon demarks the split between the server's hostname * and the export path. If the hostname starts with a left square * bracket, then it may contain colons. * * Note: caller frees hostname and export path, even on error. */ static int nfs_parse_source(struct fs_context *fc, size_t maxnamlen, size_t maxpathlen) { struct nfs_fs_context *ctx = nfs_fc2context(fc); const char *dev_name = fc->source; size_t len; const char *end; if (unlikely(!dev_name || !*dev_name)) return -EINVAL; /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); if (end == NULL || end[1] != ':') goto out_bad_devname; len = end - dev_name; end++; } else { const char *comma; end = strchr(dev_name, ':'); if (end == NULL) goto out_bad_devname; len = end - dev_name; /* kill possible hostname list: not supported */ comma = memchr(dev_name, ',', len); if (comma) len = comma - dev_name; } if (len > maxnamlen) goto out_hostname; kfree(ctx->nfs_server.hostname); /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kmemdup_nul(dev_name, len, GFP_KERNEL); if (!ctx->nfs_server.hostname) goto out_nomem; len = strlen(++end); if (len > maxpathlen) goto out_path; ctx->nfs_server.export_path = kmemdup_nul(end, len, GFP_KERNEL); if (!ctx->nfs_server.export_path) goto out_nomem; trace_nfs_mount_path(ctx->nfs_server.export_path); return 0; out_bad_devname: return nfs_invalf(fc, "NFS: device name not in host:path format"); out_nomem: nfs_errorf(fc, "NFS: not enough memory to parse device name"); return -ENOMEM; out_hostname: nfs_errorf(fc, "NFS: server hostname too long"); return -ENAMETOOLONG; out_path: nfs_errorf(fc, "NFS: export pathname too long"); return -ENAMETOOLONG; } static inline bool is_remount_fc(struct fs_context *fc) { return fc->root != NULL; } /* * Parse monolithic NFS2/NFS3 mount data * - fills in the mount root filehandle * * For option strings, user space handles the following behaviors: * * + DNS: mapping server host name to IP address ("addr=" option) * * + failure mode: how to behave if a mount request can't be handled * immediately ("fg/bg" option) * * + retry: how often to retry a mount request ("retry=" option) * * + breaking back: trying proto=udp after proto=tcp, v2 after v3, * mountproto=tcp after mountproto=udp, and so on */ static int nfs23_parse_monolithic(struct fs_context *fc, struct nfs_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_fh *mntfh = ctx->mntfh; struct sockaddr_storage *sap = &ctx->nfs_server._address; int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; int ret; if (data == NULL) goto out_no_data; ctx->version = NFS_DEFAULT_VERSION; switch (data->version) { case 1: data->namlen = 0; fallthrough; case 2: data->bsize = 0; fallthrough; case 3: if (data->flags & NFS_MOUNT_VER3) goto out_no_v3; data->root.size = NFS2_FHSIZE; memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); /* Turn off security negotiation */ extra_flags |= NFS_MOUNT_SECFLAVOUR; fallthrough; case 4: if (data->flags & NFS_MOUNT_SECFLAVOUR) goto out_no_sec; fallthrough; case 5: memset(data->context, 0, sizeof(data->context)); fallthrough; case 6: if (data->flags & NFS_MOUNT_VER3) { if (data->root.size > NFS3_FHSIZE || data->root.size == 0) goto out_invalid_fh; mntfh->size = data->root.size; ctx->version = 3; } else { mntfh->size = NFS2_FHSIZE; ctx->version = 2; } memcpy(mntfh->data, data->root.data, mntfh->size); if (mntfh->size < sizeof(mntfh->data)) memset(mntfh->data + mntfh->size, 0, sizeof(mntfh->data) - mntfh->size); /* * for proto == XPRT_TRANSPORT_UDP, which is what uses * to_exponential, implying shift: limit the shift value * to BITS_PER_LONG (majortimeo is unsigned long) */ if (!(data->flags & NFS_MOUNT_TCP)) /* this will be UDP */ if (data->retrans >= 64) /* shift value is too large */ goto out_invalid_data; /* * Translate to nfs_fs_context, which nfs_fill_super * can deal with. */ ctx->flags = data->flags & NFS_MOUNT_FLAGMASK; ctx->flags |= extra_flags; ctx->rsize = data->rsize; ctx->wsize = data->wsize; ctx->timeo = data->timeo; ctx->retrans = data->retrans; ctx->acregmin = data->acregmin; ctx->acregmax = data->acregmax; ctx->acdirmin = data->acdirmin; ctx->acdirmax = data->acdirmax; ctx->need_mount = false; if (!is_remount_fc(fc)) { memcpy(sap, &data->addr, sizeof(data->addr)); ctx->nfs_server.addrlen = sizeof(data->addr); ctx->nfs_server.port = ntohs(data->addr.sin_port); } if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL); if (!ctx->nfs_server.hostname) goto out_nomem; ctx->namlen = data->namlen; ctx->bsize = data->bsize; if (data->flags & NFS_MOUNT_SECFLAVOUR) ctx->selected_flavor = data->pseudoflavor; else ctx->selected_flavor = RPC_AUTH_UNIX; if (!(data->flags & NFS_MOUNT_NONLM)) ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| NFS_MOUNT_LOCAL_FCNTL); else ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK| NFS_MOUNT_LOCAL_FCNTL); /* * The legacy version 6 binary mount data from userspace has a * field used only to transport selinux information into the * kernel. To continue to support that functionality we * have a touch of selinux knowledge here in the NFS code. The * userspace code converted context=blah to just blah so we are * converting back to the full string selinux understands. */ if (data->context[0]){ #ifdef CONFIG_SECURITY_SELINUX int ret; data->context[NFS_MAX_CONTEXT_LEN] = '\0'; ret = vfs_parse_fs_string(fc, "context", data->context); if (ret < 0) return ret; #else return -EINVAL; #endif } break; default: goto generic; } ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; ctx->skip_reconfig_option_check = true; return 0; generic: return generic_parse_monolithic(fc, data); out_no_data: if (is_remount_fc(fc)) { ctx->skip_reconfig_option_check = true; return 0; } return nfs_invalf(fc, "NFS: mount program didn't pass any mount data"); out_no_v3: return nfs_invalf(fc, "NFS: nfs_mount_data version does not support v3"); out_no_sec: return nfs_invalf(fc, "NFS: nfs_mount_data version supports only AUTH_SYS"); out_nomem: return -ENOMEM; out_no_address: return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); out_invalid_fh: return nfs_invalf(fc, "NFS: invalid root filehandle"); out_invalid_data: return nfs_invalf(fc, "NFS: invalid binary mount data"); } #if IS_ENABLED(CONFIG_NFS_V4) struct compat_nfs_string { compat_uint_t len; compat_uptr_t data; }; static inline void compat_nfs_string(struct nfs_string *dst, struct compat_nfs_string *src) { dst->data = compat_ptr(src->data); dst->len = src->len; } struct compat_nfs4_mount_data_v1 { compat_int_t version; compat_int_t flags; compat_int_t rsize; compat_int_t wsize; compat_int_t timeo; compat_int_t retrans; compat_int_t acregmin; compat_int_t acregmax; compat_int_t acdirmin; compat_int_t acdirmax; struct compat_nfs_string client_addr; struct compat_nfs_string mnt_path; struct compat_nfs_string hostname; compat_uint_t host_addrlen; compat_uptr_t host_addr; compat_int_t proto; compat_int_t auth_flavourlen; compat_uptr_t auth_flavours; }; static void nfs4_compat_mount_data_conv(struct nfs4_mount_data *data) { struct compat_nfs4_mount_data_v1 *compat = (struct compat_nfs4_mount_data_v1 *)data; /* copy the fields backwards */ data->auth_flavours = compat_ptr(compat->auth_flavours); data->auth_flavourlen = compat->auth_flavourlen; data->proto = compat->proto; data->host_addr = compat_ptr(compat->host_addr); data->host_addrlen = compat->host_addrlen; compat_nfs_string(&data->hostname, &compat->hostname); compat_nfs_string(&data->mnt_path, &compat->mnt_path); compat_nfs_string(&data->client_addr, &compat->client_addr); data->acdirmax = compat->acdirmax; data->acdirmin = compat->acdirmin; data->acregmax = compat->acregmax; data->acregmin = compat->acregmin; data->retrans = compat->retrans; data->timeo = compat->timeo; data->wsize = compat->wsize; data->rsize = compat->rsize; data->flags = compat->flags; data->version = compat->version; } /* * Validate NFSv4 mount options */ static int nfs4_parse_monolithic(struct fs_context *fc, struct nfs4_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct sockaddr_storage *sap = &ctx->nfs_server._address; int ret; char *c; if (!data) { if (is_remount_fc(fc)) goto done; return nfs_invalf(fc, "NFS4: mount program didn't pass any mount data"); } ctx->version = 4; if (data->version != 1) return generic_parse_monolithic(fc, data); if (in_compat_syscall()) nfs4_compat_mount_data_conv(data); if (data->host_addrlen > sizeof(ctx->nfs_server.address)) goto out_no_address; if (data->host_addrlen == 0) goto out_no_address; ctx->nfs_server.addrlen = data->host_addrlen; if (copy_from_user(sap, data->host_addr, data->host_addrlen)) return -EFAULT; if (!nfs_verify_server_address(sap)) goto out_no_address; ctx->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); if (data->auth_flavourlen) { rpc_authflavor_t pseudoflavor; if (data->auth_flavourlen > 1) goto out_inval_auth; if (copy_from_user(&pseudoflavor, data->auth_flavours, sizeof(pseudoflavor))) return -EFAULT; ctx->selected_flavor = pseudoflavor; } else { ctx->selected_flavor = RPC_AUTH_UNIX; } c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.hostname = c; c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN); if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.export_path = c; trace_nfs_mount_path(c); c = strndup_user(data->client_addr.data, 16); if (IS_ERR(c)) return PTR_ERR(c); ctx->client_address = c; /* * Translate to nfs_fs_context, which nfs_fill_super * can deal with. */ ctx->flags = data->flags & NFS4_MOUNT_FLAGMASK; ctx->rsize = data->rsize; ctx->wsize = data->wsize; ctx->timeo = data->timeo; ctx->retrans = data->retrans; ctx->acregmin = data->acregmin; ctx->acregmax = data->acregmax; ctx->acdirmin = data->acdirmin; ctx->acdirmax = data->acdirmax; ctx->nfs_server.protocol = data->proto; ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; done: ctx->skip_reconfig_option_check = true; return 0; out_inval_auth: return nfs_invalf(fc, "NFS4: Invalid number of RPC auth flavours %d", data->auth_flavourlen); out_no_address: return nfs_invalf(fc, "NFS4: mount program didn't pass remote address"); } #endif /* * Parse a monolithic block of data from sys_mount(). */ static int nfs_fs_context_parse_monolithic(struct fs_context *fc, void *data) { if (fc->fs_type == &nfs_fs_type) return nfs23_parse_monolithic(fc, data); #if IS_ENABLED(CONFIG_NFS_V4) if (fc->fs_type == &nfs4_fs_type) return nfs4_parse_monolithic(fc, data); #endif return nfs_invalf(fc, "NFS: Unsupported monolithic data version"); } /* * Validate the preparsed information in the config. */ static int nfs_fs_context_validate(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_subversion *nfs_mod; struct sockaddr_storage *sap = &ctx->nfs_server._address; int max_namelen = PAGE_SIZE; int max_pathlen = NFS_MAXPATHLEN; int port = 0; int ret; if (!fc->source) goto out_no_device_name; /* Check for sanity first. */ if (ctx->minorversion && ctx->version != 4) goto out_minorversion_mismatch; if (ctx->options & NFS_OPTION_MIGRATION && (ctx->version != 4 || ctx->minorversion != 0)) goto out_migration_misuse; /* Verify that any proto=/mountproto= options match the address * families in the addr=/mountaddr= options. */ if (ctx->protofamily != AF_UNSPEC && ctx->protofamily != ctx->nfs_server.address.sa_family) goto out_proto_mismatch; if (ctx->mountfamily != AF_UNSPEC) { if (ctx->mount_server.addrlen) { if (ctx->mountfamily != ctx->mount_server.address.sa_family) goto out_mountproto_mismatch; } else { if (ctx->mountfamily != ctx->nfs_server.address.sa_family) goto out_mountproto_mismatch; } } if (!nfs_verify_server_address(sap)) goto out_no_address; ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; if (ctx->version == 4) { if (IS_ENABLED(CONFIG_NFS_V4)) { if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) port = NFS_RDMA_PORT; else port = NFS_PORT; max_namelen = NFS4_MAXNAMLEN; max_pathlen = NFS4_MAXPATHLEN; ctx->flags &= ~(NFS_MOUNT_NONLM | NFS_MOUNT_NOACL | NFS_MOUNT_VER3 | NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } else { goto out_v4_not_compiled; } } else { nfs_set_mount_transport_protocol(ctx); if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) port = NFS_RDMA_PORT; } nfs_set_port(sap, &ctx->nfs_server.port, port); ret = nfs_parse_source(fc, max_namelen, max_pathlen); if (ret < 0) return ret; /* Load the NFS protocol module if we haven't done so yet */ if (!ctx->nfs_mod) { nfs_mod = find_nfs_version(ctx->version); if (IS_ERR(nfs_mod)) { ret = PTR_ERR(nfs_mod); goto out_version_unavailable; } ctx->nfs_mod = nfs_mod; } /* Ensure the filesystem context has the correct fs_type */ if (fc->fs_type != ctx->nfs_mod->nfs_fs) { module_put(fc->fs_type->owner); __module_get(ctx->nfs_mod->nfs_fs->owner); fc->fs_type = ctx->nfs_mod->nfs_fs; } return 0; out_no_device_name: return nfs_invalf(fc, "NFS: Device name not specified"); out_v4_not_compiled: nfs_errorf(fc, "NFS: NFSv4 is not compiled into kernel"); return -EPROTONOSUPPORT; out_no_address: return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); out_mountproto_mismatch: return nfs_invalf(fc, "NFS: Mount server address does not match mountproto= option"); out_proto_mismatch: return nfs_invalf(fc, "NFS: Server address does not match proto= option"); out_minorversion_mismatch: return nfs_invalf(fc, "NFS: Mount option vers=%u does not support minorversion=%u", ctx->version, ctx->minorversion); out_migration_misuse: return nfs_invalf(fc, "NFS: 'Migration' not supported for this NFS version"); out_version_unavailable: nfs_errorf(fc, "NFS: Version unavailable"); return ret; } /* * Create an NFS superblock by the appropriate method. */ static int nfs_get_tree(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); int err = nfs_fs_context_validate(fc); if (err) return err; if (!ctx->internal) return ctx->nfs_mod->rpc_ops->try_get_tree(fc); else return nfs_get_tree_common(fc); } /* * Handle duplication of a configuration. The caller copied *src into *sc, but * it can't deal with resource pointers in the filesystem context, so we have * to do that. We need to clear pointers, copy data or get extra refs as * appropriate. */ static int nfs_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { struct nfs_fs_context *src = nfs_fc2context(src_fc), *ctx; ctx = kmemdup(src, sizeof(struct nfs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->mntfh = nfs_alloc_fhandle(); if (!ctx->mntfh) { kfree(ctx); return -ENOMEM; } nfs_copy_fh(ctx->mntfh, src->mntfh); get_nfs_version(ctx->nfs_mod); ctx->client_address = NULL; ctx->mount_server.hostname = NULL; ctx->nfs_server.export_path = NULL; ctx->nfs_server.hostname = NULL; ctx->fscache_uniq = NULL; ctx->clone_data.fattr = NULL; fc->fs_private = ctx; return 0; } static void nfs_fs_context_free(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); if (ctx) { if (ctx->server) nfs_free_server(ctx->server); if (ctx->nfs_mod) put_nfs_version(ctx->nfs_mod); kfree(ctx->client_address); kfree(ctx->mount_server.hostname); kfree(ctx->nfs_server.export_path); kfree(ctx->nfs_server.hostname); kfree(ctx->fscache_uniq); nfs_free_fhandle(ctx->mntfh); nfs_free_fattr(ctx->clone_data.fattr); kfree(ctx); } } static const struct fs_context_operations nfs_fs_context_ops = { .free = nfs_fs_context_free, .dup = nfs_fs_context_dup, .parse_param = nfs_fs_context_parse_param, .parse_monolithic = nfs_fs_context_parse_monolithic, .get_tree = nfs_get_tree, .reconfigure = nfs_reconfigure, }; /* * Prepare superblock configuration. We use the namespaces attached to the * context. This may be the current process's namespaces, or it may be a * container's namespaces. */ static int nfs_init_fs_context(struct fs_context *fc) { struct nfs_fs_context *ctx; ctx = kzalloc(sizeof(struct nfs_fs_context), GFP_KERNEL); if (unlikely(!ctx)) return -ENOMEM; ctx->mntfh = nfs_alloc_fhandle(); if (unlikely(!ctx->mntfh)) { kfree(ctx); return -ENOMEM; } ctx->protofamily = AF_UNSPEC; ctx->mountfamily = AF_UNSPEC; ctx->mount_server.port = NFS_UNSPEC_PORT; if (fc->root) { /* reconfigure, start with the current config */ struct nfs_server *nfss = fc->root->d_sb->s_fs_info; struct net *net = nfss->nfs_client->cl_net; ctx->flags = nfss->flags; ctx->rsize = nfss->rsize; ctx->wsize = nfss->wsize; ctx->retrans = nfss->client->cl_timeout->to_retries; ctx->selected_flavor = nfss->client->cl_auth->au_flavor; ctx->acregmin = nfss->acregmin / HZ; ctx->acregmax = nfss->acregmax / HZ; ctx->acdirmin = nfss->acdirmin / HZ; ctx->acdirmax = nfss->acdirmax / HZ; ctx->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; ctx->nfs_server.port = nfss->port; ctx->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; ctx->version = nfss->nfs_client->rpc_ops->version; ctx->minorversion = nfss->nfs_client->cl_minorversion; memcpy(&ctx->nfs_server._address, &nfss->nfs_client->cl_addr, ctx->nfs_server.addrlen); if (fc->net_ns != net) { put_net(fc->net_ns); fc->net_ns = get_net(net); } ctx->nfs_mod = nfss->nfs_client->cl_nfs_mod; get_nfs_version(ctx->nfs_mod); } else { /* defaults */ ctx->timeo = NFS_UNSPEC_TIMEO; ctx->retrans = NFS_UNSPEC_RETRANS; ctx->acregmin = NFS_DEF_ACREGMIN; ctx->acregmax = NFS_DEF_ACREGMAX; ctx->acdirmin = NFS_DEF_ACDIRMIN; ctx->acdirmax = NFS_DEF_ACDIRMAX; ctx->nfs_server.port = NFS_UNSPEC_PORT; ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; ctx->selected_flavor = RPC_AUTH_MAXFLAVOR; ctx->minorversion = 0; ctx->need_mount = true; ctx->xprtsec.policy = RPC_XPRTSEC_NONE; ctx->xprtsec.cert_serial = TLS_NO_CERT; ctx->xprtsec.privkey_serial = TLS_NO_PRIVKEY; if (fc->net_ns != &init_net) ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; fc->s_iflags |= SB_I_STABLE_WRITES; } fc->fs_private = ctx; fc->ops = &nfs_fs_context_ops; return 0; } struct file_system_type nfs_fs_type = { .owner = THIS_MODULE, .name = "nfs", .init_fs_context = nfs_init_fs_context, .parameters = nfs_fs_parameters, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, }; MODULE_ALIAS_FS("nfs"); EXPORT_SYMBOL_GPL(nfs_fs_type); #if IS_ENABLED(CONFIG_NFS_V4) struct file_system_type nfs4_fs_type = { .owner = THIS_MODULE, .name = "nfs4", .init_fs_context = nfs_init_fs_context, .parameters = nfs_fs_parameters, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA, }; MODULE_ALIAS_FS("nfs4"); MODULE_ALIAS("nfs4"); EXPORT_SYMBOL_GPL(nfs4_fs_type); #endif /* CONFIG_NFS_V4 */ |
| 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Wireless utility functions * * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH * Copyright (C) 2018-2023, 2025 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> #include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" const struct ieee80211_rate * ieee80211_get_response_rate(struct ieee80211_supported_band *sband, u32 basic_rates, int bitrate) { struct ieee80211_rate *result = &sband->bitrates[0]; int i; for (i = 0; i < sband->n_bitrates; i++) { if (!(basic_rates & BIT(i))) continue; if (sband->bitrates[i].bitrate > bitrate) continue; result = &sband->bitrates[i]; } return result; } EXPORT_SYMBOL(ieee80211_get_response_rate); u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband) { struct ieee80211_rate *bitrates; u32 mandatory_rates = 0; enum ieee80211_rate_flags mandatory_flag; int i; if (WARN_ON(!sband)) return 1; if (sband->band == NL80211_BAND_2GHZ) mandatory_flag = IEEE80211_RATE_MANDATORY_B; else mandatory_flag = IEEE80211_RATE_MANDATORY_A; bitrates = sband->bitrates; for (i = 0; i < sband->n_bitrates; i++) if (bitrates[i].flags & mandatory_flag) mandatory_rates |= BIT(i); return mandatory_rates; } EXPORT_SYMBOL(ieee80211_mandatory_rates); u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) { /* see 802.11 17.3.8.3.2 and Annex J * there are overlapping channel numbers in 5GHz and 2GHz bands */ if (chan <= 0) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) return MHZ_TO_KHZ(2407 + chan * 5); break; case NL80211_BAND_5GHZ: if (chan >= 182 && chan <= 196) return MHZ_TO_KHZ(4000 + chan * 5); else return MHZ_TO_KHZ(5000 + chan * 5); break; case NL80211_BAND_6GHZ: /* see 802.11ax D6.1 27.3.23.2 */ if (chan == 2) return MHZ_TO_KHZ(5935); if (chan <= 233) return MHZ_TO_KHZ(5950 + chan * 5); break; case NL80211_BAND_60GHZ: if (chan < 7) return MHZ_TO_KHZ(56160 + chan * 2160); break; case NL80211_BAND_S1GHZ: return 902000 + chan * 500; default: ; } return 0; /* not supported */ } EXPORT_SYMBOL(ieee80211_channel_to_freq_khz); int ieee80211_freq_khz_to_channel(u32 freq) { /* TODO: just handle MHz for now */ freq = KHZ_TO_MHZ(freq); /* see 802.11 17.3.8.3.2 and Annex J */ if (freq == 2484) return 14; else if (freq < 2484) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; else if (freq < 5925) return (freq - 5000) / 5; else if (freq == 5935) return 2; else if (freq <= 45000) /* DMG band lower limit */ /* see 802.11ax D6.1 27.3.22.2 */ return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else return 0; } EXPORT_SYMBOL(ieee80211_freq_khz_to_channel); struct ieee80211_channel *ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq) { enum nl80211_band band; struct ieee80211_supported_band *sband; int i; for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (ieee80211_channel_to_khz(chan) == freq) return chan; } } return NULL; } EXPORT_SYMBOL(ieee80211_get_channel_khz); static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) { int i, want; switch (sband->band) { case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: want = 3; for (i = 0; i < sband->n_bitrates; i++) { if (sband->bitrates[i].bitrate == 60 || sband->bitrates[i].bitrate == 120 || sband->bitrates[i].bitrate == 240) { sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_A; want--; } } WARN_ON(want); break; case NL80211_BAND_2GHZ: case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { case 10: case 20: case 55: case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; break; case 60: case 120: case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; fallthrough; default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; break; } } WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ WARN_ON(!sband->ht_cap.ht_supported); WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); break; case NL80211_BAND_S1GHZ: /* Figure 9-589bd: 3 means unsupported, so != 3 means at least * mandatory is ok. */ WARN_ON((sband->s1g_cap.nss_mcs[0] & 0x3) == 0x3); break; case NUM_NL80211_BANDS: default: WARN_ON(1); break; } } void ieee80211_set_bitrate_flags(struct wiphy *wiphy) { enum nl80211_band band; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) set_mandatory_flags_band(wiphy->bands[band]); } bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) { int i; for (i = 0; i < wiphy->n_cipher_suites; i++) if (cipher == wiphy->cipher_suites[i]) return true; return false; } static bool cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev) { struct wiphy *wiphy = &rdev->wiphy; int i; for (i = 0; i < wiphy->n_cipher_suites; i++) { switch (wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: return true; } } return false; } bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, int key_idx, bool pairwise) { int max_key_idx; if (pairwise) max_key_idx = 3; else if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; else if (cfg80211_igtk_cipher_supported(rdev)) max_key_idx = 5; else max_key_idx = 3; if (key_idx < 0 || key_idx > max_key_idx) return false; return true; } int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise)) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) return -EINVAL; if (pairwise && !mac_addr) return -EINVAL; switch (params->cipher) { case WLAN_CIPHER_SUITE_TKIP: /* Extended Key ID can only be used with CCMP/GCMP ciphers */ if ((pairwise && key_idx) || params->mode != NL80211_KEY_RX_TX) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: /* IEEE802.11-2016 allows only 0 and - when supporting * Extended Key ID - 1 as index for pairwise keys. * @NL80211_KEY_NO_TX is only allowed for pairwise keys when * the driver supports Extended Key ID. * @NL80211_KEY_SET_TX can't be set when installing and * validating a key. */ if ((params->mode == NL80211_KEY_NO_TX && !pairwise) || params->mode == NL80211_KEY_SET_TX) return -EINVAL; if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { if (pairwise && (key_idx < 0 || key_idx > 1)) return -EINVAL; } else if (pairwise && key_idx) { return -EINVAL; } break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: /* Disallow BIP (group-only) cipher as pairwise cipher */ if (pairwise) return -EINVAL; if (key_idx < 4) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: if (key_idx > 3) return -EINVAL; break; default: break; } switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: if (params->key_len != WLAN_KEY_LEN_WEP40) return -EINVAL; break; case WLAN_CIPHER_SUITE_TKIP: if (params->key_len != WLAN_KEY_LEN_TKIP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: if (params->key_len != WLAN_KEY_LEN_CCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP_256: if (params->key_len != WLAN_KEY_LEN_CCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP: if (params->key_len != WLAN_KEY_LEN_GCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP_256: if (params->key_len != WLAN_KEY_LEN_GCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP104: if (params->key_len != WLAN_KEY_LEN_WEP104) return -EINVAL; break; case WLAN_CIPHER_SUITE_AES_CMAC: if (params->key_len != WLAN_KEY_LEN_AES_CMAC) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256) return -EINVAL; break; default: /* * We don't know anything about this algorithm, * allow using it -- but the driver must check * all parameters! We still check below whether * or not the driver supports this algorithm, * of course. */ break; } if (params->seq) { switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: /* These ciphers do not use key sequence */ return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->seq_len != 6) return -EINVAL; break; } } if (!cfg80211_supported_cipher_suite(&rdev->wiphy, params->cipher)) return -EINVAL; return 0; } unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc) { unsigned int hdrlen = 24; if (ieee80211_is_ext(fc)) { hdrlen = 4; goto out; } if (ieee80211_is_data(fc)) { if (ieee80211_has_a4(fc)) hdrlen = 30; if (ieee80211_is_data_qos(fc)) { hdrlen += IEEE80211_QOS_CTL_LEN; if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; } goto out; } if (ieee80211_is_mgmt(fc)) { if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; goto out; } if (ieee80211_is_ctl(fc)) { /* * ACK and CTS are 10 bytes, all others 16. To see how * to get this condition consider * subtype mask: 0b0000000011110000 (0x00F0) * ACK subtype: 0b0000000011010000 (0x00D0) * CTS subtype: 0b0000000011000000 (0x00C0) * bits that matter: ^^^ (0x00E0) * value of those: 0b0000000011000000 (0x00C0) */ if ((fc & cpu_to_le16(0x00E0)) == cpu_to_le16(0x00C0)) hdrlen = 10; else hdrlen = 16; } out: return hdrlen; } EXPORT_SYMBOL(ieee80211_hdrlen); unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) { const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)skb->data; unsigned int hdrlen; if (unlikely(skb->len < 10)) return 0; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (unlikely(hdrlen > skb->len)) return 0; return hdrlen; } EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); static unsigned int __ieee80211_get_mesh_hdrlen(u8 flags) { int ae = flags & MESH_FLAGS_AE; /* 802.11-2012, 8.2.4.7.3 */ switch (ae) { default: case 0: return 6; case MESH_FLAGS_AE_A4: return 12; case MESH_FLAGS_AE_A5_A6: return 18; } } unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { return __ieee80211_get_mesh_hdrlen(meshhdr->flags); } EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto) { const __be16 *hdr_proto = hdr + ETH_ALEN; if (!(ether_addr_equal(hdr, rfc1042_header) && *hdr_proto != htons(ETH_P_AARP) && *hdr_proto != htons(ETH_P_IPX)) && !ether_addr_equal(hdr, bridge_tunnel_header)) return false; *proto = *hdr_proto; return true; } EXPORT_SYMBOL(ieee80211_get_8023_tunnel_proto); int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb) { const void *mesh_addr; struct { struct ethhdr eth; u8 flags; } payload; int hdrlen; int ret; ret = skb_copy_bits(skb, 0, &payload, sizeof(payload)); if (ret) return ret; hdrlen = sizeof(payload.eth) + __ieee80211_get_mesh_hdrlen(payload.flags); if (likely(pskb_may_pull(skb, hdrlen + 8) && ieee80211_get_8023_tunnel_proto(skb->data + hdrlen, &payload.eth.h_proto))) hdrlen += ETH_ALEN + 2; else if (!pskb_may_pull(skb, hdrlen)) return -EINVAL; else payload.eth.h_proto = htons(skb->len - hdrlen); mesh_addr = skb->data + sizeof(payload.eth) + ETH_ALEN; switch (payload.flags & MESH_FLAGS_AE) { case MESH_FLAGS_AE_A4: memcpy(&payload.eth.h_source, mesh_addr, ETH_ALEN); break; case MESH_FLAGS_AE_A5_A6: memcpy(&payload.eth, mesh_addr, 2 * ETH_ALEN); break; default: break; } pskb_pull(skb, hdrlen - sizeof(payload.eth)); memcpy(skb->data, &payload.eth, sizeof(payload.eth)); return 0; } EXPORT_SYMBOL(ieee80211_strip_8023_mesh_hdr); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { u8 hdr[ETH_ALEN] __aligned(2); __be16 proto; } payload; struct ethhdr tmp; u16 hdrlen; if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return -1; hdrlen = ieee80211_hdrlen(hdr->frame_control) + data_offset; if (skb->len < hdrlen) return -1; /* convert IEEE 802.11 header + possible LLC headers into Ethernet * header * IEEE 802.11 address fields: * ToDS FromDS Addr1 Addr2 Addr3 Addr4 * 0 0 DA SA BSSID n/a * 0 1 DA BSSID SA n/a * 1 0 BSSID SA DA n/a * 1 1 RA TA DA SA */ memcpy(tmp.h_dest, ieee80211_get_DA(hdr), ETH_ALEN); memcpy(tmp.h_source, ieee80211_get_SA(hdr), ETH_ALEN); switch (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) { case cpu_to_le16(IEEE80211_FCTL_TODS): if (unlikely(iftype != NL80211_IFTYPE_AP && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_P2P_GO)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_STATION)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): if ((iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_P2P_CLIENT && iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(tmp.h_dest) && ether_addr_equal(tmp.h_source, addr))) return -1; break; case cpu_to_le16(0): if (iftype != NL80211_IFTYPE_ADHOC && iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_OCB) return -1; break; } if (likely(!is_amsdu && iftype != NL80211_IFTYPE_MESH_POINT && skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)) == 0 && ieee80211_get_8023_tunnel_proto(&payload, &tmp.h_proto))) { /* remove RFC1042 or Bridge-Tunnel encapsulation */ hdrlen += ETH_ALEN + 2; skb_postpull_rcsum(skb, &payload, ETH_ALEN + 2); } else { tmp.h_proto = htons(skb->len - hdrlen); } pskb_pull(skb, hdrlen); if (!ehdr) ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr, &tmp, sizeof(tmp)); return 0; } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) { struct skb_shared_info *sh = skb_shinfo(skb); int page_offset; get_page(page); page_offset = ptr - page_address(page); skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size); } static void __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame, int offset, int len) { struct skb_shared_info *sh = skb_shinfo(skb); const skb_frag_t *frag = &sh->frags[0]; struct page *frag_page; void *frag_ptr; int frag_len, frag_size; int head_size = skb->len - skb->data_len; int cur_len; frag_page = virt_to_head_page(skb->head); frag_ptr = skb->data; frag_size = head_size; while (offset >= frag_size) { offset -= frag_size; frag_page = skb_frag_page(frag); frag_ptr = skb_frag_address(frag); frag_size = skb_frag_size(frag); frag++; } frag_ptr += offset; frag_len = frag_size - offset; cur_len = min(len, frag_len); __frame_add_frag(frame, frag_page, frag_ptr, cur_len, frag_size); len -= cur_len; while (len > 0) { frag_len = skb_frag_size(frag); cur_len = min(len, frag_len); __frame_add_frag(frame, skb_frag_page(frag), skb_frag_address(frag), cur_len, frag_len); len -= cur_len; frag++; } } static struct sk_buff * __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen, int offset, int len, bool reuse_frag, int min_len) { struct sk_buff *frame; int cur_len = len; if (skb->len - offset < len) return NULL; /* * When reusing fragments, copy some data to the head to simplify * ethernet header handling and speed up protocol header processing * in the stack later. */ if (reuse_frag) cur_len = min_t(int, len, min_len); /* * Allocate and reserve two bytes more for payload * alignment since sizeof(struct ethhdr) is 14. */ frame = dev_alloc_skb(hlen + sizeof(struct ethhdr) + 2 + cur_len); if (!frame) return NULL; frame->priority = skb->priority; skb_reserve(frame, hlen + sizeof(struct ethhdr) + 2); skb_copy_bits(skb, offset, skb_put(frame, cur_len), cur_len); len -= cur_len; if (!len) return frame; offset += cur_len; __ieee80211_amsdu_copy_frag(skb, frame, offset, len); return frame; } static u16 ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) { __le16 *field_le = field; __be16 *field_be = field; u16 len; if (hdr_type >= 2) len = le16_to_cpu(*field_le); else len = be16_to_cpu(*field_be); if (hdr_type) len += __ieee80211_get_mesh_hdrlen(mesh_flags); return len; } bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; if (sizeof(hdr) > remaining) return false; if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; len = ieee80211_amsdu_subframe_length(&hdr.len, hdr.mesh_flags, mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; if (subframe_len > remaining) return false; } return true; } EXPORT_SYMBOL(ieee80211_is_valid_amsdu); /* * Detects if an MSDU frame was maliciously converted into an A-MSDU * frame by an adversary. This is done by parsing the received frame * as if it were a regular MSDU, even though the A-MSDU flag is set. * * For non-mesh interfaces, detection involves checking whether the * payload, when interpreted as an MSDU, begins with a valid RFC1042 * header. This is done by comparing the A-MSDU subheader's destination * address to the start of the RFC1042 header. * * For mesh interfaces, the MSDU includes a 6-byte Mesh Control field * and an optional variable-length Mesh Address Extension field before * the RFC1042 header. The position of the RFC1042 header must therefore * be calculated based on the mesh header length. * * Since this function intentionally parses an A-MSDU frame as an MSDU, * it only assumes that the A-MSDU subframe header is present, and * beyond this it performs its own bounds checks under the assumption * that the frame is instead parsed as a non-aggregated MSDU. */ static bool is_amsdu_aggregation_attack(struct ethhdr *eth, struct sk_buff *skb, enum nl80211_iftype iftype) { int offset; /* Non-mesh case can be directly compared */ if (iftype != NL80211_IFTYPE_MESH_POINT) return ether_addr_equal(eth->h_dest, rfc1042_header); offset = __ieee80211_get_mesh_hdrlen(eth->h_dest[0]); if (offset == 6) { /* Mesh case with empty address extension field */ return ether_addr_equal(eth->h_source, rfc1042_header); } else if (offset + ETH_ALEN <= skb->len) { /* Mesh case with non-empty address extension field */ u8 temp[ETH_ALEN]; skb_copy_bits(skb, offset, temp, ETH_ALEN); return ether_addr_equal(temp, rfc1042_header); } return false; } void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, const u8 *check_da, const u8 *check_sa, u8 mesh_control) { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; int offset = 0; struct { struct ethhdr eth; uint8_t flags; } hdr; bool reuse_frag = skb->head_frag && !skb_has_frag_list(skb); bool reuse_skb = false; bool last = false; int copy_len = sizeof(hdr.eth); if (iftype == NL80211_IFTYPE_MESH_POINT) copy_len = sizeof(hdr); while (!last) { int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; if (copy_len > remaining) goto purge; skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); len = ieee80211_amsdu_subframe_length(&hdr.eth.h_proto, hdr.flags, mesh_control); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks, to be * checked when processing first subframe (offset == 0). */ if (offset == 0 && is_amsdu_aggregation_attack(&hdr.eth, skb, iftype)) goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; /* FIXME: should we really accept multicast DA? */ if ((check_da && !is_multicast_ether_addr(hdr.eth.h_dest) && !ether_addr_equal(check_da, hdr.eth.h_dest)) || (check_sa && !ether_addr_equal(check_sa, hdr.eth.h_source))) { offset += len + padding; continue; } /* reuse skb for the last subframe */ if (!skb_is_nonlinear(skb) && !reuse_frag && last) { skb_pull(skb, offset); frame = skb; reuse_skb = true; } else { frame = __ieee80211_amsdu_copy(skb, hlen, offset, len, reuse_frag, 32 + mesh_len); if (!frame) goto purge; offset += len + padding; } skb_reset_network_header(frame); frame->dev = skb->dev; frame->priority = skb->priority; if (likely(iftype != NL80211_IFTYPE_MESH_POINT && ieee80211_get_8023_tunnel_proto(frame->data, &hdr.eth.h_proto))) skb_pull(frame, ETH_ALEN + 2); memcpy(skb_push(frame, sizeof(hdr.eth)), &hdr.eth, sizeof(hdr.eth)); __skb_queue_tail(list, frame); } if (!reuse_skb) dev_kfree_skb(skb); return; purge: __skb_queue_purge(list); dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_amsdu_to_8023s); /* Given a data frame determine the 802.1p/1d tag to use. */ unsigned int cfg80211_classify8021d(struct sk_buff *skb, struct cfg80211_qos_map *qos_map) { unsigned int dscp; unsigned char vlan_priority; unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ if (skb->priority >= 256 && skb->priority <= 263) { ret = skb->priority - 256; goto out; } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; if (vlan_priority > 0) { ret = vlan_priority; goto out; } } switch (skb->protocol) { case htons(ETH_P_IP): dscp = ipv4_get_dsfield(ip_hdr(skb)) & 0xfc; break; case htons(ETH_P_IPV6): dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc; break; case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): { struct mpls_label mpls_tmp, *mpls; mpls = skb_header_pointer(skb, sizeof(struct ethhdr), sizeof(*mpls), &mpls_tmp); if (!mpls) return 0; ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ return 7; default: return 0; } if (qos_map) { unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { if (tmp_dscp == qos_map->dscp_exception[i].dscp) { ret = qos_map->dscp_exception[i].up; goto out; } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && tmp_dscp <= qos_map->up[i].high) { ret = i; goto out; } } } /* The default mapping as defined Section 2.3 in RFC8325: The three * Most Significant Bits (MSBs) of the DSCP are used as the * corresponding L2 markings. */ ret = dscp >> 5; /* Handle specific DSCP values for which the default mapping (as * described above) doesn't adhere to the intended usage of the DSCP * value. See section 4 in RFC8325. Specifically, for the following * Diffserv Service Classes no update is needed: * - Standard: DF * - Low Priority Data: CS1 * - Multimedia Conferencing: AF41, AF42, AF43 * - Network Control Traffic: CS7 * - Real-Time Interactive: CS4 * - Signaling: CS5 */ switch (dscp >> 2) { case 10: case 12: case 14: /* High throughput data: AF11, AF12, AF13 */ ret = 0; break; case 16: /* Operations, Administration, and Maintenance and Provisioning: * CS2 */ ret = 0; break; case 18: case 20: case 22: /* Low latency data: AF21, AF22, AF23 */ ret = 3; break; case 24: /* Broadcasting video: CS3 */ ret = 4; break; case 26: case 28: case 30: /* Multimedia Streaming: AF31, AF32, AF33 */ ret = 4; break; case 44: /* Voice Admit: VA */ ret = 6; break; case 46: /* Telephony traffic: EF */ ret = 6; break; case 48: /* Network Control Traffic: CS6 */ ret = 7; break; } out: return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id) { const struct cfg80211_bss_ies *ies; ies = rcu_dereference(bss->ies); if (!ies) return NULL; return cfg80211_find_elem(id, ies->data, ies->len); } EXPORT_SYMBOL(ieee80211_bss_get_elem); void cfg80211_upload_connect_keys(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct net_device *dev = wdev->netdev; int i; if (!wdev->connect_keys) return; for (i = 0; i < 4; i++) { if (!wdev->connect_keys->params[i].cipher) continue; if (rdev_add_key(rdev, dev, -1, i, false, NULL, &wdev->connect_keys->params[i])) { netdev_err(dev, "failed to set key %d\n", i); continue; } if (wdev->connect_keys->def == i && rdev_set_default_key(rdev, dev, -1, i, true, true)) { netdev_err(dev, "failed to set defkey %d\n", i); continue; } } kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; } void cfg80211_process_wdev_events(struct wireless_dev *wdev) { struct cfg80211_event *ev; unsigned long flags; spin_lock_irqsave(&wdev->event_lock, flags); while (!list_empty(&wdev->event_list)) { ev = list_first_entry(&wdev->event_list, struct cfg80211_event, list); list_del(&ev->list); spin_unlock_irqrestore(&wdev->event_lock, flags); switch (ev->type) { case EVENT_CONNECT_RESULT: __cfg80211_connect_result( wdev->netdev, &ev->cr, ev->cr.status == WLAN_STATUS_SUCCESS); break; case EVENT_ROAMED: __cfg80211_roamed(wdev, &ev->rm); break; case EVENT_DISCONNECTED: __cfg80211_disconnected(wdev->netdev, ev->dc.ie, ev->dc.ie_len, ev->dc.reason, !ev->dc.locally_generated); break; case EVENT_IBSS_JOINED: __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, ev->ij.channel); break; case EVENT_STOPPED: cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: __cfg80211_port_authorized(wdev, ev->pa.peer_addr, ev->pa.td_bitmap, ev->pa.td_bitmap_len); break; } kfree(ev); spin_lock_irqsave(&wdev->event_lock, flags); } spin_unlock_irqrestore(&wdev->event_lock, flags); } void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; lockdep_assert_held(&rdev->wiphy.mtx); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_process_wdev_events(wdev); } int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, struct vif_params *params) { int err; enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; lockdep_assert_held(&rdev->wiphy.mtx); /* don't support changing VLANs, you just re-create them */ if (otype == NL80211_IFTYPE_AP_VLAN) return -EOPNOTSUPP; /* cannot change into P2P device or NAN */ if (ntype == NL80211_IFTYPE_P2P_DEVICE || ntype == NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!rdev->ops->change_virtual_intf || !(rdev->wiphy.interface_modes & (1 << ntype))) return -EOPNOTSUPP; if (ntype != otype) { /* if it's part of a bridge, reject changing type to station/ibss */ if (netif_is_bridge_port(dev) && (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION || ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; dev->ieee80211_ptr->use_4addr = false; rdev_set_qos_map(rdev, dev, NULL); switch (otype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, -1, true); break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, true); break; case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; case NL80211_IFTYPE_OCB: cfg80211_leave_ocb(rdev, dev); break; default: break; } cfg80211_process_rdev_events(rdev); cfg80211_mlme_purge_registrations(dev->ieee80211_ptr); memset(&dev->ieee80211_ptr->u, 0, sizeof(dev->ieee80211_ptr->u)); memset(&dev->ieee80211_ptr->links, 0, sizeof(dev->ieee80211_ptr->links)); } err = rdev_change_virtual_intf(rdev, dev, ntype, params); WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); if (!err && params && params->use_4addr != -1) dev->ieee80211_ptr->use_4addr = params->use_4addr; if (!err) { dev->priv_flags &= ~IFF_DONT_BRIDGE; switch (ntype) { case NL80211_IFTYPE_STATION: if (dev->ieee80211_ptr->use_4addr) break; fallthrough; case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: dev->priv_flags |= IFF_DONT_BRIDGE; break; case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MESH_POINT: /* bridging OK */ break; case NL80211_IFTYPE_MONITOR: /* monitor can't bridge anyway */ break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: /* not happening */ break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_NAN: WARN_ON(1); break; } } if (!err && ntype != otype && netif_running(dev)) { cfg80211_update_iface_num(rdev, ntype, 1); cfg80211_update_iface_num(rdev, otype, -1); } return err; } static u32 cfg80211_calculate_bitrate_ht(struct rate_info *rate) { int modulation, streams, bitrate; /* the formula below does only work for MCS values smaller than 32 */ if (WARN_ON_ONCE(rate->mcs >= 32)) return 0; modulation = rate->mcs & 7; streams = (rate->mcs >> 3) + 1; bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000; if (modulation < 4) bitrate *= (modulation + 1); else if (modulation == 4) bitrate *= (modulation + 2); else bitrate *= (modulation + 3); bitrate *= streams; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; } static u32 cfg80211_calculate_bitrate_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 15400, [7] = 19250, [8] = 23100, [9] = 25025, [10] = 30800, [11] = 38500, [12] = 46200, /* OFDM PHY */ [13] = 6930, [14] = 8662, /* 866.25 mbps */ [15] = 13860, [16] = 17325, [17] = 20790, [18] = 27720, [19] = 34650, [20] = 41580, [21] = 45045, [22] = 51975, [23] = 62370, [24] = 67568, /* 6756.75 mbps */ /* LP-SC PHY */ [25] = 6260, [26] = 8340, [27] = 11120, [28] = 12510, [29] = 16680, [30] = 22240, [31] = 25030, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs]; } static u32 cfg80211_calculate_bitrate_extended_sc_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { [6 - 6] = 26950, /* MCS 9.1 : 2695.0 mbps */ [7 - 6] = 50050, /* MCS 12.1 */ [8 - 6] = 53900, [9 - 6] = 57750, [10 - 6] = 63900, [11 - 6] = 75075, [12 - 6] = 80850, }; /* Extended SC MCS not defined for base MCS below 6 or above 12 */ if (WARN_ON_ONCE(rate->mcs < 6 || rate->mcs > 12)) return 0; return __mcs2bitrate[rate->mcs - 6]; } static u32 cfg80211_calculate_bitrate_edmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 13475, [7] = 15400, [8] = 19250, [9] = 23100, [10] = 25025, [11] = 26950, [12] = 30800, [13] = 38500, [14] = 46200, [15] = 50050, [16] = 53900, [17] = 57750, [18] = 69300, [19] = 75075, [20] = 80850, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs] * rate->n_bonded_ch; } static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) { static const u32 base[4][12] = { { 6500000, 13000000, 19500000, 26000000, 39000000, 52000000, 58500000, 65000000, 78000000, /* not in the spec, but some devices use this: */ 86700000, 97500000, 108300000, }, { 13500000, 27000000, 40500000, 54000000, 81000000, 108000000, 121500000, 135000000, 162000000, 180000000, 202500000, 225000000, }, { 29300000, 58500000, 87800000, 117000000, 175500000, 234000000, 263300000, 292500000, 351000000, 390000000, 438800000, 487500000, }, { 58500000, 117000000, 175500000, 234000000, 351000000, 468000000, 526500000, 585000000, 702000000, 780000000, 877500000, 975000000, }, }; u32 bitrate; int idx; if (rate->mcs > 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_160: idx = 3; break; case RATE_INFO_BW_80: idx = 2; break; case RATE_INFO_BW_40: idx = 1; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: default: goto warn; case RATE_INFO_BW_20: idx = 0; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) { #define SCALE 6144 u32 mcs_divisors[14] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; u32 rates_52[3] = { 18820000, 17777777, 16000000 }; u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 13)) return 0; if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->he_ru_alloc > NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) result = rates_484[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242)) result = rates_242[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106) result = rates_106[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52) result = rates_52[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) result = rates_26[rate->he_gi]; else { WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", rate->bw, rate->he_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); result = tmp; /* and take NSS, DCM into account */ result = (result * rate->nss) / 8; if (rate->he_dcm) result /= 2; return result / 10000; } static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) { #define SCALE 6144 static const u32 mcs_divisors[16] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ 409600, /* 66.666666... */ 204800, /* 33.333333... */ }; static const u32 rates_996[3] = { 480388888, 453700000, 408333333 }; static const u32 rates_484[3] = { 229411111, 216666666, 195000000 }; static const u32 rates_242[3] = { 114711111, 108333333, 97500000 }; static const u32 rates_106[3] = { 40000000, 37777777, 34000000 }; static const u32 rates_52[3] = { 18820000, 17777777, 16000000 }; static const u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 15)) return 0; if (WARN_ON_ONCE(rate->eht_gi > NL80211_RATE_INFO_EHT_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->eht_ru_alloc > NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; /* Bandwidth checks for MCS 14 */ if (rate->mcs == 14) { if ((rate->bw != RATE_INFO_BW_EHT_RU && rate->bw != RATE_INFO_BW_80 && rate->bw != RATE_INFO_BW_160 && rate->bw != RATE_INFO_BW_320) || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_2x996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) { WARN(1, "invalid EHT BW for MCS 14: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } } if (rate->bw == RATE_INFO_BW_320 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) result = 4 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484) result = 3 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996) result = 3 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484) result = 2 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996)) result = 2 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996)) result = rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484P242) result = rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484)) result = rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_242)) result = rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106P26) result = rates_106[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106) result = rates_106[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52P26) result = rates_52[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52) result = rates_52[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_26) result = rates_26[rate->eht_gi]; else { WARN(1, "invalid EHT MCS: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); /* and take NSS */ tmp *= rate->nss; do_div(tmp, 8); result = tmp; return result / 10000; } static u32 cfg80211_calculate_bitrate_s1g(struct rate_info *rate) { /* For 1, 2, 4, 8 and 16 MHz channels */ static const u32 base[5][11] = { { 300000, 600000, 900000, 1200000, 1800000, 2400000, 2700000, 3000000, 3600000, 4000000, /* MCS 10 supported in 1 MHz only */ 150000, }, { 650000, 1300000, 1950000, 2600000, 3900000, 5200000, 5850000, 6500000, 7800000, /* MCS 9 not valid */ }, { 1350000, 2700000, 4050000, 5400000, 8100000, 10800000, 12150000, 13500000, 16200000, 18000000, }, { 2925000, 5850000, 8775000, 11700000, 17550000, 23400000, 26325000, 29250000, 35100000, 39000000, }, { 8580000, 11700000, 17550000, 23400000, 35100000, 46800000, 52650000, 58500000, 70200000, 78000000, }, }; u32 bitrate; /* default is 1 MHz index */ int idx = 0; if (rate->mcs >= 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_16: idx = 4; break; case RATE_INFO_BW_8: idx = 3; break; case RATE_INFO_BW_4: idx = 2; break; case RATE_INFO_BW_2: idx = 1; break; case RATE_INFO_BW_1: idx = 0; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: case RATE_INFO_BW_20: case RATE_INFO_BW_40: case RATE_INFO_BW_80: case RATE_INFO_BW_160: default: goto warn; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) return cfg80211_calculate_bitrate_ht(rate); if (rate->flags & RATE_INFO_FLAGS_DMG) return cfg80211_calculate_bitrate_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EXTENDED_SC_DMG) return cfg80211_calculate_bitrate_extended_sc_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EDMG) return cfg80211_calculate_bitrate_edmg(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) return cfg80211_calculate_bitrate_vht(rate); if (rate->flags & RATE_INFO_FLAGS_HE_MCS) return cfg80211_calculate_bitrate_he(rate); if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) return cfg80211_calculate_bitrate_eht(rate); if (rate->flags & RATE_INFO_FLAGS_S1G_MCS) return cfg80211_calculate_bitrate_s1g(rate); return rate->legacy; } EXPORT_SYMBOL(cfg80211_calculate_bitrate); int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, enum ieee80211_p2p_attr_id attr, u8 *buf, unsigned int bufsize) { u8 *out = buf; u16 attr_remaining = 0; bool desired_attr = false; u16 desired_len = 0; while (len > 0) { unsigned int iedatalen; unsigned int copy; const u8 *iedata; if (len < 2) return -EILSEQ; iedatalen = ies[1]; if (iedatalen + 2 > len) return -EILSEQ; if (ies[0] != WLAN_EID_VENDOR_SPECIFIC) goto cont; if (iedatalen < 4) goto cont; iedata = ies + 2; /* check WFA OUI, P2P subtype */ if (iedata[0] != 0x50 || iedata[1] != 0x6f || iedata[2] != 0x9a || iedata[3] != 0x09) goto cont; iedatalen -= 4; iedata += 4; /* check attribute continuation into this IE */ copy = min_t(unsigned int, attr_remaining, iedatalen); if (copy && desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_remaining) return desired_len; } attr_remaining -= copy; if (attr_remaining) goto cont; iedatalen -= copy; iedata += copy; while (iedatalen > 0) { u16 attr_len; /* P2P attribute ID & size must fit */ if (iedatalen < 3) return -EILSEQ; desired_attr = iedata[0] == attr; attr_len = get_unaligned_le16(iedata + 1); iedatalen -= 3; iedata += 3; copy = min_t(unsigned int, attr_len, iedatalen); if (desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_len) return desired_len; } iedata += copy; iedatalen -= copy; attr_remaining = attr_len - copy; } cont: len -= ies[1] + 2; ies += ies[1] + 2; } if (attr_remaining && desired_attr) return -EILSEQ; return -ENOENT; } EXPORT_SYMBOL(cfg80211_get_p2p_attr); static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; /* Make sure array values are legal */ if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) return false; i = 0; while (i < n_ids) { if (ids[i] == WLAN_EID_EXTENSION) { if (id_ext && (ids[i + 1] == id)) return true; i += 2; continue; } if (ids[i] == id && !id_ext) return true; i++; } return false; } static size_t skip_ie(const u8 *ies, size_t ielen, size_t pos) { /* we assume a validly formed IEs buffer */ u8 len = ies[pos + 1]; pos += 2 + len; /* the IE itself must have 255 bytes for fragments to follow */ if (len < 255) return pos; while (pos < ielen && ies[pos] == WLAN_EID_FRAGMENT) { len = ies[pos + 1]; pos += 2 + len; } return pos; } size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, const u8 *after_ric, int n_after_ric, size_t offset) { size_t pos = offset; while (pos < ielen) { u8 ext = 0; if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], ies[pos] == WLAN_EID_EXTENSION)) break; if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); while (pos < ielen) { if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; else ext = 0; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(after_ric, n_after_ric, ies[pos + ext], ext == 2)) pos = skip_ie(ies, ielen, pos); else break; } } else { pos = skip_ie(ies, ielen, pos); } } return pos; } EXPORT_SYMBOL(ieee80211_ie_split_ric); void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id) { unsigned int elem_len; if (!len_pos) return; elem_len = skb->data + skb->len - len_pos - 1; while (elem_len > 255) { /* this one is 255 */ *len_pos = 255; /* remaining data gets smaller */ elem_len -= 255; /* make space for the fragment ID/len in SKB */ skb_put(skb, 2); /* shift back the remaining data to place fragment ID/len */ memmove(len_pos + 255 + 3, len_pos + 255 + 1, elem_len); /* place the fragment ID */ len_pos += 255 + 1; *len_pos = frag_id; /* and point to fragment length to update later */ len_pos++; } *len_pos = elem_len; } EXPORT_SYMBOL(ieee80211_fragment_element); bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band) { switch (operating_class) { case 112: case 115 ... 127: case 128 ... 130: *band = NL80211_BAND_5GHZ; return true; case 131 ... 135: case 137: *band = NL80211_BAND_6GHZ; return true; case 81: case 82: case 83: case 84: *band = NL80211_BAND_2GHZ; return true; case 180: *band = NL80211_BAND_60GHZ; return true; } return false; } EXPORT_SYMBOL(ieee80211_operating_class_to_band); bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, struct cfg80211_chan_def *chandef) { u32 control_freq, offset = 0; enum nl80211_band band; if (!ieee80211_operating_class_to_band(operating_class, &band) || !chan || band != chan->band) return false; control_freq = chan->center_freq; chandef->chan = chan; if (control_freq >= 5955) offset = control_freq - 5955; else if (control_freq >= 5745) offset = control_freq - 5745; else if (control_freq >= 5180) offset = control_freq - 5180; offset /= 20; switch (operating_class) { case 81: /* 2 GHz band; 20 MHz; channels 1..13 */ case 82: /* 2 GHz band; 20 MHz; channel 14 */ case 115: /* 5 GHz band; 20 MHz; channels 36,40,44,48 */ case 118: /* 5 GHz band; 20 MHz; channels 52,56,60,64 */ case 121: /* 5 GHz band; 20 MHz; channels 100..144 */ case 124: /* 5 GHz band; 20 MHz; channels 149,153,157,161 */ case 125: /* 5 GHz band; 20 MHz; channels 149..177 */ case 131: /* 6 GHz band; 20 MHz; channels 1..233*/ case 136: /* 6 GHz band; 20 MHz; channel 2 */ chandef->center_freq1 = control_freq; chandef->width = NL80211_CHAN_WIDTH_20; return true; case 83: /* 2 GHz band; 40 MHz; channels 1..9 */ case 116: /* 5 GHz band; 40 MHz; channels 36,44 */ case 119: /* 5 GHz band; 40 MHz; channels 52,60 */ case 122: /* 5 GHz band; 40 MHz; channels 100,108,116,124,132,140 */ case 126: /* 5 GHz band; 40 MHz; channels 149,157,165,173 */ chandef->center_freq1 = control_freq + 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 84: /* 2 GHz band; 40 MHz; channels 5..13 */ case 117: /* 5 GHz band; 40 MHz; channels 40,48 */ case 120: /* 5 GHz band; 40 MHz; channels 56,64 */ case 123: /* 5 GHz band; 40 MHz; channels 104,112,120,128,136,144 */ case 127: /* 5 GHz band; 40 MHz; channels 153,161,169,177 */ chandef->center_freq1 = control_freq - 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 132: /* 6 GHz band; 40 MHz; channels 1,5,..,229*/ chandef->center_freq1 = control_freq + 10 - (offset & 1) * 20; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 128: /* 5 GHz band; 80 MHz; channels 36..64,100..144,149..177 */ case 133: /* 6 GHz band; 80 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 30 - (offset & 3) * 20; chandef->width = NL80211_CHAN_WIDTH_80; return true; case 129: /* 5 GHz band; 160 MHz; channels 36..64,100..144,149..177 */ case 134: /* 6 GHz band; 160 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 70 - (offset & 7) * 20; chandef->width = NL80211_CHAN_WIDTH_160; return true; case 130: /* 5 GHz band; 80+80 MHz; channels 36..64,100..144,149..177 */ case 135: /* 6 GHz band; 80+80 MHz; channels 1,5,..,229 */ /* The center_freq2 of 80+80 MHz is unknown */ case 137: /* 6 GHz band; 320 MHz; channels 1,5,..,229 */ /* 320-1 or 320-2 channelization is unknown */ default: return false; } } EXPORT_SYMBOL(ieee80211_operating_class_to_chandef); bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) return false; /* 2.407 GHz, channels 1..13 */ if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 83; /* HT40+ */ else *op_class = 84; /* HT40- */ } else { *op_class = 81; } return true; } if (freq == 2484) { /* channel 14 is only for IEEE 802.11b */ if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return false; *op_class = 82; /* channel 14 */ return true; } switch (chandef->width) { case NL80211_CHAN_WIDTH_80: vht_opclass = 128; break; case NL80211_CHAN_WIDTH_160: vht_opclass = 129; break; case NL80211_CHAN_WIDTH_80P80: vht_opclass = 130; break; case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_5: return false; /* unsupported for now */ default: vht_opclass = 0; break; } /* 5 GHz, channels 36..48 */ if (freq >= 5180 && freq <= 5240) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 116; else *op_class = 117; } else { *op_class = 115; } return true; } /* 5 GHz, channels 52..64 */ if (freq >= 5260 && freq <= 5320) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 119; else *op_class = 120; } else { *op_class = 118; } return true; } /* 5 GHz, channels 100..144 */ if (freq >= 5500 && freq <= 5720) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 122; else *op_class = 123; } else { *op_class = 121; } return true; } /* 5 GHz, channels 149..169 */ if (freq >= 5745 && freq <= 5845) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 126; else *op_class = 127; } else if (freq <= 5805) { *op_class = 124; } else { *op_class = 125; } return true; } /* 56.16 GHz, channel 1..4 */ if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 6) { if (chandef->width >= NL80211_CHAN_WIDTH_40) return false; *op_class = 180; return true; } /* not supported yet */ return false; } EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); static int cfg80211_wdev_bi(struct wireless_dev *wdev) { switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: WARN_ON(wdev->valid_links); return wdev->links[0].ap.beacon_interval; case NL80211_IFTYPE_MESH_POINT: return wdev->u.mesh.beacon_interval; case NL80211_IFTYPE_ADHOC: return wdev->u.ibss.beacon_interval; default: break; } return 0; } static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, u32 *beacon_int_gcd, bool *beacon_int_different, int radio_idx) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; *beacon_int_gcd = 0; *beacon_int_different = false; rdev = wiphy_to_rdev(wiphy); list_for_each_entry(wdev, &wiphy->wdev_list, list) { int wdev_bi; /* this feature isn't supported with MLO */ if (wdev->valid_links) continue; /* skip wdevs not active on the given wiphy radio */ if (radio_idx >= 0 && !(rdev_get_radio_mask(rdev, wdev->netdev) & BIT(radio_idx))) continue; wdev_bi = cfg80211_wdev_bi(wdev); if (!wdev_bi) continue; if (!*beacon_int_gcd) { *beacon_int_gcd = wdev_bi; continue; } if (wdev_bi == *beacon_int_gcd) continue; *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, wdev_bi); } if (new_beacon_int && *beacon_int_gcd != new_beacon_int) { if (*beacon_int_gcd) *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, new_beacon_int); } } int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, u32 beacon_int) { /* * This is just a basic pre-condition check; if interface combinations * are possible the driver must already be checking those with a call * to cfg80211_check_combinations(), in which case we'll validate more * through the cfg80211_calculate_bi_data() call and code in * cfg80211_iter_combinations(). */ if (beacon_int < 10 || beacon_int > 10000) return -EINVAL; return 0; } int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, void (*iter)(const struct ieee80211_iface_combination *c, void *data), void *data) { const struct wiphy_radio *radio = NULL; const struct ieee80211_iface_combination *c, *cs; const struct ieee80211_regdomain *regdom; enum nl80211_dfs_regions region = 0; int i, j, n, iftype; int num_interfaces = 0; u32 used_iftypes = 0; u32 beacon_int_gcd; bool beacon_int_different; if (params->radio_idx >= 0) radio = &wiphy->radio[params->radio_idx]; /* * This is a bit strange, since the iteration used to rely only on * the data given by the driver, but here it now relies on context, * in form of the currently operating interfaces. * This is OK for all current users, and saves us from having to * push the GCD calculations into all the drivers. * In the future, this should probably rely more on data that's in * cfg80211 already - the only thing not would appear to be any new * interfaces (while being brought up) and channel/radar data. */ cfg80211_calculate_bi_data(wiphy, params->new_beacon_int, &beacon_int_gcd, &beacon_int_different, params->radio_idx); if (params->radar_detect) { rcu_read_lock(); regdom = rcu_dereference(cfg80211_regdomain); if (regdom) region = regdom->dfs_region; rcu_read_unlock(); } for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } if (radio) { cs = radio->iface_combinations; n = radio->n_iface_combinations; } else { cs = wiphy->iface_combinations; n = wiphy->n_iface_combinations; } for (i = 0; i < n; i++) { struct ieee80211_iface_limit *limits; u32 all_iftypes = 0; c = &cs[i]; if (num_interfaces > c->max_interfaces) continue; if (params->num_different_channels > c->num_different_channels) continue; limits = kmemdup_array(c->limits, c->n_limits, sizeof(*limits), GFP_KERNEL); if (!limits) return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < params->iftype_num[iftype]) goto cont; limits[j].max -= params->iftype_num[iftype]; } } if (params->radar_detect != (c->radar_detect_widths & params->radar_detect)) goto cont; if (params->radar_detect && c->radar_detect_regions && !(c->radar_detect_regions & BIT(region))) goto cont; /* Finally check that all iftypes that we're currently * using are actually part of this combination. If they * aren't then we can't use this combination and have * to continue to the next. */ if ((all_iftypes & used_iftypes) != used_iftypes) goto cont; if (beacon_int_gcd) { if (c->beacon_int_min_gcd && beacon_int_gcd < c->beacon_int_min_gcd) goto cont; if (!c->beacon_int_min_gcd && beacon_int_different) goto cont; } /* This combination covered all interface types and * supported the requested numbers, so we're good. */ (*iter)(c, data); cont: kfree(limits); } return 0; } EXPORT_SYMBOL(cfg80211_iter_combinations); static void cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c, void *data) { int *num = data; (*num)++; } int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params) { int err, num = 0; err = cfg80211_iter_combinations(wiphy, params, cfg80211_iter_sum_ifcombs, &num); if (err) return err; if (num == 0) return -EBUSY; return 0; } EXPORT_SYMBOL(cfg80211_check_combinations); int cfg80211_get_radio_idx_by_chan(struct wiphy *wiphy, const struct ieee80211_channel *chan) { const struct wiphy_radio *radio; int i, j; u32 freq; if (!chan) return -EINVAL; freq = ieee80211_channel_to_khz(chan); for (i = 0; i < wiphy->n_radio; i++) { radio = &wiphy->radio[i]; for (j = 0; j < radio->n_freq_range; j++) { if (freq >= radio->freq_range[j].start_freq && freq < radio->freq_range[j].end_freq) return i; } } return -EINVAL; } EXPORT_SYMBOL(cfg80211_get_radio_idx_by_chan); int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, const u8 *rates, unsigned int n_rates, u32 *mask) { int i, j; if (!sband) return -EINVAL; if (n_rates == 0 || n_rates > NL80211_MAX_SUPP_RATES) return -EINVAL; *mask = 0; for (i = 0; i < n_rates; i++) { int rate = (rates[i] & 0x7f) * 5; bool found = false; for (j = 0; j < sband->n_bitrates; j++) { if (sband->bitrates[j].bitrate == rate) { found = true; *mask |= BIT(j); break; } } if (!found) return -EINVAL; } /* * mask must have at least one bit set here since we * didn't accept a 0-length rates array nor allowed * entries in the array that didn't exist */ return 0; } unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy) { enum nl80211_band band; unsigned int n_channels = 0; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) n_channels += wiphy->bands[band]->n_channels; return n_channels; } EXPORT_SYMBOL(ieee80211_get_num_supported_channels); int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (!rdev->ops->get_station) return -EOPNOTSUPP; memset(sinfo, 0, sizeof(*sinfo)); guard(wiphy)(&rdev->wiphy); return rdev_get_station(rdev, dev, mac_addr, sinfo); } EXPORT_SYMBOL(cfg80211_get_station); void cfg80211_free_nan_func(struct cfg80211_nan_func *f) { int i; if (!f) return; kfree(f->serv_spec_info); kfree(f->srf_bf); kfree(f->srf_macs); for (i = 0; i < f->num_rx_filters; i++) kfree(f->rx_filters[i].filter); for (i = 0; i < f->num_tx_filters; i++) kfree(f->tx_filters[i].filter); kfree(f->rx_filters); kfree(f->tx_filters); kfree(f); } EXPORT_SYMBOL(cfg80211_free_nan_func); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz) { u32 start_freq_khz, end_freq_khz; start_freq_khz = center_freq_khz - (bw_khz / 2); end_freq_khz = center_freq_khz + (bw_khz / 2); if (start_freq_khz >= freq_range->start_freq_khz && end_freq_khz <= freq_range->end_freq_khz) return true; return false; } int cfg80211_link_sinfo_alloc_tid_stats(struct link_station_info *link_sinfo, gfp_t gfp) { link_sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, sizeof(*link_sinfo->pertid), gfp); if (!link_sinfo->pertid) return -ENOMEM; return 0; } EXPORT_SYMBOL(cfg80211_link_sinfo_alloc_tid_stats); int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp) { sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, sizeof(*(sinfo->pertid)), gfp); if (!sinfo->pertid) return -ENOMEM; return 0; } EXPORT_SYMBOL(cfg80211_sinfo_alloc_tid_stats); /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; EXPORT_SYMBOL(rfc1042_header); /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; EXPORT_SYMBOL(bridge_tunnel_header); /* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ struct iapp_layer2_update { u8 da[ETH_ALEN]; /* broadcast */ u8 sa[ETH_ALEN]; /* STA addr */ __be16 len; /* 6 */ u8 dsap; /* 0 */ u8 ssap; /* 0 */ u8 control; u8 xid_info[3]; } __packed; void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) { struct iapp_layer2_update *msg; struct sk_buff *skb; /* Send Level 2 Update Frame to update forwarding tables in layer 2 * bridge devices */ skb = dev_alloc_skb(sizeof(*msg)); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ eth_broadcast_addr(msg->da); ether_addr_copy(msg->sa, addr); msg->len = htons(6); msg->dsap = 0; msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ msg->control = 0xaf; /* XID response lsb.1111F101. * F=0 (no poll command; unsolicited frame) */ msg->xid_info[0] = 0x81; /* XID format identifier */ msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ skb->dev = dev; skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); netif_rx(skb); } EXPORT_SYMBOL(cfg80211_send_layer2_update); int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss) { u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); int ext_nss_bw; int supp_width; int i, mcs_encoding; if (map == 0xffff) return 0; if (WARN_ON(mcs > 9 || max_vht_nss > 8)) return 0; if (mcs <= 7) mcs_encoding = 0; else if (mcs == 8) mcs_encoding = 1; else mcs_encoding = 2; if (!max_vht_nss) { /* find max_vht_nss for the given MCS */ for (i = 7; i >= 0; i--) { int supp = (map >> (2 * i)) & 3; if (supp == 3) continue; if (supp >= mcs_encoding) { max_vht_nss = i + 1; break; } } } if (!(cap->supp_mcs.tx_mcs_map & cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) return max_vht_nss; ext_nss_bw = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); supp_width = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); /* if not capable, treat ext_nss_bw as 0 */ if (!ext_nss_bw_capable) ext_nss_bw = 0; /* This is invalid */ if (supp_width == 3) return 0; /* This is an invalid combination so pretend nothing is supported */ if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return 0; /* * Cover all the special cases according to IEEE 802.11-2016 * Table 9-250. All other cases are either factor of 1 or not * valid/supported. */ switch (bw) { case IEEE80211_VHT_CHANWIDTH_USE_HT: case IEEE80211_VHT_CHANWIDTH_80MHZ: if ((supp_width == 1 || supp_width == 2) && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_160MHZ: if (supp_width == 0 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: if (supp_width == 0 && ext_nss_bw == 1) return 0; /* not possible */ if (supp_width == 0 && ext_nss_bw == 2) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 0) return 0; /* not possible */ if (supp_width == 1 && ext_nss_bw == 1) return max_vht_nss / 2; if (supp_width == 1 && ext_nss_bw == 2) return (3 * max_vht_nss) / 4; break; } /* not covered or invalid combination received */ return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif) { bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; switch (check_swif) { case 0: if (is_vlan && is_4addr) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->interface_modes & BIT(iftype); case 1: if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->software_iftypes & BIT(iftype); default: break; } return false; } EXPORT_SYMBOL(cfg80211_iftype_allowed); void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); lockdep_assert_wiphy(wdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, link_id, true); break; default: /* per-link not relevant */ break; } rdev_del_intf_link(rdev, wdev, link_id); wdev->valid_links &= ~BIT(link_id); eth_zero_addr(wdev->links[link_id].addr); } void cfg80211_remove_links(struct wireless_dev *wdev) { unsigned int link_id; /* * links are controlled by upper layers (userspace/cfg) * only for AP mode, so only remove them here for AP */ if (wdev->iftype != NL80211_IFTYPE_AP) return; if (wdev->valid_links) { for_each_valid_link(wdev, link_id) cfg80211_remove_link(wdev, link_id); } } int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { cfg80211_remove_links(wdev); return rdev_del_virtual_intf(rdev, wdev); } const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type) { int i; for (i = 0; i < wiphy->num_iftype_ext_capab; i++) { if (wiphy->iftype_ext_capab[i].iftype == type) return &wiphy->iftype_ext_capab[i]; } return NULL; } EXPORT_SYMBOL(cfg80211_get_iftype_ext_capa); static bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, u32 freq, u32 width) { const struct wiphy_radio_freq_range *r; int i; for (i = 0; i < radio->n_freq_range; i++) { r = &radio->freq_range[i]; if (freq - width / 2 >= r->start_freq && freq + width / 2 <= r->end_freq) return true; } return false; } bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef) { u32 freq, width; freq = ieee80211_chandef_to_khz(chandef); width = MHZ_TO_KHZ(cfg80211_chandef_get_width(chandef)); if (!ieee80211_radio_freq_range_valid(radio, freq, width)) return false; freq = MHZ_TO_KHZ(chandef->center_freq2); if (freq && !ieee80211_radio_freq_range_valid(radio, freq, width)) return false; return true; } EXPORT_SYMBOL(cfg80211_radio_chandef_valid); bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, struct ieee80211_channel *chan) { struct wiphy *wiphy = wdev->wiphy; const struct wiphy_radio *radio; struct cfg80211_chan_def chandef; u32 radio_mask; int i; radio_mask = wdev->radio_mask; if (!wiphy->n_radio || radio_mask == BIT(wiphy->n_radio) - 1) return true; cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); for (i = 0; i < wiphy->n_radio; i++) { if (!(radio_mask & BIT(i))) continue; radio = &wiphy->radio[i]; if (!cfg80211_radio_chandef_valid(radio, &chandef)) continue; return true; } return false; } EXPORT_SYMBOL(cfg80211_wdev_channel_allowed); |
| 3 3 4 4 2 2 4 4 1 1 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | // SPDX-License-Identifier: GPL-2.0+ /* * Support for dynamic clock devices * * Copyright (C) 2010 OMICRON electronics GmbH */ #include <linux/device.h> #include <linux/export.h> #include <linux/file.h> #include <linux/posix-clock.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include "posix-timers.h" /* * Returns NULL if the posix_clock instance attached to 'fp' is old and stale. */ static struct posix_clock *get_posix_clock(struct file *fp) { struct posix_clock_context *pccontext = fp->private_data; struct posix_clock *clk = pccontext->clk; down_read(&clk->rwsem); if (!clk->zombie) return clk; up_read(&clk->rwsem); return NULL; } static void put_posix_clock(struct posix_clock *clk) { up_read(&clk->rwsem); } static ssize_t posix_clock_read(struct file *fp, char __user *buf, size_t count, loff_t *ppos) { struct posix_clock_context *pccontext = fp->private_data; struct posix_clock *clk = get_posix_clock(fp); int err = -EINVAL; if (!clk) return -ENODEV; if (clk->ops.read) err = clk->ops.read(pccontext, fp->f_flags, buf, count); put_posix_clock(clk); return err; } static __poll_t posix_clock_poll(struct file *fp, poll_table *wait) { struct posix_clock_context *pccontext = fp->private_data; struct posix_clock *clk = get_posix_clock(fp); __poll_t result = 0; if (!clk) return EPOLLERR; if (clk->ops.poll) result = clk->ops.poll(pccontext, fp, wait); put_posix_clock(clk); return result; } static long posix_clock_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { struct posix_clock_context *pccontext = fp->private_data; struct posix_clock *clk = get_posix_clock(fp); int err = -ENOTTY; if (!clk) return -ENODEV; if (clk->ops.ioctl) err = clk->ops.ioctl(pccontext, cmd, arg); put_posix_clock(clk); return err; } static int posix_clock_open(struct inode *inode, struct file *fp) { int err; struct posix_clock *clk = container_of(inode->i_cdev, struct posix_clock, cdev); struct posix_clock_context *pccontext; down_read(&clk->rwsem); if (clk->zombie) { err = -ENODEV; goto out; } pccontext = kzalloc(sizeof(*pccontext), GFP_KERNEL); if (!pccontext) { err = -ENOMEM; goto out; } pccontext->clk = clk; pccontext->fp = fp; if (clk->ops.open) { err = clk->ops.open(pccontext, fp->f_mode); if (err) { kfree(pccontext); goto out; } } fp->private_data = pccontext; get_device(clk->dev); err = 0; out: up_read(&clk->rwsem); return err; } static int posix_clock_release(struct inode *inode, struct file *fp) { struct posix_clock_context *pccontext = fp->private_data; struct posix_clock *clk; int err = 0; if (!pccontext) return -ENODEV; clk = pccontext->clk; if (clk->ops.release) err = clk->ops.release(pccontext); put_device(clk->dev); kfree(pccontext); fp->private_data = NULL; return err; } static const struct file_operations posix_clock_file_operations = { .owner = THIS_MODULE, .read = posix_clock_read, .poll = posix_clock_poll, .unlocked_ioctl = posix_clock_ioctl, .compat_ioctl = posix_clock_ioctl, .open = posix_clock_open, .release = posix_clock_release, }; int posix_clock_register(struct posix_clock *clk, struct device *dev) { int err; init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); err = cdev_device_add(&clk->cdev, dev); if (err) { pr_err("%s unable to add device %d:%d\n", dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt)); return err; } clk->cdev.owner = clk->ops.owner; clk->dev = dev; return 0; } EXPORT_SYMBOL_GPL(posix_clock_register); void posix_clock_unregister(struct posix_clock *clk) { cdev_device_del(&clk->cdev, clk->dev); down_write(&clk->rwsem); clk->zombie = true; up_write(&clk->rwsem); put_device(clk->dev); } EXPORT_SYMBOL_GPL(posix_clock_unregister); struct posix_clock_desc { struct file *fp; struct posix_clock *clk; }; static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd) { struct file *fp = fget(clockid_to_fd(id)); int err = -EINVAL; if (!fp) return err; if (fp->f_op->open != posix_clock_open || !fp->private_data) goto out; cd->fp = fp; cd->clk = get_posix_clock(fp); err = cd->clk ? 0 : -ENODEV; out: if (err) fput(fp); return err; } static void put_clock_desc(struct posix_clock_desc *cd) { put_posix_clock(cd->clk); fput(cd->fp); } static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx) { struct posix_clock_desc cd; int err; err = get_clock_desc(id, &cd); if (err) return err; if (tx->modes && (cd.fp->f_mode & FMODE_WRITE) == 0) { err = -EACCES; goto out; } if (cd.clk->ops.clock_adjtime) err = cd.clk->ops.clock_adjtime(cd.clk, tx); else err = -EOPNOTSUPP; out: put_clock_desc(&cd); return err; } static int pc_clock_gettime(clockid_t id, struct timespec64 *ts) { struct posix_clock_desc cd; int err; err = get_clock_desc(id, &cd); if (err) return err; if (cd.clk->ops.clock_gettime) err = cd.clk->ops.clock_gettime(cd.clk, ts); else err = -EOPNOTSUPP; put_clock_desc(&cd); return err; } static int pc_clock_getres(clockid_t id, struct timespec64 *ts) { struct posix_clock_desc cd; int err; err = get_clock_desc(id, &cd); if (err) return err; if (cd.clk->ops.clock_getres) err = cd.clk->ops.clock_getres(cd.clk, ts); else err = -EOPNOTSUPP; put_clock_desc(&cd); return err; } static int pc_clock_settime(clockid_t id, const struct timespec64 *ts) { struct posix_clock_desc cd; int err; if (!timespec64_valid_strict(ts)) return -EINVAL; err = get_clock_desc(id, &cd); if (err) return err; if ((cd.fp->f_mode & FMODE_WRITE) == 0) { err = -EACCES; goto out; } if (cd.clk->ops.clock_settime) err = cd.clk->ops.clock_settime(cd.clk, ts); else err = -EOPNOTSUPP; out: put_clock_desc(&cd); return err; } const struct k_clock clock_posix_dynamic = { .clock_getres = pc_clock_getres, .clock_set = pc_clock_settime, .clock_get_timespec = pc_clock_gettime, .clock_adj = pc_clock_adjtime, }; |
| 2528 3 3 3 3 3 3 3 110 104 2 107 3 3 2 3 1 3 110 109 109 1 109 1 1 2420 2430 2422 2416 2401 1439 1653 1651 1654 1653 1652 1649 1051 1052 1054 137 16 140 138 16 139 151 6 1052 1052 1055 1052 8 8 8 3 5 1727 2432 2384 2380 1057 1050 256 1055 1649 1651 1653 1652 1650 1653 1648 1 2 1652 5 5 3 1 1 4 1653 1651 1 1649 3 7 1646 1747 1745 1738 1733 1749 1354 1347 34 188 1648 1653 1 182 11 179 178 179 180 64 65 27 47 46 9 1 8 8 7 7 1 6 6 4 4 2 2 2 2 2 2355 2353 2349 2355 2355 2351 212 238 1648 1654 1648 1653 1650 8 1655 1052 1049 1052 1051 1054 1053 1054 1055 1051 1048 1053 6 1053 1051 1051 18 18 17 14 3 1322 562 1035 2 13 11 10 10 2 11 10 2 13 9 22 22 22 13 2 9 13 13 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/dir.c - kernfs directory implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/hash.h> #include "kernfs-internal.h" /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() * will perform wakeups when releasing console_sem. Holding rename_lock * will introduce deadlock if the scheduler reads the kernfs_name in the * wakeup path. */ static DEFINE_SPINLOCK(kernfs_pr_cont_lock); static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) static bool __kernfs_active(struct kernfs_node *kn) { return atomic_read(&kn->active) >= 0; } static bool kernfs_active(struct kernfs_node *kn) { lockdep_assert_held(&kernfs_root(kn)->kernfs_rwsem); return __kernfs_active(kn); } static bool kernfs_lockdep(struct kernfs_node *kn) { #ifdef CONFIG_DEBUG_LOCK_ALLOC return kn->flags & KERNFS_LOCKDEP; #else return false; #endif } /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; while (rcu_dereference(to->__parent) && to != from) { depth++; to = rcu_dereference(to->__parent); } return depth; } static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, struct kernfs_node *b) { size_t da, db; struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b); if (ra != rb) return NULL; da = kernfs_depth(ra->kn, a); db = kernfs_depth(rb->kn, b); while (da > db) { a = rcu_dereference(a->__parent); da--; } while (db > da) { b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { b = rcu_dereference(b->__parent); a = rcu_dereference(a->__parent); } return a; } /** * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to, * where kn_from is treated as root of the path. * @kn_from: kernfs node which should be treated as root for the path * @kn_to: kernfs node to which path is needed * @buf: buffer to copy the path into * @buflen: size of @buf * * We need to handle couple of scenarios here: * [1] when @kn_from is an ancestor of @kn_to at some level * kn_from: /n1/n2/n3 * kn_to: /n1/n2/n3/n4/n5 * result: /n4/n5 * * [2] when @kn_from is on a different hierarchy and we need to find common * ancestor between @kn_from and @kn_to. * kn_from: /n1/n2/n3/n4 * kn_to: /n1/n2/n5 * result: /../../n5 * OR * kn_from: /n1/n2/n3/n4/n5 [depth=5] * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * * [3] when @kn_to is %NULL result will be "(null)" * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen) { struct kernfs_node *kn, *common; const char parent_str[] = "/.."; size_t depth_from, depth_to, len = 0; ssize_t copied; int i, j; if (!kn_to) return strscpy(buf, "(null)", buflen); if (!kn_from) kn_from = kernfs_root(kn_to)->kn; if (kn_from == kn_to) return strscpy(buf, "/", buflen); common = kernfs_common_ancestor(kn_from, kn_to); if (WARN_ON(!common)) return -EINVAL; depth_to = kernfs_depth(common, kn_to); depth_from = kernfs_depth(common, kn_from); buf[0] = '\0'; for (i = 0; i < depth_from; i++) { copied = strscpy(buf + len, parent_str, buflen - len); if (copied < 0) return copied; len += copied; } /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { const char *name; for (kn = kn_to, j = 0; j < i; j++) kn = rcu_dereference(kn->__parent); name = rcu_dereference(kn->name); len += scnprintf(buf + len, buflen - len, "/%s", name); } return len; } /** * kernfs_name - obtain the name of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is * similar to strscpy(). * * Fills buffer with "(null)" if @kn is %NULL. * * Return: the resulting length of @buf. If @buf isn't long enough, * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { struct kernfs_node *kn_parent; if (!kn) return strscpy(buf, "(null)", buflen); guard(rcu)(); /* * KERNFS_ROOT_INVARIANT_PARENT is ignored here. The name is RCU freed and * the parent is either existing or not. */ kn_parent = rcu_dereference(kn->__parent); return strscpy(buf, kn_parent ? rcu_dereference(kn->name) : "/", buflen); } /** * kernfs_path_from_node - build path of node @to relative to @from. * @from: parent kernfs_node relative to which we need to build the path * @to: kernfs_node of interest * @buf: buffer to copy @to's path into * @buflen: size of @buf * * Builds @to's path relative to @from in @buf. @from and @to must * be on the same kernfs-root. If @from is not parent of @to, then a relative * path (which includes '..'s) as needed to reach from @from to @to is * returned. * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { struct kernfs_root *root; guard(rcu)(); if (to) { root = kernfs_root(to); if (!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)) { guard(read_lock_irqsave)(&root->kernfs_rename_lock); return kernfs_path_from_node_locked(to, from, buf, buflen); } } return kernfs_path_from_node_locked(to, from, buf, buflen); } EXPORT_SYMBOL_GPL(kernfs_path_from_node); /** * pr_cont_kernfs_name - pr_cont name of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_name(struct kernfs_node *kn) { unsigned long flags; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); pr_cont("%s", kernfs_pr_cont_buf); spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * pr_cont_kernfs_path - pr_cont path of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_path(struct kernfs_node *kn) { unsigned long flags; int sz; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); if (sz < 0) { if (sz == -E2BIG) pr_cont("(name too long)"); else pr_cont("(error)"); goto out; } pr_cont("%s", kernfs_pr_cont_buf); out: spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * kernfs_get_parent - determine the parent node and pin it * @kn: kernfs_node of interest * * Determines @kn's parent, pins and returns it. This function can be * called from any context. * * Return: parent node of @kn */ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; unsigned long flags; root = kernfs_root(kn); read_lock_irqsave(&root->kernfs_rename_lock, flags); parent = kernfs_parent(kn); kernfs_get(parent); read_unlock_irqrestore(&root->kernfs_rename_lock, flags); return parent; } /** * kernfs_name_hash - calculate hash of @ns + @name * @name: Null terminated string to hash * @ns: Namespace tag to hash * * Return: 31-bit hash of ns + name (so it fits in an off_t) */ static unsigned int kernfs_name_hash(const char *name, const void *ns) { unsigned long hash = init_name_hash(ns); unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); hash = end_name_hash(hash); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; return hash; } static int kernfs_name_compare(unsigned int hash, const char *name, const void *ns, const struct kernfs_node *kn) { if (hash < kn->hash) return -1; if (hash > kn->hash) return 1; if (ns < kn->ns) return -1; if (ns > kn->ns) return 1; return strcmp(name, kernfs_rcu_name(kn)); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { return kernfs_name_compare(left->hash, kernfs_rcu_name(left), left->ns, right); } /** * kernfs_link_sibling - link kernfs_node into sibling rbtree * @kn: kernfs_node of interest * * Link @kn into its sibling rbtree which starts from * @kn->parent->dir.children. * * Locking: * kernfs_rwsem held exclusive * * Return: * %0 on success, -EEXIST on failure. */ static int kernfs_link_sibling(struct kernfs_node *kn) { struct rb_node *parent = NULL; struct kernfs_node *kn_parent; struct rb_node **node; kn_parent = kernfs_parent(kn); node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; int result; pos = rb_to_kn(*node); parent = *node; result = kernfs_sd_compare(kn, pos); if (result < 0) node = &pos->rb.rb_left; else if (result > 0) node = &pos->rb.rb_right; else return -EEXIST; } /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) kn_parent->dir.subdirs++; kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; } /** * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree * @kn: kernfs_node of interest * * Try to unlink @kn from its sibling rbtree which starts from * kn->parent->dir.children. * * Return: %true if @kn was actually removed, * %false if @kn wasn't on the rbtree. * * Locking: * kernfs_rwsem held exclusive */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { struct kernfs_node *kn_parent; if (RB_EMPTY_NODE(&kn->rb)) return false; kn_parent = kernfs_parent(kn); down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) kn_parent->dir.subdirs--; kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } /** * kernfs_get_active - get an active reference to kernfs_node * @kn: kernfs_node to get an active reference to * * Get an active reference of @kn. This function is noop if @kn * is %NULL. * * Return: * Pointer to @kn on success, %NULL on failure. */ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) { if (unlikely(!kn)) return NULL; if (!atomic_inc_unless_negative(&kn->active)) return NULL; if (kernfs_lockdep(kn)) rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); return kn; } /** * kernfs_put_active - put an active reference to kernfs_node * @kn: kernfs_node to put an active reference to * * Put an active reference to @kn. This function is noop if @kn * is %NULL. */ void kernfs_put_active(struct kernfs_node *kn) { int v; if (unlikely(!kn)) return; if (kernfs_lockdep(kn)) rwsem_release(&kn->dep_map, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; wake_up_all(&kernfs_root(kn)->deactivate_waitq); } /** * kernfs_drain - drain kernfs_node * @kn: kernfs_node to drain * * Drain existing usages and nuke all existing mmaps of @kn. Multiple * removers may invoke this function concurrently on @kn and all will * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) __releases(&kernfs_root(kn)->kernfs_rwsem) __acquires(&kernfs_root(kn)->kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); lockdep_assert_held_write(&root->kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); /* * Skip draining if already fully drained. This avoids draining and its * lockdep annotations for nodes which have never been activated * allowing embedding kernfs_remove() in create error paths without * worrying about draining. */ if (atomic_read(&kn->active) == KN_DEACTIVATED_BIAS && !kernfs_should_drain_open_files(kn)) return; up_write(&root->kernfs_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) lock_contended(&kn->dep_map, _RET_IP_); } wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); if (kernfs_lockdep(kn)) { lock_acquired(&kn->dep_map, _RET_IP_); rwsem_release(&kn->dep_map, _RET_IP_); } if (kernfs_should_drain_open_files(kn)) kernfs_drain_open_files(kn); down_write(&root->kernfs_rwsem); } /** * kernfs_get - get a reference count on a kernfs_node * @kn: the target kernfs_node */ void kernfs_get(struct kernfs_node *kn) { if (kn) { WARN_ON(!atomic_read(&kn->count)); atomic_inc(&kn->count); } } EXPORT_SYMBOL_GPL(kernfs_get); static void kernfs_free_rcu(struct rcu_head *rcu) { struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu); /* If the whole node goes away, then name can't be used outside */ kfree_const(rcu_access_pointer(kn->name)); if (kn->iattr) { simple_xattrs_free(&kn->iattr->xattrs, NULL); kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } kmem_cache_free(kernfs_node_cache, kn); } /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node * * Put a reference count of @kn and destroy it if it reached zero. */ void kernfs_put(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; if (!kn || !atomic_dec_and_test(&kn->count)) return; root = kernfs_root(kn); repeat: /* * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", parent ? rcu_dereference(parent->name) : "", rcu_dereference(kn->name), atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&root->kernfs_idr_lock); call_rcu(&kn->rcu, kernfs_free_rcu); kn = parent; if (kn) { if (atomic_dec_and_test(&kn->count)) goto repeat; } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); kfree_rcu(root, rcu); } } EXPORT_SYMBOL_GPL(kernfs_put); /** * kernfs_node_from_dentry - determine kernfs_node associated with a dentry * @dentry: the dentry in question * * Return: the kernfs_node associated with @dentry. If @dentry is not a * kernfs one, %NULL is returned. * * While the returned kernfs_node will stay accessible as long as @dentry * is accessible, the returned node can be in any state and the caller is * fully responsible for determining what's accessible. */ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { if (dentry->d_sb->s_op == &kernfs_sops) return kernfs_dentry_node(dentry); return NULL; } static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; u32 id_highbits; int ret; name = kstrdup_const(name, GFP_KERNEL); if (!name) return NULL; kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL); if (!kn) goto err_out1; idr_preload(GFP_KERNEL); spin_lock(&root->kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); if (ret >= 0 && ret < root->last_id_lowbits) root->id_highbits++; id_highbits = root->id_highbits; root->last_id_lowbits = ret; spin_unlock(&root->kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; kn->id = (u64)id_highbits << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); rcu_assign_pointer(kn->name, name); kn->mode = mode; kn->flags = flags; if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = uid, .ia_gid = gid, }; ret = __kernfs_setattr(kn, &iattr); if (ret < 0) goto err_out3; } if (parent) { ret = security_kernfs_init_security(parent, kn); if (ret) goto err_out3; } return kn; err_out3: spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&root->kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: kfree_const(name); return NULL; } struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; if (parent->mode & S_ISGID) { /* this code block imitates inode_init_owner() for * kernfs */ if (parent->iattr) gid = parent->iattr->ia_gid; if (flags & KERNFS_DIR) mode |= S_ISGID; } kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); rcu_assign_pointer(kn->__parent, parent); } return kn; } /* * kernfs_find_and_get_node_by_id - get kernfs_node from node id * @root: the kernfs root * @id: the target node id * * @id's lower 32bits encode ino and upper gen. If the gen portion is * zero, all generations are matched. * * Return: %NULL on failure, * otherwise a kernfs node with reference counter incremented. */ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); rcu_read_lock(); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) goto err_unlock; if (sizeof(ino_t) >= sizeof(u64)) { /* we looked up with the low 32bits, compare the whole */ if (kernfs_ino(kn) != ino) goto err_unlock; } else { /* 0 matches all generations */ if (unlikely(gen && kernfs_gen(kn) != gen)) goto err_unlock; } /* * We should fail if @kn has never been activated and guarantee success * if the caller knows that @kn is active. Both can be achieved by * __kernfs_active() which tests @kn->active without kernfs_rwsem. */ if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; rcu_read_unlock(); return kn; err_unlock: rcu_read_unlock(); return NULL; } /** * kernfs_add_one - add kernfs_node to parent without warning * @kn: kernfs_node to be added * * The caller must already have initialized @kn->parent. This * function increments nlink of the parent's inode if @kn is a * directory and link into the children list of the parent. * * Return: * %0 on success, -EEXIST if entry with the given name already * exists. */ int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", kernfs_rcu_name(parent), kernfs_rcu_name(kn))) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) goto out_unlock; ret = -ENOENT; if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR)) goto out_unlock; kn->hash = kernfs_name_hash(kernfs_rcu_name(kn), kn->ns); ret = kernfs_link_sibling(kn); if (ret) goto out_unlock; /* Update timestamps on the parent */ down_write(&root->kernfs_iattr_rwsem); ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } up_write(&root->kernfs_iattr_rwsem); up_write(&root->kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. * If not activated here, the kernfs user is responsible for * activating the node with kernfs_activate(). A node which hasn't * been activated is not visible to userland and its removal won't * trigger deactivation. */ if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return 0; out_unlock: up_write(&root->kernfs_rwsem); return ret; } /** * kernfs_find_ns - find kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, const unsigned char *name, const void *ns) { struct rb_node *node = parent->dir.children.rb_node; bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; lockdep_assert_held(&kernfs_root(parent)->kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", kernfs_rcu_name(parent), name); return NULL; } hash = kernfs_name_hash(name, ns); while (node) { struct kernfs_node *kn; int result; kn = rb_to_kn(node); result = kernfs_name_compare(hash, name, ns, kn); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return kn; } return NULL; } static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const void *ns) { ssize_t len; char *p, *name; lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); if (len < 0) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } p = kernfs_pr_cont_buf; while ((name = strsep(&p, "/")) && parent) { if (*name == '\0') continue; parent = kernfs_find_ns(parent, name, ns); } spin_unlock_irq(&kernfs_pr_cont_lock); return parent; } /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** * kernfs_walk_and_get_ns - find and get kernfs_node with the given path * @parent: kernfs_node to search under * @path: path to look for * @ns: the namespace tag to use * * Look for kernfs_node with path @path under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } unsigned int kernfs_root_flags(struct kernfs_node *kn) { return kernfs_root(kn)->flags; } /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags * @priv: opaque data associated with the new directory * * Return: the root of the new hierarchy on success, ERR_PTR() value on * failure. */ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { struct kernfs_root *root; struct kernfs_node *kn; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); spin_lock_init(&root->kernfs_idr_lock); init_rwsem(&root->kernfs_rwsem); init_rwsem(&root->kernfs_iattr_rwsem); init_rwsem(&root->kernfs_supers_rwsem); INIT_LIST_HEAD(&root->supers); rwlock_init(&root->kernfs_rename_lock); /* * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. * High bits generation. The starting value for both ino and * genenration is 1. Initialize upper 32bit allocation * accordingly. */ if (sizeof(ino_t) >= sizeof(u64)) root->id_highbits = 0; else root->id_highbits = 1; kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { idr_destroy(&root->ino_idr); kfree(root); return ERR_PTR(-ENOMEM); } kn->priv = priv; kn->dir.root = root; root->syscall_ops = scops; root->flags = flags; root->kn = kn; init_waitqueue_head(&root->deactivate_waitq); if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return root; } /** * kernfs_destroy_root - destroy a kernfs hierarchy * @root: root of the hierarchy to destroy * * Destroy the hierarchy anchored at @root by removing all existing * directories and destroying @root. */ void kernfs_destroy_root(struct kernfs_root *root) { /* * kernfs_remove holds kernfs_rwsem from the root so the root * shouldn't be freed during the operation. */ kernfs_get(root->kn); kernfs_remove(root->kn); kernfs_put(root->kn); /* will also free @root */ } /** * kernfs_root_to_node - return the kernfs_node associated with a kernfs_root * @root: root to use to lookup * * Return: @root's kernfs_node */ struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root) { return root->kn; } /** * kernfs_create_dir_ns - create a directory * @parent: parent in which to create a new directory * @name: name of the new directory * @mode: mode of the new directory * @uid: uid of the new directory * @gid: gid of the new directory * @priv: opaque data associated with the new directory * @ns: optional namespace tag of the directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, mode | S_IFDIR, uid, gid, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->dir.root = parent->dir.root; kn->ns = ns; kn->priv = priv; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } /** * kernfs_create_empty_dir - create an always empty directory * @parent: parent in which to create a new directory * @name: name of the new directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->flags |= KERNFS_EMPTY_DIR; kn->dir.root = parent->dir.root; kn->ns = NULL; kn->priv = NULL; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) return -ECHILD; /* Negative hashed dentry? */ if (d_really_is_negative(dentry)) { /* If the kernfs parent node has changed discard and * proceed to ->lookup. * * There's nothing special needed here when getting the * dentry parent, even if a concurrent rename is in * progress. That's because the dentry is negative so * it can only be the target of the rename and it will * be doing a d_move() not a replace. Consequently the * dentry d_parent won't change over the d_move(). * * Also kernfs negative dentries transitioning from * negative to positive during revalidate won't happen * because they are invalidated on containing directory * changes and the lookup re-done so that a new positive * dentry can be properly created. */ root = kernfs_root_from_sb(dentry->d_sb); down_read(&root->kernfs_rwsem); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { if (kernfs_dir_changed(parent, dentry)) { up_read(&root->kernfs_rwsem); return 0; } } up_read(&root->kernfs_rwsem); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. */ return 1; } kn = kernfs_dentry_node(dentry); root = kernfs_root(kn); down_read(&root->kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) goto out_bad; parent = kernfs_parent(kn); /* The kernfs node has been moved? */ if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ if (strcmp(dentry->d_name.name, kernfs_rcu_name(kn)) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ if (parent && kernfs_ns_enabled(parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; up_read(&root->kernfs_rwsem); return 1; out_bad: up_read(&root->kernfs_rwsem); return 0; } const struct dentry_operations kernfs_dops = { .d_revalidate = kernfs_dop_revalidate, }; static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct kernfs_root *root; struct inode *inode = NULL; const void *ns = NULL; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* attach dentry and inode */ if (kn) { /* Inactive nodes are invisible to the VFS so don't * create a negative. */ if (!kernfs_active(kn)) { up_read(&root->kernfs_rwsem); return NULL; } inode = kernfs_get_inode(dir->i_sb, kn); if (!inode) inode = ERR_PTR(-ENOMEM); } /* * Needed for negative dentry validation. * The negative dentry can be created in kernfs_iop_lookup() * or transforms from positive dentry in dentry_unlink_inode() * called from vfs_rmdir(). */ if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&root->kernfs_rwsem); /* instantiate and hash (possibly negative) dentry */ return d_splice_alias(inode, dentry); } static struct dentry *kernfs_iop_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) return ERR_PTR(-EPERM); if (!kernfs_get_active(parent)) return ERR_PTR(-ENODEV); ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); return ERR_PTR(ret); } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (!scops || !scops->rmdir) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; ret = scops->rmdir(kn); kernfs_put_active(kn); return ret; } static int kernfs_iop_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct kernfs_node *kn = kernfs_dentry_node(old_dentry); struct kernfs_node *new_parent = new_dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (flags) return -EINVAL; if (!scops || !scops->rename) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; if (!kernfs_get_active(new_parent)) { kernfs_put_active(kn); return -ENODEV; } ret = scops->rename(kn, new_parent, new_dentry->d_name.name); kernfs_put_active(new_parent); kernfs_put_active(kn); return ret; } const struct inode_operations kernfs_dir_iops = { .lookup = kernfs_iop_lookup, .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .listxattr = kernfs_iop_listxattr, .mkdir = kernfs_iop_mkdir, .rmdir = kernfs_iop_rmdir, .rename = kernfs_iop_rename, }; static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos) { struct kernfs_node *last; while (true) { struct rb_node *rbn; last = pos; if (kernfs_type(pos) != KERNFS_DIR) break; rbn = rb_first(&pos->dir.children); if (!rbn) break; pos = rb_to_kn(rbn); } return last; } /** * kernfs_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: kernfs_node whose descendants to walk * * Find the next descendant to visit for post-order traversal of @root's * descendants. @root is included in the iteration and the last node to be * visited. * * Return: the next descendant to visit or %NULL when done. */ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, struct kernfs_node *root) { struct rb_node *rbn; lockdep_assert_held_write(&kernfs_root(root)->kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) return kernfs_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ rbn = rb_next(&pos->rb); if (rbn) return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) { lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); kn->flags |= KERNFS_ACTIVATED; if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); } /** * kernfs_activate - activate a node which started deactivated * @kn: kernfs_node whose subtree is to be activated * * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node * needs to be explicitly activated. A node which hasn't been activated * isn't visible to userland and deactivation is skipped during its * removal. This is useful to construct atomic init sequences where * creation of multiple nodes should either succeed or fail atomically. * * The caller is responsible for ensuring that this function is not called * after kernfs_remove*() is invoked on @kn. */ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; struct kernfs_root *root = kernfs_root(kn); down_write(&root->kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) kernfs_activate_one(pos); up_write(&root->kernfs_rwsem); } /** * kernfs_show - show or hide a node * @kn: kernfs_node to show or hide * @show: whether to show or hide * * If @show is %false, @kn is marked hidden and deactivated. A hidden node is * ignored in future activaitons. If %true, the mark is removed and activation * state is restored. This function won't implicitly activate a new node in a * %KERNFS_ROOT_CREATE_DEACTIVATED root which hasn't been activated yet. * * To avoid recursion complexities, directories aren't supported for now. */ void kernfs_show(struct kernfs_node *kn, bool show) { struct kernfs_root *root = kernfs_root(kn); if (WARN_ON_ONCE(kernfs_type(kn) == KERNFS_DIR)) return; down_write(&root->kernfs_rwsem); if (show) { kn->flags &= ~KERNFS_HIDDEN; if (kn->flags & KERNFS_ACTIVATED) kernfs_activate_one(kn); } else { kn->flags |= KERNFS_HIDDEN; if (kernfs_active(kn)) atomic_add(KN_DEACTIVATED_BIAS, &kn->active); kernfs_drain(kn); } up_write(&root->kernfs_rwsem); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) return; lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); /* * This is for kernfs_remove_self() which plays with active ref * after removal. */ if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; pr_debug("kernfs %s: removing\n", kernfs_rcu_name(kn)); /* prevent new usage by marking all nodes removing and deactivating */ pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { pos->flags |= KERNFS_REMOVING; if (kernfs_active(pos)) atomic_add(KN_DEACTIVATED_BIAS, &pos->active); } /* deactivate and unlink the subtree node-by-node */ do { pos = kernfs_leftmost_descendant(kn); /* * kernfs_drain() may drop kernfs_rwsem temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. */ kernfs_get(pos); kernfs_drain(pos); parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = parent ? parent->iattr : NULL; /* update timestamps on the parent */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_put(pos); } kernfs_put(pos); } while (pos != kn); } /** * kernfs_remove - remove a kernfs_node recursively * @kn: the kernfs_node to remove * * Remove @kn along with all its subdirectories and files. */ void kernfs_remove(struct kernfs_node *kn) { struct kernfs_root *root; if (!kn) return; root = kernfs_root(kn); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); up_write(&root->kernfs_rwsem); } /** * kernfs_break_active_protection - break out of active protection * @kn: the self kernfs_node * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. Each invocation of * this function must also be matched with an invocation of * kernfs_unbreak_active_protection(). * * This function releases the active reference of @kn the caller is * holding. Once this function is called, @kn may be removed at any point * and the caller is solely responsible for ensuring that the objects it * dereferences are accessible. */ void kernfs_break_active_protection(struct kernfs_node *kn) { /* * Take out ourself out of the active ref dependency chain. If * we're called without an active ref, lockdep will complain. */ kernfs_put_active(kn); } /** * kernfs_unbreak_active_protection - undo kernfs_break_active_protection() * @kn: the self kernfs_node * * If kernfs_break_active_protection() was called, this function must be * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of * being drained and removed. Once kernfs_break_active_protection() is * invoked, that protection is irreversibly gone for the kernfs operation * instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location * would be right before the enclosing kernfs operation returns. */ void kernfs_unbreak_active_protection(struct kernfs_node *kn) { /* * @kn->active could be in any state; however, the increment we do * here will be undone as soon as the enclosing kernfs operation * finishes and this temporary bump can't break anything. If @kn * is alive, nothing changes. If @kn is being deactivated, the * soon-to-follow put will either finish deactivation or restore * deactivated state. If @kn is already removed, the temporary * bump is guaranteed to be gone before @kn is released. */ atomic_inc(&kn->active); if (kernfs_lockdep(kn)) rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_); } /** * kernfs_remove_self - remove a kernfs_node from its own method * @kn: the self kernfs_node to remove * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. This can be used to * implement a file operation which deletes itself. * * For example, the "delete" file for a sysfs device directory can be * implemented by invoking kernfs_remove_self() on the "delete" file * itself. This function breaks the circular dependency of trying to * deactivate self while holding an active ref itself. It isn't necessary * to modify the usual removal path to use kernfs_remove_self(). The * "delete" implementation can simply invoke kernfs_remove_self() on self * before proceeding with the usual removal path. kernfs will ignore later * kernfs_remove() on self. * * kernfs_remove_self() can be called multiple times concurrently on the * same kernfs_node. Only the first one actually performs removal and * returns %true. All others will wait until the kernfs operation which * won self-removal finishes and return %false. Note that the losers wait * for the completion of not only the winning kernfs_remove_self() but also * the whole kernfs_ops which won the arbitration. This can be used to * guarantee, for example, all concurrent writes to a "delete" file to * finish only after the whole operation is complete. * * Return: %true if @kn is removed by this call, otherwise %false. */ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; struct kernfs_root *root = kernfs_root(kn); down_write(&root->kernfs_rwsem); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored * while kernfs_rwsem for held exclusive. The ones which lost * arbitration waits for SUICIDED && drained which can happen only * after the enclosing kernfs operation which executed the winning * instance of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; __kernfs_remove(kn); kn->flags |= KERNFS_SUICIDED; ret = true; } else { wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq; DEFINE_WAIT(wait); while (true) { prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE); if ((kn->flags & KERNFS_SUICIDED) && atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; up_write(&root->kernfs_rwsem); schedule(); down_write(&root->kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); ret = false; } /* * This must be done while kernfs_rwsem held exclusive; otherwise, * waiting for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); up_write(&root->kernfs_rwsem); return ret; } /** * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it * @parent: parent of the target * @name: name of the kernfs_node to remove * @ns: namespace tag of the kernfs_node to remove * * Look for the kernfs_node with @name and @ns under @parent and remove it. * * Return: %0 on success, -ENOENT if such entry doesn't exist. */ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root; if (!parent) { WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", name); return -ENOENT; } root = kernfs_root(parent); down_write(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) { kernfs_get(kn); __kernfs_remove(kn); kernfs_put(kn); } up_write(&root->kernfs_rwsem); if (kn) return 0; else return -ENOENT; } /** * kernfs_rename_ns - move and rename a kernfs_node * @kn: target node * @new_parent: new parent to put @sd under * @new_name: new name * @new_ns: new namespace tag * * Return: %0 on success, -errno on failure. */ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { struct kernfs_node *old_parent; struct kernfs_root *root; const char *old_name; int error; /* can't move or rename root */ if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); down_write(&root->kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; old_parent = kernfs_parent(kn); if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { error = -EINVAL; if (WARN_ON_ONCE(old_parent != new_parent)) goto out; } error = 0; old_name = kernfs_rcu_name(kn); if (!new_name) new_name = old_name; if ((old_parent == new_parent) && (kn->ns == new_ns) && (strcmp(old_name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; if (kernfs_find_ns(new_parent, new_name, new_ns)) goto out; /* rename kernfs_node */ if (strcmp(old_name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) goto out; } else { new_name = NULL; } /* * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); /* rename_lock protects ->parent accessors */ if (old_parent != new_parent) { kernfs_get(new_parent); write_lock_irq(&root->kernfs_rename_lock); rcu_assign_pointer(kn->__parent, new_parent); kn->ns = new_ns; if (new_name) rcu_assign_pointer(kn->name, new_name); write_unlock_irq(&root->kernfs_rename_lock); kernfs_put(old_parent); } else { /* name assignment is RCU protected, parent is the same */ kn->ns = new_ns; if (new_name) rcu_assign_pointer(kn->name, new_name); } kn->hash = kernfs_name_hash(new_name ?: old_name, kn->ns); kernfs_link_sibling(kn); if (new_name && !is_kernel_rodata((unsigned long)old_name)) kfree_rcu_mightsleep(old_name); error = 0; out: up_write(&root->kernfs_rwsem); return error; } static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); return 0; } static struct kernfs_node *kernfs_dir_pos(const void *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { int valid = kernfs_active(pos) && rcu_access_pointer(pos->__parent) == parent && hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; } if (!pos && (hash > 1) && (hash < INT_MAX)) { struct rb_node *node = parent->dir.children.rb_node; while (node) { pos = rb_to_kn(node); if (hash < pos->hash) node = node->rb_left; else if (hash > pos->hash) node = node->rb_right; else break; } } /* Skip over entries which are dying/dead or in the wrong namespace */ while (pos && (!kernfs_active(pos) || pos->ns != ns)) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } return pos; } static struct kernfs_node *kernfs_dir_next_pos(const void *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); if (pos) { do { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } while (pos && (!kernfs_active(pos) || pos->ns != ns)); } return pos; } static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; struct kernfs_root *root; const void *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { const char *name = kernfs_rcu_name(pos); unsigned int type = fs_umode_to_dtype(pos->mode); int len = strlen(name); ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; kernfs_get(pos); if (!dir_emit(ctx, name, len, ino, type)) { up_read(&root->kernfs_rwsem); return 0; } } up_read(&root->kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; } const struct file_operations kernfs_dir_fops = { .read = generic_read_dir, .iterate_shared = kernfs_fop_readdir, .release = kernfs_dir_fop_release, .llseek = generic_file_llseek, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ALSA sequencer Ports * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> */ #ifndef __SND_SEQ_PORTS_H #define __SND_SEQ_PORTS_H #include <sound/seq_kernel.h> #include <sound/ump_convert.h> #include "seq_lock.h" /* list of 'exported' ports */ /* Client ports that are not exported are still accessible, but are anonymous ports. If a port supports SUBSCRIPTION, that port can send events to all subscribersto a special address, with address (queue==SNDRV_SEQ_ADDRESS_SUBSCRIBERS). The message is then send to all recipients that are registered in the subscription list. A typical application for these SUBSCRIPTION events is handling of incoming MIDI data. The port doesn't 'know' what other clients are interested in this message. If for instance a MIDI recording application would like to receive the events from that port, it will first have to subscribe with that port. */ struct snd_seq_subscribers { struct snd_seq_port_subscribe info; /* additional info */ struct list_head src_list; /* link of sources */ struct list_head dest_list; /* link of destinations */ atomic_t ref_count; }; struct snd_seq_port_subs_info { struct list_head list_head; /* list of subscribed ports */ unsigned int count; /* count of subscribers */ unsigned int exclusive: 1; /* exclusive mode */ struct rw_semaphore list_mutex; rwlock_t list_lock; int (*open)(void *private_data, struct snd_seq_port_subscribe *info); int (*close)(void *private_data, struct snd_seq_port_subscribe *info); }; struct snd_seq_client_port { struct snd_seq_addr addr; /* client/port number */ struct module *owner; /* owner of this port */ char name[64]; /* port name */ struct list_head list; /* port list */ snd_use_lock_t use_lock; /* subscribers */ struct snd_seq_port_subs_info c_src; /* read (sender) list */ struct snd_seq_port_subs_info c_dest; /* write (dest) list */ int (*event_input)(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop); void (*private_free)(void *private_data); void *private_data; unsigned int closing : 1; unsigned int timestamping: 1; unsigned int time_real: 1; int time_queue; /* capability, inport, output, sync */ unsigned int capability; /* port capability bits */ unsigned int type; /* port type bits */ /* supported channels */ int midi_channels; int midi_voices; int synth_voices; /* UMP direction and group */ unsigned char direction; unsigned char ump_group; bool is_midi1; /* keep MIDI 1.0 protocol */ #if IS_ENABLED(CONFIG_SND_SEQ_UMP) struct ump_cvt_to_ump_bank midi2_bank[16]; /* per channel */ #endif }; struct snd_seq_client; /* return pointer to port structure and lock port */ struct snd_seq_client_port *snd_seq_port_use_ptr(struct snd_seq_client *client, int num); /* search for next port - port is locked if found */ struct snd_seq_client_port *snd_seq_port_query_nearest(struct snd_seq_client *client, struct snd_seq_port_info *pinfo); /* unlock the port */ #define snd_seq_port_unlock(port) snd_use_lock_free(&(port)->use_lock) DEFINE_FREE(snd_seq_port, struct snd_seq_client_port *, if (!IS_ERR_OR_NULL(_T)) snd_seq_port_unlock(_T)) /* create a port, port number or a negative error code is returned */ int snd_seq_create_port(struct snd_seq_client *client, int port_index, struct snd_seq_client_port **port_ret); /* delete a port */ int snd_seq_delete_port(struct snd_seq_client *client, int port); /* delete all ports */ int snd_seq_delete_all_ports(struct snd_seq_client *client); /* set port info fields */ int snd_seq_set_port_info(struct snd_seq_client_port *port, struct snd_seq_port_info *info); /* get port info fields */ int snd_seq_get_port_info(struct snd_seq_client_port *port, struct snd_seq_port_info *info); /* add subscriber to subscription list */ int snd_seq_port_connect(struct snd_seq_client *caller, struct snd_seq_client *s, struct snd_seq_client_port *sp, struct snd_seq_client *d, struct snd_seq_client_port *dp, struct snd_seq_port_subscribe *info); /* remove subscriber from subscription list */ int snd_seq_port_disconnect(struct snd_seq_client *caller, struct snd_seq_client *s, struct snd_seq_client_port *sp, struct snd_seq_client *d, struct snd_seq_client_port *dp, struct snd_seq_port_subscribe *info); /* subscribe port */ int snd_seq_port_subscribe(struct snd_seq_client_port *port, struct snd_seq_port_subscribe *info); /* get matched subscriber */ int snd_seq_port_get_subscription(struct snd_seq_port_subs_info *src_grp, struct snd_seq_addr *dest_addr, struct snd_seq_port_subscribe *subs); #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017-2018 HUAWEI, Inc. * https://www.huawei.com/ */ #ifndef __EROFS_XATTR_H #define __EROFS_XATTR_H #include "internal.h" #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #ifdef CONFIG_EROFS_FS_XATTR extern const struct xattr_handler erofs_xattr_user_handler; extern const struct xattr_handler erofs_xattr_trusted_handler; extern const struct xattr_handler erofs_xattr_security_handler; static inline const char *erofs_xattr_prefix(unsigned int idx, struct dentry *dentry) { const struct xattr_handler *handler = NULL; static const struct xattr_handler * const xattr_handler_map[] = { [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler, #ifdef CONFIG_EROFS_FS_POSIX_ACL [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler, #ifdef CONFIG_EROFS_FS_SECURITY [EROFS_XATTR_INDEX_SECURITY] = &erofs_xattr_security_handler, #endif }; if (idx && idx < ARRAY_SIZE(xattr_handler_map)) handler = xattr_handler_map[idx]; if (!xattr_handler_can_list(handler, dentry)) return NULL; return xattr_prefix(handler); } extern const struct xattr_handler * const erofs_xattr_handlers[]; int erofs_xattr_prefixes_init(struct super_block *sb); void erofs_xattr_prefixes_cleanup(struct super_block *sb); int erofs_getxattr(struct inode *, int, const char *, void *, size_t); ssize_t erofs_listxattr(struct dentry *, char *, size_t); #else static inline int erofs_xattr_prefixes_init(struct super_block *sb) { return 0; } static inline void erofs_xattr_prefixes_cleanup(struct super_block *sb) {} static inline int erofs_getxattr(struct inode *inode, int index, const char *name, void *buffer, size_t buffer_size) { return -EOPNOTSUPP; } #define erofs_listxattr (NULL) #define erofs_xattr_handlers (NULL) #endif /* !CONFIG_EROFS_FS_XATTR */ #ifdef CONFIG_EROFS_FS_POSIX_ACL struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu); #else #define erofs_get_acl (NULL) #endif #endif |
| 1848 4020 1573 1889 4698 4210 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @bucket_expiry: the bucket expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long bucket_expiry), TP_ARGS(timer, bucket_expiry), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, bucket_expiry ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = timer->expires; __entry->bucket_expiry = bucket_expiry; __entry->now = jiffies; __entry->flags = timer->flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); TRACE_EVENT(timer_base_idle, TP_PROTO(bool is_idle, unsigned int cpu), TP_ARGS(is_idle, cpu), TP_STRUCT__entry( __field( bool, is_idle ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->is_idle = is_idle; __entry->cpu = cpu; ), TP_printk("is_idle=%d cpu=%d", __entry->is_idle, __entry->cpu) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_setup - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_setup, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = ACCESS_PRIVATE(hrtimer, function); __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = ACCESS_PRIVATE(hrtimer, function); ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> #include <net/secure_seq.h> #include <linux/netfilter.h> static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { return get_random_u32_above(0); } /* This function exists only for tap drivers that must support broken * clients requesting UFO without specifying an IPv6 fragment ID. * * This is similar to ipv6_select_ident() but we use an independent hash * seed to limit information leakage. * * The network header must be set before calling this. */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; addrs = skb_header_pointer(skb, skb_network_offset(skb) + offsetof(struct ipv6hdr, saddr), sizeof(buf), buf); if (!addrs) return 0; id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { u32 id; id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { case NEXTHDR_HOP: break; case NEXTHDR_ROUTING: found_rhdr = 1; break; case NEXTHDR_DEST: #if IS_ENABLED(CONFIG_IPV6_MIP6) if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) break; #endif if (found_rhdr) return offset; break; default: return offset; } if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) return -EINVAL; exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); offset += ipv6_optlen(exthdr); if (offset > IPV6_MAXPLEN) return -EINVAL; *nexthdr = &exthdr->nexthdr; } return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); #if IS_ENABLED(CONFIG_IPV6) int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); rcu_read_lock(); if (hoplimit == 0) { struct net_device *dev = dst_dev_rcu(dst); struct inet6_dev *idev; idev = __in6_dev_get(dev); if (idev) hoplimit = READ_ONCE(idev->cnf.hop_limit); else hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); } rcu_read_unlock(); return hoplimit; } EXPORT_SYMBOL(ip6_dst_hoplimit); #endif int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int len; len = skb->len - sizeof(struct ipv6hdr); if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IPV6); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip6_local_out); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2014 SGI. * All rights reserved. */ #include "utf8n.h" int utf8version_is_supported(const struct unicode_map *um, unsigned int version) { int i = um->tables->utf8agetab_size - 1; while (i >= 0 && um->tables->utf8agetab[i] != 0) { if (version == um->tables->utf8agetab[i]) return 1; i--; } return 0; } /* * UTF-8 valid ranges. * * The UTF-8 encoding spreads the bits of a 32bit word over several * bytes. This table gives the ranges that can be held and how they'd * be represented. * * 0x00000000 0x0000007F: 0xxxxxxx * 0x00000000 0x000007FF: 110xxxxx 10xxxxxx * 0x00000000 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx * 0x00000000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx * 0x00000000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx * 0x00000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx * * There is an additional requirement on UTF-8, in that only the * shortest representation of a 32bit value is to be used. A decoder * must not decode sequences that do not satisfy this requirement. * Thus the allowed ranges have a lower bound. * * 0x00000000 0x0000007F: 0xxxxxxx * 0x00000080 0x000007FF: 110xxxxx 10xxxxxx * 0x00000800 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx * 0x00010000 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx * 0x00200000 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx * 0x04000000 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx * * Actual unicode characters are limited to the range 0x0 - 0x10FFFF, * 17 planes of 65536 values. This limits the sequences actually seen * even more, to just the following. * * 0 - 0x7F: 0 - 0x7F * 0x80 - 0x7FF: 0xC2 0x80 - 0xDF 0xBF * 0x800 - 0xFFFF: 0xE0 0xA0 0x80 - 0xEF 0xBF 0xBF * 0x10000 - 0x10FFFF: 0xF0 0x90 0x80 0x80 - 0xF4 0x8F 0xBF 0xBF * * Within those ranges the surrogates 0xD800 - 0xDFFF are not allowed. * * Note that the longest sequence seen with valid usage is 4 bytes, * the same a single UTF-32 character. This makes the UTF-8 * representation of Unicode strictly smaller than UTF-32. * * The shortest sequence requirement was introduced by: * Corrigendum #1: UTF-8 Shortest Form * It can be found here: * http://www.unicode.org/versions/corrigendum1.html * */ /* * Return the number of bytes used by the current UTF-8 sequence. * Assumes the input points to the first byte of a valid UTF-8 * sequence. */ static inline int utf8clen(const char *s) { unsigned char c = *s; return 1 + (c >= 0xC0) + (c >= 0xE0) + (c >= 0xF0); } /* * Decode a 3-byte UTF-8 sequence. */ static unsigned int utf8decode3(const char *str) { unsigned int uc; uc = *str++ & 0x0F; uc <<= 6; uc |= *str++ & 0x3F; uc <<= 6; uc |= *str++ & 0x3F; return uc; } /* * Encode a 3-byte UTF-8 sequence. */ static int utf8encode3(char *str, unsigned int val) { str[2] = (val & 0x3F) | 0x80; val >>= 6; str[1] = (val & 0x3F) | 0x80; val >>= 6; str[0] = val | 0xE0; return 3; } /* * utf8trie_t * * A compact binary tree, used to decode UTF-8 characters. * * Internal nodes are one byte for the node itself, and up to three * bytes for an offset into the tree. The first byte contains the * following information: * NEXTBYTE - flag - advance to next byte if set * BITNUM - 3 bit field - the bit number to tested * OFFLEN - 2 bit field - number of bytes in the offset * if offlen == 0 (non-branching node) * RIGHTPATH - 1 bit field - set if the following node is for the * right-hand path (tested bit is set) * TRIENODE - 1 bit field - set if the following node is an internal * node, otherwise it is a leaf node * if offlen != 0 (branching node) * LEFTNODE - 1 bit field - set if the left-hand node is internal * RIGHTNODE - 1 bit field - set if the right-hand node is internal * * Due to the way utf8 works, there cannot be branching nodes with * NEXTBYTE set, and moreover those nodes always have a righthand * descendant. */ typedef const unsigned char utf8trie_t; #define BITNUM 0x07 #define NEXTBYTE 0x08 #define OFFLEN 0x30 #define OFFLEN_SHIFT 4 #define RIGHTPATH 0x40 #define TRIENODE 0x80 #define RIGHTNODE 0x40 #define LEFTNODE 0x80 /* * utf8leaf_t * * The leaves of the trie are embedded in the trie, and so the same * underlying datatype: unsigned char. * * leaf[0]: The unicode version, stored as a generation number that is * an index into ->utf8agetab[]. With this we can filter code * points based on the unicode version in which they were * defined. The CCC of a non-defined code point is 0. * leaf[1]: Canonical Combining Class. During normalization, we need * to do a stable sort into ascending order of all characters * with a non-zero CCC that occur between two characters with * a CCC of 0, or at the begin or end of a string. * The unicode standard guarantees that all CCC values are * between 0 and 254 inclusive, which leaves 255 available as * a special value. * Code points with CCC 0 are known as stoppers. * leaf[2]: Decomposition. If leaf[1] == 255, then leaf[2] is the * start of a NUL-terminated string that is the decomposition * of the character. * The CCC of a decomposable character is the same as the CCC * of the first character of its decomposition. * Some characters decompose as the empty string: these are * characters with the Default_Ignorable_Code_Point property. * These do affect normalization, as they all have CCC 0. * * The decompositions in the trie have been fully expanded, with the * exception of Hangul syllables, which are decomposed algorithmically. * * Casefolding, if applicable, is also done using decompositions. * * The trie is constructed in such a way that leaves exist for all * UTF-8 sequences that match the criteria from the "UTF-8 valid * ranges" comment above, and only for those sequences. Therefore a * lookup in the trie can be used to validate the UTF-8 input. */ typedef const unsigned char utf8leaf_t; #define LEAF_GEN(LEAF) ((LEAF)[0]) #define LEAF_CCC(LEAF) ((LEAF)[1]) #define LEAF_STR(LEAF) ((const char *)((LEAF) + 2)) #define MINCCC (0) #define MAXCCC (254) #define STOPPER (0) #define DECOMPOSE (255) /* Marker for hangul syllable decomposition. */ #define HANGUL ((char)(255)) /* Size of the synthesized leaf used for Hangul syllable decomposition. */ #define UTF8HANGULLEAF (12) /* * Hangul decomposition (algorithm from Section 3.12 of Unicode 6.3.0) * * AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;; * D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;; * * SBase = 0xAC00 * LBase = 0x1100 * VBase = 0x1161 * TBase = 0x11A7 * LCount = 19 * VCount = 21 * TCount = 28 * NCount = 588 (VCount * TCount) * SCount = 11172 (LCount * NCount) * * Decomposition: * SIndex = s - SBase * * LV (Canonical/Full) * LIndex = SIndex / NCount * VIndex = (Sindex % NCount) / TCount * LPart = LBase + LIndex * VPart = VBase + VIndex * * LVT (Canonical) * LVIndex = (SIndex / TCount) * TCount * TIndex = (Sindex % TCount) * LVPart = SBase + LVIndex * TPart = TBase + TIndex * * LVT (Full) * LIndex = SIndex / NCount * VIndex = (Sindex % NCount) / TCount * TIndex = (Sindex % TCount) * LPart = LBase + LIndex * VPart = VBase + VIndex * if (TIndex == 0) { * d = <LPart, VPart> * } else { * TPart = TBase + TIndex * d = <LPart, TPart, VPart> * } */ /* Constants */ #define SB (0xAC00) #define LB (0x1100) #define VB (0x1161) #define TB (0x11A7) #define LC (19) #define VC (21) #define TC (28) #define NC (VC * TC) #define SC (LC * NC) /* Algorithmic decomposition of hangul syllable. */ static utf8leaf_t * utf8hangul(const char *str, unsigned char *hangul) { unsigned int si; unsigned int li; unsigned int vi; unsigned int ti; unsigned char *h; /* Calculate the SI, LI, VI, and TI values. */ si = utf8decode3(str) - SB; li = si / NC; vi = (si % NC) / TC; ti = si % TC; /* Fill in base of leaf. */ h = hangul; LEAF_GEN(h) = 2; LEAF_CCC(h) = DECOMPOSE; h += 2; /* Add LPart, a 3-byte UTF-8 sequence. */ h += utf8encode3((char *)h, li + LB); /* Add VPart, a 3-byte UTF-8 sequence. */ h += utf8encode3((char *)h, vi + VB); /* Add TPart if required, also a 3-byte UTF-8 sequence. */ if (ti) h += utf8encode3((char *)h, ti + TB); /* Terminate string. */ h[0] = '\0'; return hangul; } /* * Use trie to scan s, touching at most len bytes. * Returns the leaf if one exists, NULL otherwise. * * A non-NULL return guarantees that the UTF-8 sequence starting at s * is well-formed and corresponds to a known unicode code point. The * shorthand for this will be "is valid UTF-8 unicode". */ static utf8leaf_t *utf8nlookup(const struct unicode_map *um, enum utf8_normalization n, unsigned char *hangul, const char *s, size_t len) { utf8trie_t *trie = um->tables->utf8data + um->ntab[n]->offset; int offlen; int offset; int mask; int node; if (len == 0) return NULL; node = 1; while (node) { offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT; if (*trie & NEXTBYTE) { if (--len == 0) return NULL; s++; } mask = 1 << (*trie & BITNUM); if (*s & mask) { /* Right leg */ if (offlen) { /* Right node at offset of trie */ node = (*trie & RIGHTNODE); offset = trie[offlen]; while (--offlen) { offset <<= 8; offset |= trie[offlen]; } trie += offset; } else if (*trie & RIGHTPATH) { /* Right node after this node */ node = (*trie & TRIENODE); trie++; } else { /* No right node. */ return NULL; } } else { /* Left leg */ if (offlen) { /* Left node after this node. */ node = (*trie & LEFTNODE); trie += offlen + 1; } else if (*trie & RIGHTPATH) { /* No left node. */ return NULL; } else { /* Left node after this node */ node = (*trie & TRIENODE); trie++; } } } /* * Hangul decomposition is done algorithmically. These are the * codepoints >= 0xAC00 and <= 0xD7A3. Their UTF-8 encoding is * always 3 bytes long, so s has been advanced twice, and the * start of the sequence is at s-2. */ if (LEAF_CCC(trie) == DECOMPOSE && LEAF_STR(trie)[0] == HANGUL) trie = utf8hangul(s - 2, hangul); return trie; } /* * Use trie to scan s. * Returns the leaf if one exists, NULL otherwise. * * Forwards to utf8nlookup(). */ static utf8leaf_t *utf8lookup(const struct unicode_map *um, enum utf8_normalization n, unsigned char *hangul, const char *s) { return utf8nlookup(um, n, hangul, s, (size_t)-1); } /* * Length of the normalization of s, touch at most len bytes. * Return -1 if s is not valid UTF-8 unicode. */ ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n, const char *s, size_t len) { utf8leaf_t *leaf; size_t ret = 0; unsigned char hangul[UTF8HANGULLEAF]; while (len && *s) { leaf = utf8nlookup(um, n, hangul, s, len); if (!leaf) return -1; if (um->tables->utf8agetab[LEAF_GEN(leaf)] > um->ntab[n]->maxage) ret += utf8clen(s); else if (LEAF_CCC(leaf) == DECOMPOSE) ret += strlen(LEAF_STR(leaf)); else ret += utf8clen(s); len -= utf8clen(s); s += utf8clen(s); } return ret; } /* * Set up an utf8cursor for use by utf8byte(). * * u8c : pointer to cursor. * data : const struct utf8data to use for normalization. * s : string. * len : length of s. * * Returns -1 on error, 0 on success. */ int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um, enum utf8_normalization n, const char *s, size_t len) { if (!s) return -1; u8c->um = um; u8c->n = n; u8c->s = s; u8c->p = NULL; u8c->ss = NULL; u8c->sp = NULL; u8c->len = len; u8c->slen = 0; u8c->ccc = STOPPER; u8c->nccc = STOPPER; /* Check we didn't clobber the maximum length. */ if (u8c->len != len) return -1; /* The first byte of s may not be an utf8 continuation. */ if (len > 0 && (*s & 0xC0) == 0x80) return -1; return 0; } /* * Get one byte from the normalized form of the string described by u8c. * * Returns the byte cast to an unsigned char on succes, and -1 on failure. * * The cursor keeps track of the location in the string in u8c->s. * When a character is decomposed, the current location is stored in * u8c->p, and u8c->s is set to the start of the decomposition. Note * that bytes from a decomposition do not count against u8c->len. * * Characters are emitted if they match the current CCC in u8c->ccc. * Hitting end-of-string while u8c->ccc == STOPPER means we're done, * and the function returns 0 in that case. * * Sorting by CCC is done by repeatedly scanning the string. The * values of u8c->s and u8c->p are stored in u8c->ss and u8c->sp at * the start of the scan. The first pass finds the lowest CCC to be * emitted and stores it in u8c->nccc, the second pass emits the * characters with this CCC and finds the next lowest CCC. This limits * the number of passes to 1 + the number of different CCCs in the * sequence being scanned. * * Therefore: * u8c->p != NULL -> a decomposition is being scanned. * u8c->ss != NULL -> this is a repeating scan. * u8c->ccc == -1 -> this is the first scan of a repeating scan. */ int utf8byte(struct utf8cursor *u8c) { utf8leaf_t *leaf; int ccc; for (;;) { /* Check for the end of a decomposed character. */ if (u8c->p && *u8c->s == '\0') { u8c->s = u8c->p; u8c->p = NULL; } /* Check for end-of-string. */ if (!u8c->p && (u8c->len == 0 || *u8c->s == '\0')) { /* There is no next byte. */ if (u8c->ccc == STOPPER) return 0; /* End-of-string during a scan counts as a stopper. */ ccc = STOPPER; goto ccc_mismatch; } else if ((*u8c->s & 0xC0) == 0x80) { /* This is a continuation of the current character. */ if (!u8c->p) u8c->len--; return (unsigned char)*u8c->s++; } /* Look up the data for the current character. */ if (u8c->p) { leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s); } else { leaf = utf8nlookup(u8c->um, u8c->n, u8c->hangul, u8c->s, u8c->len); } /* No leaf found implies that the input is a binary blob. */ if (!leaf) return -1; ccc = LEAF_CCC(leaf); /* Characters that are too new have CCC 0. */ if (u8c->um->tables->utf8agetab[LEAF_GEN(leaf)] > u8c->um->ntab[u8c->n]->maxage) { ccc = STOPPER; } else if (ccc == DECOMPOSE) { u8c->len -= utf8clen(u8c->s); u8c->p = u8c->s + utf8clen(u8c->s); u8c->s = LEAF_STR(leaf); /* Empty decomposition implies CCC 0. */ if (*u8c->s == '\0') { if (u8c->ccc == STOPPER) continue; ccc = STOPPER; goto ccc_mismatch; } leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s); if (!leaf) return -1; ccc = LEAF_CCC(leaf); } /* * If this is not a stopper, then see if it updates * the next canonical class to be emitted. */ if (ccc != STOPPER && u8c->ccc < ccc && ccc < u8c->nccc) u8c->nccc = ccc; /* * Return the current byte if this is the current * combining class. */ if (ccc == u8c->ccc) { if (!u8c->p) u8c->len--; return (unsigned char)*u8c->s++; } /* Current combining class mismatch. */ ccc_mismatch: if (u8c->nccc == STOPPER) { /* * Scan forward for the first canonical class * to be emitted. Save the position from * which to restart. */ u8c->ccc = MINCCC - 1; u8c->nccc = ccc; u8c->sp = u8c->p; u8c->ss = u8c->s; u8c->slen = u8c->len; if (!u8c->p) u8c->len -= utf8clen(u8c->s); u8c->s += utf8clen(u8c->s); } else if (ccc != STOPPER) { /* Not a stopper, and not the ccc we're emitting. */ if (!u8c->p) u8c->len -= utf8clen(u8c->s); u8c->s += utf8clen(u8c->s); } else if (u8c->nccc != MAXCCC + 1) { /* At a stopper, restart for next ccc. */ u8c->ccc = u8c->nccc; u8c->nccc = MAXCCC + 1; u8c->s = u8c->ss; u8c->p = u8c->sp; u8c->len = u8c->slen; } else { /* All done, proceed from here. */ u8c->ccc = STOPPER; u8c->nccc = STOPPER; u8c->sp = NULL; u8c->ss = NULL; u8c->slen = 0; } } } #if IS_MODULE(CONFIG_UNICODE_NORMALIZATION_KUNIT_TEST) EXPORT_SYMBOL_GPL(utf8version_is_supported); EXPORT_SYMBOL_GPL(utf8nlen); EXPORT_SYMBOL_GPL(utf8ncursor); EXPORT_SYMBOL_GPL(utf8byte); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019, 2020 Amazon.com, Inc. or its affiliates. All rights reserved. * * User extended attribute client side cache functions. * * Author: Frank van der Linden <fllinden@amazon.com> */ #include <linux/errno.h> #include <linux/nfs_fs.h> #include <linux/hashtable.h> #include <linux/refcount.h> #include <uapi/linux/xattr.h> #include "nfs4_fs.h" #include "internal.h" /* * User extended attributes client side caching is implemented by having * a cache structure attached to NFS inodes. This structure is allocated * when needed, and freed when the cache is zapped. * * The cache structure contains as hash table of entries, and a pointer * to a special-cased entry for the listxattr cache. * * Accessing and allocating / freeing the caches is done via reference * counting. The cache entries use a similar refcounting scheme. * * This makes freeing a cache, both from the shrinker and from the * zap cache path, easy. It also means that, in current use cases, * the large majority of inodes will not waste any memory, as they * will never have any user extended attributes assigned to them. * * Attribute entries are hashed in to a simple hash table. They are * also part of an LRU. * * There are three shrinkers. * * Two shrinkers deal with the cache entries themselves: one for * large entries (> PAGE_SIZE), and one for smaller entries. The * shrinker for the larger entries works more aggressively than * those for the smaller entries. * * The other shrinker frees the cache structures themselves. */ /* * 64 buckets is a good default. There is likely no reasonable * workload that uses more than even 64 user extended attributes. * You can certainly add a lot more - but you get what you ask for * in those circumstances. */ #define NFS4_XATTR_HASH_SIZE 64 #define NFSDBG_FACILITY NFSDBG_XATTRCACHE struct nfs4_xattr_cache; struct nfs4_xattr_entry; struct nfs4_xattr_bucket { spinlock_t lock; struct hlist_head hlist; struct nfs4_xattr_cache *cache; bool draining; }; struct nfs4_xattr_cache { struct kref ref; struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE]; struct list_head lru; struct list_head dispose; atomic_long_t nent; spinlock_t listxattr_lock; struct inode *inode; struct nfs4_xattr_entry *listxattr; }; struct nfs4_xattr_entry { struct kref ref; struct hlist_node hnode; struct list_head lru; struct list_head dispose; char *xattr_name; void *xattr_value; size_t xattr_size; struct nfs4_xattr_bucket *bucket; uint32_t flags; }; #define NFS4_XATTR_ENTRY_EXTVAL 0x0001 /* * LRU list of NFS inodes that have xattr caches. */ static struct list_lru nfs4_xattr_cache_lru; static struct list_lru nfs4_xattr_entry_lru; static struct list_lru nfs4_xattr_large_entry_lru; static struct kmem_cache *nfs4_xattr_cache_cachep; /* * Hashing helper functions. */ static void nfs4_xattr_hash_init(struct nfs4_xattr_cache *cache) { unsigned int i; for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { INIT_HLIST_HEAD(&cache->buckets[i].hlist); spin_lock_init(&cache->buckets[i].lock); cache->buckets[i].cache = cache; cache->buckets[i].draining = false; } } /* * Locking order: * 1. inode i_lock or bucket lock * 2. list_lru lock (taken by list_lru_* functions) */ /* * Wrapper functions to add a cache entry to the right LRU. */ static bool nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry) { struct list_lru *lru; lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; return list_lru_add_obj(lru, &entry->lru); } static bool nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry) { struct list_lru *lru; lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; return list_lru_del_obj(lru, &entry->lru); } /* * This function allocates cache entries. They are the normal * extended attribute name/value pairs, but may also be a listxattr * cache. Those allocations use the same entry so that they can be * treated as one by the memory shrinker. * * xattr cache entries are allocated together with names. If the * value fits in to one page with the entry structure and the name, * it will also be part of the same allocation (kmalloc). This is * expected to be the vast majority of cases. Larger allocations * have a value pointer that is allocated separately by kvmalloc. * * Parameters: * * @name: Name of the extended attribute. NULL for listxattr cache * entry. * @value: Value of attribute, or listxattr cache. NULL if the * value is to be copied from pages instead. * @pages: Pages to copy the value from, if not NULL. Passed in to * make it easier to copy the value after an RPC, even if * the value will not be passed up to application (e.g. * for a 'query' getxattr with NULL buffer). * @len: Length of the value. Can be 0 for zero-length attributes. * @value and @pages will be NULL if @len is 0. */ static struct nfs4_xattr_entry * nfs4_xattr_alloc_entry(const char *name, const void *value, struct page **pages, size_t len) { struct nfs4_xattr_entry *entry; void *valp; char *namep; size_t alloclen, slen; char *buf; uint32_t flags; BUILD_BUG_ON(sizeof(struct nfs4_xattr_entry) + XATTR_NAME_MAX + 1 > PAGE_SIZE); alloclen = sizeof(struct nfs4_xattr_entry); if (name != NULL) { slen = strlen(name) + 1; alloclen += slen; } else slen = 0; if (alloclen + len <= PAGE_SIZE) { alloclen += len; flags = 0; } else { flags = NFS4_XATTR_ENTRY_EXTVAL; } buf = kmalloc(alloclen, GFP_KERNEL); if (buf == NULL) return NULL; entry = (struct nfs4_xattr_entry *)buf; if (name != NULL) { namep = buf + sizeof(struct nfs4_xattr_entry); memcpy(namep, name, slen); } else { namep = NULL; } if (flags & NFS4_XATTR_ENTRY_EXTVAL) { valp = kvmalloc(len, GFP_KERNEL); if (valp == NULL) { kfree(buf); return NULL; } } else if (len != 0) { valp = buf + sizeof(struct nfs4_xattr_entry) + slen; } else valp = NULL; if (valp != NULL) { if (value != NULL) memcpy(valp, value, len); else _copy_from_pages(valp, pages, 0, len); } entry->flags = flags; entry->xattr_value = valp; kref_init(&entry->ref); entry->xattr_name = namep; entry->xattr_size = len; entry->bucket = NULL; INIT_LIST_HEAD(&entry->lru); INIT_LIST_HEAD(&entry->dispose); INIT_HLIST_NODE(&entry->hnode); return entry; } static void nfs4_xattr_free_entry(struct nfs4_xattr_entry *entry) { if (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) kvfree(entry->xattr_value); kfree(entry); } static void nfs4_xattr_free_entry_cb(struct kref *kref) { struct nfs4_xattr_entry *entry; entry = container_of(kref, struct nfs4_xattr_entry, ref); if (WARN_ON(!list_empty(&entry->lru))) return; nfs4_xattr_free_entry(entry); } static void nfs4_xattr_free_cache_cb(struct kref *kref) { struct nfs4_xattr_cache *cache; int i; cache = container_of(kref, struct nfs4_xattr_cache, ref); for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { if (WARN_ON(!hlist_empty(&cache->buckets[i].hlist))) return; cache->buckets[i].draining = false; } cache->listxattr = NULL; kmem_cache_free(nfs4_xattr_cache_cachep, cache); } static struct nfs4_xattr_cache * nfs4_xattr_alloc_cache(void) { struct nfs4_xattr_cache *cache; cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, GFP_KERNEL); if (cache == NULL) return NULL; kref_init(&cache->ref); atomic_long_set(&cache->nent, 0); return cache; } /* * Set the listxattr cache, which is a special-cased cache entry. * The special value ERR_PTR(-ESTALE) is used to indicate that * the cache is being drained - this prevents a new listxattr * cache from being added to what is now a stale cache. */ static int nfs4_xattr_set_listcache(struct nfs4_xattr_cache *cache, struct nfs4_xattr_entry *new) { struct nfs4_xattr_entry *old; int ret = 1; spin_lock(&cache->listxattr_lock); old = cache->listxattr; if (old == ERR_PTR(-ESTALE)) { ret = 0; goto out; } cache->listxattr = new; if (new != NULL && new != ERR_PTR(-ESTALE)) nfs4_xattr_entry_lru_add(new); if (old != NULL) { nfs4_xattr_entry_lru_del(old); kref_put(&old->ref, nfs4_xattr_free_entry_cb); } out: spin_unlock(&cache->listxattr_lock); return ret; } /* * Unlink a cache from its parent inode, clearing out an invalid * cache. Must be called with i_lock held. */ static struct nfs4_xattr_cache * nfs4_xattr_cache_unlink(struct inode *inode) { struct nfs_inode *nfsi; struct nfs4_xattr_cache *oldcache; nfsi = NFS_I(inode); oldcache = nfsi->xattr_cache; if (oldcache != NULL) { list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru); oldcache->inode = NULL; } nfsi->xattr_cache = NULL; nfsi->cache_validity &= ~NFS_INO_INVALID_XATTR; return oldcache; } /* * Discard a cache. Called by get_cache() if there was an old, * invalid cache. Can also be called from a shrinker callback. * * The cache is dead, it has already been unlinked from its inode, * and no longer appears on the cache LRU list. * * Mark all buckets as draining, so that no new entries are added. This * could still happen in the unlikely, but possible case that another * thread had grabbed a reference before it was unlinked from the inode, * and is still holding it for an add operation. * * Remove all entries from the LRU lists, so that there is no longer * any way to 'find' this cache. Then, remove the entries from the hash * table. * * At that point, the cache will remain empty and can be freed when the final * reference drops, which is very likely the kref_put at the end of * this function, or the one called immediately afterwards in the * shrinker callback. */ static void nfs4_xattr_discard_cache(struct nfs4_xattr_cache *cache) { unsigned int i; struct nfs4_xattr_entry *entry; struct nfs4_xattr_bucket *bucket; struct hlist_node *n; nfs4_xattr_set_listcache(cache, ERR_PTR(-ESTALE)); for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { bucket = &cache->buckets[i]; spin_lock(&bucket->lock); bucket->draining = true; hlist_for_each_entry_safe(entry, n, &bucket->hlist, hnode) { nfs4_xattr_entry_lru_del(entry); hlist_del_init(&entry->hnode); kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } spin_unlock(&bucket->lock); } atomic_long_set(&cache->nent, 0); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Get a referenced copy of the cache structure. Avoid doing allocs * while holding i_lock. Which means that we do some optimistic allocation, * and might have to free the result in rare cases. * * This function only checks the NFS_INO_INVALID_XATTR cache validity bit * and acts accordingly, replacing the cache when needed. For the read case * (!add), this means that the caller must make sure that the cache * is valid before caling this function. getxattr and listxattr call * revalidate_inode to do this. The attribute cache timeout (for the * non-delegated case) is expected to be dealt with in the revalidate * call. */ static struct nfs4_xattr_cache * nfs4_xattr_get_cache(struct inode *inode, int add) { struct nfs_inode *nfsi; struct nfs4_xattr_cache *cache, *oldcache, *newcache; nfsi = NFS_I(inode); cache = oldcache = NULL; spin_lock(&inode->i_lock); if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) oldcache = nfs4_xattr_cache_unlink(inode); else cache = nfsi->xattr_cache; if (cache != NULL) kref_get(&cache->ref); spin_unlock(&inode->i_lock); if (add && cache == NULL) { newcache = NULL; cache = nfs4_xattr_alloc_cache(); if (cache == NULL) goto out; spin_lock(&inode->i_lock); if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) { /* * The cache was invalidated again. Give up, * since what we want to enter is now likely * outdated anyway. */ spin_unlock(&inode->i_lock); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); cache = NULL; goto out; } /* * Check if someone beat us to it. */ if (nfsi->xattr_cache != NULL) { newcache = nfsi->xattr_cache; kref_get(&newcache->ref); } else { kref_get(&cache->ref); nfsi->xattr_cache = cache; cache->inode = inode; list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru); } spin_unlock(&inode->i_lock); /* * If there was a race, throw away the cache we just * allocated, and use the new one allocated by someone * else. */ if (newcache != NULL) { kref_put(&cache->ref, nfs4_xattr_free_cache_cb); cache = newcache; } } out: /* * Discard the now orphaned old cache. */ if (oldcache != NULL) nfs4_xattr_discard_cache(oldcache); return cache; } static inline struct nfs4_xattr_bucket * nfs4_xattr_hash_bucket(struct nfs4_xattr_cache *cache, const char *name) { return &cache->buckets[jhash(name, strlen(name), 0) & (ARRAY_SIZE(cache->buckets) - 1)]; } static struct nfs4_xattr_entry * nfs4_xattr_get_entry(struct nfs4_xattr_bucket *bucket, const char *name) { struct nfs4_xattr_entry *entry; entry = NULL; hlist_for_each_entry(entry, &bucket->hlist, hnode) { if (!strcmp(entry->xattr_name, name)) break; } return entry; } static int nfs4_xattr_hash_add(struct nfs4_xattr_cache *cache, struct nfs4_xattr_entry *entry) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *oldentry = NULL; int ret = 1; bucket = nfs4_xattr_hash_bucket(cache, entry->xattr_name); entry->bucket = bucket; spin_lock(&bucket->lock); if (bucket->draining) { ret = 0; goto out; } oldentry = nfs4_xattr_get_entry(bucket, entry->xattr_name); if (oldentry != NULL) { hlist_del_init(&oldentry->hnode); nfs4_xattr_entry_lru_del(oldentry); } else { atomic_long_inc(&cache->nent); } hlist_add_head(&entry->hnode, &bucket->hlist); nfs4_xattr_entry_lru_add(entry); out: spin_unlock(&bucket->lock); if (oldentry != NULL) kref_put(&oldentry->ref, nfs4_xattr_free_entry_cb); return ret; } static void nfs4_xattr_hash_remove(struct nfs4_xattr_cache *cache, const char *name) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *entry; bucket = nfs4_xattr_hash_bucket(cache, name); spin_lock(&bucket->lock); entry = nfs4_xattr_get_entry(bucket, name); if (entry != NULL) { hlist_del_init(&entry->hnode); nfs4_xattr_entry_lru_del(entry); atomic_long_dec(&cache->nent); } spin_unlock(&bucket->lock); if (entry != NULL) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } static struct nfs4_xattr_entry * nfs4_xattr_hash_find(struct nfs4_xattr_cache *cache, const char *name) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *entry; bucket = nfs4_xattr_hash_bucket(cache, name); spin_lock(&bucket->lock); entry = nfs4_xattr_get_entry(bucket, name); if (entry != NULL) kref_get(&entry->ref); spin_unlock(&bucket->lock); return entry; } /* * Entry point to retrieve an entry from the cache. */ ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name, char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; ssize_t ret; cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return -ENOENT; ret = 0; entry = nfs4_xattr_hash_find(cache, name); if (entry != NULL) { dprintk("%s: cache hit '%s', len %lu\n", __func__, entry->xattr_name, (unsigned long)entry->xattr_size); if (buflen == 0) { /* Length probe only */ ret = entry->xattr_size; } else if (buflen < entry->xattr_size) ret = -ERANGE; else { memcpy(buf, entry->xattr_value, entry->xattr_size); ret = entry->xattr_size; } kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } else { dprintk("%s: cache miss '%s'\n", __func__, name); ret = -ENOENT; } kref_put(&cache->ref, nfs4_xattr_free_cache_cb); return ret; } /* * Retrieve a cached list of xattrs from the cache. */ ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; ssize_t ret; cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return -ENOENT; spin_lock(&cache->listxattr_lock); entry = cache->listxattr; if (entry != NULL && entry != ERR_PTR(-ESTALE)) { if (buflen == 0) { /* Length probe only */ ret = entry->xattr_size; } else if (entry->xattr_size > buflen) ret = -ERANGE; else { memcpy(buf, entry->xattr_value, entry->xattr_size); ret = entry->xattr_size; } } else { ret = -ENOENT; } spin_unlock(&cache->listxattr_lock); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); return ret; } /* * Add an xattr to the cache. * * This also invalidates the xattr list cache. */ void nfs4_xattr_cache_add(struct inode *inode, const char *name, const char *buf, struct page **pages, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; dprintk("%s: add '%s' len %lu\n", __func__, name, (unsigned long)buflen); cache = nfs4_xattr_get_cache(inode, 1); if (cache == NULL) return; entry = nfs4_xattr_alloc_entry(name, buf, pages, buflen); if (entry == NULL) goto out; (void)nfs4_xattr_set_listcache(cache, NULL); if (!nfs4_xattr_hash_add(cache, entry)) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); out: kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Remove an xattr from the cache. * * This also invalidates the xattr list cache. */ void nfs4_xattr_cache_remove(struct inode *inode, const char *name) { struct nfs4_xattr_cache *cache; dprintk("%s: remove '%s'\n", __func__, name); cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return; (void)nfs4_xattr_set_listcache(cache, NULL); nfs4_xattr_hash_remove(cache, name); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Cache listxattr output, replacing any possible old one. */ void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; cache = nfs4_xattr_get_cache(inode, 1); if (cache == NULL) return; entry = nfs4_xattr_alloc_entry(NULL, buf, NULL, buflen); if (entry == NULL) goto out; /* * This is just there to be able to get to bucket->cache, * which is obviously the same for all buckets, so just * use bucket 0. */ entry->bucket = &cache->buckets[0]; if (!nfs4_xattr_set_listcache(cache, entry)) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); out: kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Zap the entire cache. Called when an inode is evicted. */ void nfs4_xattr_cache_zap(struct inode *inode) { struct nfs4_xattr_cache *oldcache; spin_lock(&inode->i_lock); oldcache = nfs4_xattr_cache_unlink(inode); spin_unlock(&inode->i_lock); if (oldcache) nfs4_xattr_discard_cache(oldcache); } /* * The entry LRU is shrunk more aggressively than the cache LRU, * by settings @seeks to 1. * * Cache structures are freed only when they've become empty, after * pruning all but one entry. */ static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc); static struct shrinker *nfs4_xattr_cache_shrinker; static struct shrinker *nfs4_xattr_entry_shrinker; static struct shrinker *nfs4_xattr_large_entry_shrinker; static enum lru_status cache_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct inode *inode; struct nfs4_xattr_cache *cache = container_of(item, struct nfs4_xattr_cache, lru); if (atomic_long_read(&cache->nent) > 1) return LRU_SKIP; /* * If a cache structure is on the LRU list, we know that * its inode is valid. Try to lock it to break the link. * Since we're inverting the lock order here, only try. */ inode = cache->inode; if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; kref_get(&cache->ref); cache->inode = NULL; NFS_I(inode)->xattr_cache = NULL; NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_XATTR; list_lru_isolate(lru, &cache->lru); spin_unlock(&inode->i_lock); list_add_tail(&cache->dispose, dispose); return LRU_REMOVED; } static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; struct nfs4_xattr_cache *cache; freed = list_lru_shrink_walk(&nfs4_xattr_cache_lru, sc, cache_lru_isolate, &dispose); while (!list_empty(&dispose)) { cache = list_first_entry(&dispose, struct nfs4_xattr_cache, dispose); list_del_init(&cache->dispose); nfs4_xattr_discard_cache(cache); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } return freed; } static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; count = list_lru_shrink_count(&nfs4_xattr_cache_lru, sc); return vfs_pressure_ratio(count); } static enum lru_status entry_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry = container_of(item, struct nfs4_xattr_entry, lru); bucket = entry->bucket; cache = bucket->cache; /* * Unhook the entry from its parent (either a cache bucket * or a cache structure if it's a listxattr buf), so that * it's no longer found. Then add it to the isolate list, * to be freed later. * * In both cases, we're reverting lock order, so use * trylock and skip the entry if we can't get the lock. */ if (entry->xattr_name != NULL) { /* Regular cache entry */ if (!spin_trylock(&bucket->lock)) return LRU_SKIP; kref_get(&entry->ref); hlist_del_init(&entry->hnode); atomic_long_dec(&cache->nent); list_lru_isolate(lru, &entry->lru); spin_unlock(&bucket->lock); } else { /* Listxattr cache entry */ if (!spin_trylock(&cache->listxattr_lock)) return LRU_SKIP; kref_get(&entry->ref); cache->listxattr = NULL; list_lru_isolate(lru, &entry->lru); spin_unlock(&cache->listxattr_lock); } list_add_tail(&entry->dispose, dispose); return LRU_REMOVED; } static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; struct nfs4_xattr_entry *entry; struct list_lru *lru; lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; freed = list_lru_shrink_walk(lru, sc, entry_lru_isolate, &dispose); while (!list_empty(&dispose)) { entry = list_first_entry(&dispose, struct nfs4_xattr_entry, dispose); list_del_init(&entry->dispose); /* * Drop two references: the one that we just grabbed * in entry_lru_isolate, and the one that was set * when the entry was first allocated. */ kref_put(&entry->ref, nfs4_xattr_free_entry_cb); kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } return freed; } static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; struct list_lru *lru; lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; count = list_lru_shrink_count(lru, sc); return vfs_pressure_ratio(count); } static void nfs4_xattr_cache_init_once(void *p) { struct nfs4_xattr_cache *cache = p; spin_lock_init(&cache->listxattr_lock); atomic_long_set(&cache->nent, 0); nfs4_xattr_hash_init(cache); cache->listxattr = NULL; INIT_LIST_HEAD(&cache->lru); INIT_LIST_HEAD(&cache->dispose); } typedef unsigned long (*count_objects_cb)(struct shrinker *s, struct shrink_control *sc); typedef unsigned long (*scan_objects_cb)(struct shrinker *s, struct shrink_control *sc); static int __init nfs4_xattr_shrinker_init(struct shrinker **shrinker, struct list_lru *lru, const char *name, count_objects_cb count, scan_objects_cb scan, long batch, int seeks) { int ret; *shrinker = shrinker_alloc(SHRINKER_MEMCG_AWARE, name); if (!*shrinker) return -ENOMEM; ret = list_lru_init_memcg(lru, *shrinker); if (ret) { shrinker_free(*shrinker); return ret; } (*shrinker)->count_objects = count; (*shrinker)->scan_objects = scan; (*shrinker)->batch = batch; (*shrinker)->seeks = seeks; shrinker_register(*shrinker); return ret; } static void nfs4_xattr_shrinker_destroy(struct shrinker *shrinker, struct list_lru *lru) { shrinker_free(shrinker); list_lru_destroy(lru); } int __init nfs4_xattr_cache_init(void) { int ret = 0; nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, (SLAB_RECLAIM_ACCOUNT), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru, "nfs-xattr_cache", nfs4_xattr_cache_count, nfs4_xattr_cache_scan, 0, DEFAULT_SEEKS); if (ret) goto out1; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru, "nfs-xattr_entry", nfs4_xattr_entry_count, nfs4_xattr_entry_scan, 512, DEFAULT_SEEKS); if (ret) goto out2; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru, "nfs-xattr_large_entry", nfs4_xattr_entry_count, nfs4_xattr_entry_scan, 512, 1); if (!ret) return 0; nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); out2: nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); out1: kmem_cache_destroy(nfs4_xattr_cache_cachep); return ret; } void nfs4_xattr_cache_exit(void) { nfs4_xattr_shrinker_destroy(nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru); nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); } |
| 2782 443 445 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H #include <asm/cpufeature.h> #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 #define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u32 read_pkru(void) { if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru != rdpkru()) wrpkru(pkru); } static inline void pkru_write_default(void) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; wrpkru(pkru_get_init_value()); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 5 5 1 5 1 1 5 1 1 1 1 1 1 1 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the core interrupt handling code, for irq-chip based * architectures. Detailed information is available in * Documentation/core-api/genericirq.rst */ #include <linux/irq.h> #include <linux/msi.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/irqdomain.h> #include <trace/events/irq.h> #include "internals.h" static irqreturn_t bad_chained_irq(int irq, void *dev_id) { WARN_ONCE(1, "Chained irq %d should not call an action\n", irq); return IRQ_NONE; } /* * Chained handlers should never call action on their IRQ. This default * action will emit warning if such thing happens. */ struct irqaction chained_action = { .handler = bad_chained_irq, }; /** * irq_set_chip - set the irq chip for an irq * @irq: irq number * @chip: pointer to irq chip description structure */ int irq_set_chip(unsigned int irq, const struct irq_chip *chip) { int ret = -EINVAL; scoped_irqdesc_get_and_lock(irq, 0) { scoped_irqdesc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); ret = 0; } /* For !CONFIG_SPARSE_IRQ make the irq show up in allocated_irqs. */ if (!ret) irq_mark_irq(irq); return ret; } EXPORT_SYMBOL(irq_set_chip); /** * irq_set_irq_type - set the irq trigger type for an irq * @irq: irq number * @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h */ int irq_set_irq_type(unsigned int irq, unsigned int type) { scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) return __irq_set_trigger(scoped_irqdesc, type); return -EINVAL; } EXPORT_SYMBOL(irq_set_irq_type); /** * irq_set_handler_data - set irq handler data for an irq * @irq: Interrupt number * @data: Pointer to interrupt specific data * * Set the hardware irq controller data for an irq */ int irq_set_handler_data(unsigned int irq, void *data) { scoped_irqdesc_get_and_lock(irq, 0) { scoped_irqdesc->irq_common_data.handler_data = data; return 0; } return -EINVAL; } EXPORT_SYMBOL(irq_set_handler_data); /** * irq_set_msi_desc_off - set MSI descriptor data for an irq at offset * @irq_base: Interrupt number base * @irq_offset: Interrupt number offset * @entry: Pointer to MSI descriptor data * * Set the MSI descriptor entry for an irq at offset */ int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, struct msi_desc *entry) { scoped_irqdesc_get_and_lock(irq_base + irq_offset, IRQ_GET_DESC_CHECK_GLOBAL) { scoped_irqdesc->irq_common_data.msi_desc = entry; if (entry && !irq_offset) entry->irq = irq_base; return 0; } return -EINVAL; } /** * irq_set_msi_desc - set MSI descriptor data for an irq * @irq: Interrupt number * @entry: Pointer to MSI descriptor data * * Set the MSI descriptor entry for an irq */ int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry) { return irq_set_msi_desc_off(irq, 0, entry); } /** * irq_set_chip_data - set irq chip data for an irq * @irq: Interrupt number * @data: Pointer to chip specific data * * Set the hardware irq chip data for an irq */ int irq_set_chip_data(unsigned int irq, void *data) { scoped_irqdesc_get_and_lock(irq, 0) { scoped_irqdesc->irq_data.chip_data = data; return 0; } return -EINVAL; } EXPORT_SYMBOL(irq_set_chip_data); struct irq_data *irq_get_irq_data(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); return desc ? &desc->irq_data : NULL; } EXPORT_SYMBOL_GPL(irq_get_irq_data); static void irq_state_clr_disabled(struct irq_desc *desc) { irqd_clear(&desc->irq_data, IRQD_IRQ_DISABLED); } static void irq_state_clr_masked(struct irq_desc *desc) { irqd_clear(&desc->irq_data, IRQD_IRQ_MASKED); } static void irq_state_clr_started(struct irq_desc *desc) { irqd_clear(&desc->irq_data, IRQD_IRQ_STARTED); } static void irq_state_set_started(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_STARTED); } enum { IRQ_STARTUP_NORMAL, IRQ_STARTUP_MANAGED, IRQ_STARTUP_ABORT, }; #ifdef CONFIG_SMP static int __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff, bool force) { struct irq_data *d = irq_desc_get_irq_data(desc); if (!irqd_affinity_is_managed(d)) return IRQ_STARTUP_NORMAL; irqd_clr_managed_shutdown(d); if (!cpumask_intersects(aff, cpu_online_mask)) { /* * Catch code which fiddles with enable_irq() on a managed * and potentially shutdown IRQ. Chained interrupt * installment or irq auto probing should not happen on * managed irqs either. */ if (WARN_ON_ONCE(force)) return IRQ_STARTUP_ABORT; /* * The interrupt was requested, but there is no online CPU * in it's affinity mask. Put it into managed shutdown * state and let the cpu hotplug mechanism start it up once * a CPU in the mask becomes available. */ return IRQ_STARTUP_ABORT; } /* * Managed interrupts have reserved resources, so this should not * happen. */ if (WARN_ON(irq_domain_activate_irq(d, false))) return IRQ_STARTUP_ABORT; return IRQ_STARTUP_MANAGED; } void irq_startup_managed(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); /* * Clear managed-shutdown flag, so we don't repeat managed-startup for * multiple hotplugs, and cause imbalanced disable depth. */ irqd_clr_managed_shutdown(d); /* * Only start it up when the disable depth is 1, so that a disable, * hotunplug, hotplug sequence does not end up enabling it during * hotplug unconditionally. */ desc->depth--; if (!desc->depth) irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } #else static __always_inline int __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff, bool force) { return IRQ_STARTUP_NORMAL; } #endif static void irq_enable(struct irq_desc *desc) { if (!irqd_irq_disabled(&desc->irq_data)) { unmask_irq(desc); } else { irq_state_clr_disabled(desc); if (desc->irq_data.chip->irq_enable) { desc->irq_data.chip->irq_enable(&desc->irq_data); irq_state_clr_masked(desc); } else { unmask_irq(desc); } } } static int __irq_startup(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); int ret = 0; /* Warn if this interrupt is not activated but try nevertheless */ WARN_ON_ONCE(!irqd_is_activated(d)); if (d->chip->irq_startup) { ret = d->chip->irq_startup(d); irq_state_clr_disabled(desc); irq_state_clr_masked(desc); } else { irq_enable(desc); } irq_state_set_started(desc); return ret; } int irq_startup(struct irq_desc *desc, bool resend, bool force) { struct irq_data *d = irq_desc_get_irq_data(desc); const struct cpumask *aff = irq_data_get_affinity_mask(d); int ret = 0; desc->depth = 0; if (irqd_is_started(d)) { irq_enable(desc); } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) irq_setup_affinity(desc); ret = __irq_startup(desc); if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); ret = __irq_startup(desc); break; case IRQ_STARTUP_ABORT: desc->depth = 1; irqd_set_managed_shutdown(d); return 0; } } if (resend) check_irq_resend(desc, false); return ret; } int irq_activate(struct irq_desc *desc) { struct irq_data *d = irq_desc_get_irq_data(desc); if (!irqd_affinity_is_managed(d)) return irq_domain_activate_irq(d, false); return 0; } int irq_activate_and_startup(struct irq_desc *desc, bool resend) { if (WARN_ON(irq_activate(desc))) return 0; return irq_startup(desc, resend, IRQ_START_FORCE); } static void __irq_disable(struct irq_desc *desc, bool mask); void irq_shutdown(struct irq_desc *desc) { if (irqd_is_started(&desc->irq_data)) { clear_irq_resend(desc); /* * Increment disable depth, so that a managed shutdown on * CPU hotunplug preserves the actual disabled state when the * CPU comes back online. See irq_startup_managed(). */ desc->depth++; if (desc->irq_data.chip->irq_shutdown) { desc->irq_data.chip->irq_shutdown(&desc->irq_data); irq_state_set_disabled(desc); irq_state_set_masked(desc); } else { __irq_disable(desc, true); } irq_state_clr_started(desc); } } void irq_shutdown_and_deactivate(struct irq_desc *desc) { irq_shutdown(desc); /* * This must be called even if the interrupt was never started up, * because the activation can happen before the interrupt is * available for request/startup. It has it's own state tracking so * it's safe to call it unconditionally. */ irq_domain_deactivate_irq(&desc->irq_data); } static void __irq_disable(struct irq_desc *desc, bool mask) { if (irqd_irq_disabled(&desc->irq_data)) { if (mask) mask_irq(desc); } else { irq_state_set_disabled(desc); if (desc->irq_data.chip->irq_disable) { desc->irq_data.chip->irq_disable(&desc->irq_data); irq_state_set_masked(desc); } else if (mask) { mask_irq(desc); } } } /** * irq_disable - Mark interrupt disabled * @desc: irq descriptor which should be disabled * * If the chip does not implement the irq_disable callback, we * use a lazy disable approach. That means we mark the interrupt * disabled, but leave the hardware unmasked. That's an * optimization because we avoid the hardware access for the * common case where no interrupt happens after we marked it * disabled. If an interrupt happens, then the interrupt flow * handler masks the line at the hardware level and marks it * pending. * * If the interrupt chip does not implement the irq_disable callback, * a driver can disable the lazy approach for a particular irq line by * calling 'irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY)'. This can * be used for devices which cannot disable the interrupt at the * device level under certain circumstances and have to use * disable_irq[_nosync] instead. */ void irq_disable(struct irq_desc *desc) { __irq_disable(desc, irq_settings_disable_unlazy(desc)); } void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu) { if (desc->irq_data.chip->irq_enable) desc->irq_data.chip->irq_enable(&desc->irq_data); else desc->irq_data.chip->irq_unmask(&desc->irq_data); cpumask_set_cpu(cpu, desc->percpu_enabled); } void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu) { if (desc->irq_data.chip->irq_disable) desc->irq_data.chip->irq_disable(&desc->irq_data); else desc->irq_data.chip->irq_mask(&desc->irq_data); cpumask_clear_cpu(cpu, desc->percpu_enabled); } static inline void mask_ack_irq(struct irq_desc *desc) { if (desc->irq_data.chip->irq_mask_ack) { desc->irq_data.chip->irq_mask_ack(&desc->irq_data); irq_state_set_masked(desc); } else { mask_irq(desc); if (desc->irq_data.chip->irq_ack) desc->irq_data.chip->irq_ack(&desc->irq_data); } } void mask_irq(struct irq_desc *desc) { if (irqd_irq_masked(&desc->irq_data)) return; if (desc->irq_data.chip->irq_mask) { desc->irq_data.chip->irq_mask(&desc->irq_data); irq_state_set_masked(desc); } } void unmask_irq(struct irq_desc *desc) { if (!irqd_irq_masked(&desc->irq_data)) return; if (desc->irq_data.chip->irq_unmask) { desc->irq_data.chip->irq_unmask(&desc->irq_data); irq_state_clr_masked(desc); } } void unmask_threaded_irq(struct irq_desc *desc) { struct irq_chip *chip = desc->irq_data.chip; if (chip->flags & IRQCHIP_EOI_THREADED) chip->irq_eoi(&desc->irq_data); unmask_irq(desc); } /* Busy wait until INPROGRESS is cleared */ static bool irq_wait_on_inprogress(struct irq_desc *desc) { if (IS_ENABLED(CONFIG_SMP)) { do { raw_spin_unlock(&desc->lock); while (irqd_irq_inprogress(&desc->irq_data)) cpu_relax(); raw_spin_lock(&desc->lock); } while (irqd_irq_inprogress(&desc->irq_data)); /* Might have been disabled in meantime */ return !irqd_irq_disabled(&desc->irq_data) && desc->action; } return false; } static bool irq_can_handle_pm(struct irq_desc *desc) { struct irq_data *irqd = &desc->irq_data; const struct cpumask *aff; /* * If the interrupt is not in progress and is not an armed * wakeup interrupt, proceed. */ if (!irqd_has_set(irqd, IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED)) return true; /* * If the interrupt is an armed wakeup source, mark it pending * and suspended, disable it and notify the pm core about the * event. */ if (unlikely(irqd_has_set(irqd, IRQD_WAKEUP_ARMED))) { irq_pm_handle_wakeup(desc); return false; } /* Check whether the interrupt is polled on another CPU */ if (unlikely(desc->istate & IRQS_POLL_INPROGRESS)) { if (WARN_ONCE(irq_poll_cpu == smp_processor_id(), "irq poll in progress on cpu %d for irq %d\n", smp_processor_id(), desc->irq_data.irq)) return false; return irq_wait_on_inprogress(desc); } /* The below works only for single target interrupts */ if (!IS_ENABLED(CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK) || !irqd_is_single_target(irqd) || desc->handle_irq != handle_edge_irq) return false; /* * If the interrupt affinity was moved to this CPU and the * interrupt is currently handled on the previous target CPU, then * busy wait for INPROGRESS to be cleared. Otherwise for edge type * interrupts the handler might get stuck on the previous target: * * CPU 0 CPU 1 (new target) * handle_edge_irq() * repeat: * handle_event() handle_edge_irq() * if (INPROGESS) { * set(PENDING); * mask(); * return; * } * if (PENDING) { * clear(PENDING); * unmask(); * goto repeat; * } * * This happens when the device raises interrupts with a high rate * and always before handle_event() completes and the CPU0 handler * can clear INPROGRESS. This has been observed in virtual machines. */ aff = irq_data_get_effective_affinity_mask(irqd); if (cpumask_first(aff) != smp_processor_id()) return false; return irq_wait_on_inprogress(desc); } static inline bool irq_can_handle_actions(struct irq_desc *desc) { desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { desc->istate |= IRQS_PENDING; return false; } return true; } static inline bool irq_can_handle(struct irq_desc *desc) { if (!irq_can_handle_pm(desc)) return false; return irq_can_handle_actions(desc); } /** * handle_nested_irq - Handle a nested irq from a irq thread * @irq: the interrupt number * * Handle interrupts which are nested into a threaded interrupt * handler. The handler function is called inside the calling threads * context. */ void handle_nested_irq(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action; irqreturn_t action_ret; might_sleep(); scoped_guard(raw_spinlock_irq, &desc->lock) { if (!irq_can_handle_actions(desc)) return; action = desc->action; kstat_incr_irqs_this_cpu(desc); atomic_inc(&desc->threads_active); } action_ret = IRQ_NONE; for_each_action_of_desc(desc, action) action_ret |= action->thread_fn(action->irq, action->dev_id); if (!irq_settings_no_debug(desc)) note_interrupt(desc, action_ret); wake_threads_waitq(desc); } EXPORT_SYMBOL_GPL(handle_nested_irq); /** * handle_simple_irq - Simple and software-decoded IRQs. * @desc: the interrupt description structure for this irq * * Simple interrupts are either sent from a demultiplexing interrupt * handler or come from hardware, where no interrupt hardware control is * necessary. * * Note: The caller is expected to handle the ack, clear, mask and unmask * issues if necessary. */ void handle_simple_irq(struct irq_desc *desc) { guard(raw_spinlock)(&desc->lock); if (!irq_can_handle_pm(desc)) { if (irqd_needs_resend_when_in_progress(&desc->irq_data)) desc->istate |= IRQS_PENDING; return; } if (!irq_can_handle_actions(desc)) return; kstat_incr_irqs_this_cpu(desc); handle_irq_event(desc); } EXPORT_SYMBOL_GPL(handle_simple_irq); /** * handle_untracked_irq - Simple and software-decoded IRQs. * @desc: the interrupt description structure for this irq * * Untracked interrupts are sent from a demultiplexing interrupt handler * when the demultiplexer does not know which device it its multiplexed irq * domain generated the interrupt. IRQ's handled through here are not * subjected to stats tracking, randomness, or spurious interrupt * detection. * * Note: Like handle_simple_irq, the caller is expected to handle the ack, * clear, mask and unmask issues if necessary. */ void handle_untracked_irq(struct irq_desc *desc) { scoped_guard(raw_spinlock, &desc->lock) { if (!irq_can_handle(desc)) return; desc->istate &= ~IRQS_PENDING; irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); } __handle_irq_event_percpu(desc); scoped_guard(raw_spinlock, &desc->lock) irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); } EXPORT_SYMBOL_GPL(handle_untracked_irq); /* * Called unconditionally from handle_level_irq() and only for oneshot * interrupts from handle_fasteoi_irq() */ static void cond_unmask_irq(struct irq_desc *desc) { /* * We need to unmask in the following cases: * - Standard level irq (IRQF_ONESHOT is not set) * - Oneshot irq which did not wake the thread (caused by a * spurious interrupt or a primary handler handling it * completely). */ if (!irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) unmask_irq(desc); } /** * handle_level_irq - Level type irq handler * @desc: the interrupt description structure for this irq * * Level type interrupts are active as long as the hardware line has the * active level. This may require to mask the interrupt and unmask it after * the associated handler has acknowledged the device, so the interrupt * line is back to inactive. */ void handle_level_irq(struct irq_desc *desc) { guard(raw_spinlock)(&desc->lock); mask_ack_irq(desc); if (!irq_can_handle(desc)) return; kstat_incr_irqs_this_cpu(desc); handle_irq_event(desc); cond_unmask_irq(desc); } EXPORT_SYMBOL_GPL(handle_level_irq); static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) { if (!(desc->istate & IRQS_ONESHOT)) { chip->irq_eoi(&desc->irq_data); return; } /* * We need to unmask in the following cases: * - Oneshot irq which did not wake the thread (caused by a * spurious interrupt or a primary handler handling it * completely). */ if (!irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) { chip->irq_eoi(&desc->irq_data); unmask_irq(desc); } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) { chip->irq_eoi(&desc->irq_data); } } static inline void cond_eoi_irq(struct irq_chip *chip, struct irq_data *data) { if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED)) chip->irq_eoi(data); } /** * handle_fasteoi_irq - irq handler for transparent controllers * @desc: the interrupt description structure for this irq * * Only a single callback will be issued to the chip: an ->eoi() call when * the interrupt has been serviced. This enables support for modern forms * of interrupt handlers, which handle the flow details in hardware, * transparently. */ void handle_fasteoi_irq(struct irq_desc *desc) { struct irq_chip *chip = desc->irq_data.chip; guard(raw_spinlock)(&desc->lock); /* * When an affinity change races with IRQ handling, the next interrupt * can arrive on the new CPU before the original CPU has completed * handling the previous one - it may need to be resent. */ if (!irq_can_handle_pm(desc)) { if (irqd_needs_resend_when_in_progress(&desc->irq_data)) desc->istate |= IRQS_PENDING; cond_eoi_irq(chip, &desc->irq_data); return; } if (!irq_can_handle_actions(desc)) { mask_irq(desc); cond_eoi_irq(chip, &desc->irq_data); return; } kstat_incr_irqs_this_cpu(desc); if (desc->istate & IRQS_ONESHOT) mask_irq(desc); handle_irq_event(desc); cond_unmask_eoi_irq(desc, chip); /* * When the race described above happens this will resend the interrupt. */ if (unlikely(desc->istate & IRQS_PENDING)) check_irq_resend(desc, false); } EXPORT_SYMBOL_GPL(handle_fasteoi_irq); /** * handle_fasteoi_nmi - irq handler for NMI interrupt lines * @desc: the interrupt description structure for this irq * * A simple NMI-safe handler, considering the restrictions * from request_nmi. * * Only a single callback will be issued to the chip: an ->eoi() * call when the interrupt has been serviced. This enables support * for modern forms of interrupt handlers, which handle the flow * details in hardware, transparently. */ void handle_fasteoi_nmi(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irqaction *action = desc->action; unsigned int irq = irq_desc_get_irq(desc); irqreturn_t res; __kstat_incr_irqs_this_cpu(desc); trace_irq_handler_entry(irq, action); /* * NMIs cannot be shared, there is only one action. */ res = action->handler(irq, action->dev_id); trace_irq_handler_exit(irq, action, res); if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); } EXPORT_SYMBOL_GPL(handle_fasteoi_nmi); /** * handle_edge_irq - edge type IRQ handler * @desc: the interrupt description structure for this irq * * Interrupt occurs on the falling and/or rising edge of a hardware * signal. The occurrence is latched into the irq controller hardware and * must be acked in order to be reenabled. After the ack another interrupt * can happen on the same source even before the first one is handled by * the associated event handler. If this happens it might be necessary to * disable (mask) the interrupt depending on the controller hardware. This * requires to reenable the interrupt inside of the loop which handles the * interrupts which have arrived while the handler was running. If all * pending interrupts are handled, the loop is left. */ void handle_edge_irq(struct irq_desc *desc) { guard(raw_spinlock)(&desc->lock); if (!irq_can_handle(desc)) { desc->istate |= IRQS_PENDING; mask_ack_irq(desc); return; } kstat_incr_irqs_this_cpu(desc); /* Start handling the irq */ desc->irq_data.chip->irq_ack(&desc->irq_data); do { if (unlikely(!desc->action)) { mask_irq(desc); return; } /* * When another irq arrived while we were handling * one, we could have masked the irq. * Reenable it, if it was not disabled in meantime. */ if (unlikely(desc->istate & IRQS_PENDING)) { if (!irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data)) unmask_irq(desc); } handle_irq_event(desc); } while ((desc->istate & IRQS_PENDING) && !irqd_irq_disabled(&desc->irq_data)); } EXPORT_SYMBOL(handle_edge_irq); /** * handle_percpu_irq - Per CPU local irq handler * @desc: the interrupt description structure for this irq * * Per CPU interrupts on SMP machines without locking requirements */ void handle_percpu_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); /* * PER CPU interrupts are not serialized. Do not touch * desc->tot_count. */ __kstat_incr_irqs_this_cpu(desc); if (chip->irq_ack) chip->irq_ack(&desc->irq_data); handle_irq_event_percpu(desc); if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); } /** * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids * @desc: the interrupt description structure for this irq * * Per CPU interrupts on SMP machines without locking requirements. Same as * handle_percpu_irq() above but with the following extras: * * action->percpu_dev_id is a pointer to percpu variables which * contain the real device id for the cpu on which this handler is * called */ void handle_percpu_devid_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irqaction *action = desc->action; unsigned int irq = irq_desc_get_irq(desc); irqreturn_t res; /* * PER CPU interrupts are not serialized. Do not touch * desc->tot_count. */ __kstat_incr_irqs_this_cpu(desc); if (chip->irq_ack) chip->irq_ack(&desc->irq_data); if (likely(action)) { trace_irq_handler_entry(irq, action); res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id)); trace_irq_handler_exit(irq, action, res); } else { unsigned int cpu = smp_processor_id(); bool enabled = cpumask_test_cpu(cpu, desc->percpu_enabled); if (enabled) irq_percpu_disable(desc, cpu); pr_err_once("Spurious%s percpu IRQ%u on CPU%u\n", enabled ? " and unmasked" : "", irq, cpu); } if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); } /** * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu * dev ids * @desc: the interrupt description structure for this irq * * Similar to handle_fasteoi_nmi, but handling the dev_id cookie * as a percpu pointer. */ void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irqaction *action = desc->action; unsigned int irq = irq_desc_get_irq(desc); irqreturn_t res; __kstat_incr_irqs_this_cpu(desc); trace_irq_handler_entry(irq, action); res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id)); trace_irq_handler_exit(irq, action, res); if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); } static void __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, int is_chained, const char *name) { if (!handle) { handle = handle_bad_irq; } else { struct irq_data *irq_data = &desc->irq_data; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /* * With hierarchical domains we might run into a * situation where the outermost chip is not yet set * up, but the inner chips are there. Instead of * bailing we install the handler, but obviously we * cannot enable/startup the interrupt at this point. */ while (irq_data) { if (irq_data->chip != &no_irq_chip) break; /* * Bail out if the outer chip is not set up * and the interrupt supposed to be started * right away. */ if (WARN_ON(is_chained)) return; /* Try the parent */ irq_data = irq_data->parent_data; } #endif if (WARN_ON(!irq_data || irq_data->chip == &no_irq_chip)) return; } /* Uninstall? */ if (handle == handle_bad_irq) { if (desc->irq_data.chip != &no_irq_chip) mask_ack_irq(desc); irq_state_set_disabled(desc); if (is_chained) { desc->action = NULL; WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc))); } desc->depth = 1; } desc->handle_irq = handle; desc->name = name; if (handle != handle_bad_irq && is_chained) { unsigned int type = irqd_get_trigger_type(&desc->irq_data); /* * We're about to start this interrupt immediately, * hence the need to set the trigger configuration. * But the .set_type callback may have overridden the * flow handler, ignoring that we're dealing with a * chained interrupt. Reset it immediately because we * do know better. */ if (type != IRQ_TYPE_NONE) { __irq_set_trigger(desc, type); desc->handle_irq = handle; } irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc))); irq_activate_and_startup(desc, IRQ_RESEND); } } void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name) { scoped_irqdesc_get_and_buslock(irq, 0) __irq_do_set_handler(scoped_irqdesc, handle, is_chained, name); } EXPORT_SYMBOL_GPL(__irq_set_handler); void irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, void *data) { scoped_irqdesc_get_and_buslock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; desc->irq_common_data.handler_data = data; __irq_do_set_handler(desc, handle, 1, NULL); } } EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data); void irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name) { irq_set_chip(irq, chip); __irq_set_handler(irq, handle, 0, name); } EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { scoped_irqdesc_get_and_lock(irq, 0) { struct irq_desc *desc = scoped_irqdesc; unsigned long trigger, tmp; /* * Warn when a driver sets the no autoenable flag on an already * active interrupt. */ WARN_ON_ONCE(!desc->depth && (set & _IRQ_NOAUTOEN)); irq_settings_clr_and_set(desc, clr, set); trigger = irqd_get_trigger_type(&desc->irq_data); irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | IRQD_TRIGGER_MASK | IRQD_LEVEL); if (irq_settings_has_no_balance_set(desc)) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); if (irq_settings_is_per_cpu(desc)) irqd_set(&desc->irq_data, IRQD_PER_CPU); if (irq_settings_is_level(desc)) irqd_set(&desc->irq_data, IRQD_LEVEL); tmp = irq_settings_get_trigger_mask(desc); if (tmp != IRQ_TYPE_NONE) trigger = tmp; irqd_set(&desc->irq_data, trigger); } } EXPORT_SYMBOL_GPL(irq_modify_status); #ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE /** * irq_cpu_online - Invoke all irq_cpu_online functions. * * Iterate through all irqs and invoke the chip.irq_cpu_online() * for each. */ void irq_cpu_online(void) { unsigned int irq; for_each_active_irq(irq) { struct irq_desc *desc = irq_to_desc(irq); struct irq_chip *chip; if (!desc) continue; guard(raw_spinlock_irqsave)(&desc->lock); chip = irq_data_get_irq_chip(&desc->irq_data); if (chip && chip->irq_cpu_online && (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || !irqd_irq_disabled(&desc->irq_data))) chip->irq_cpu_online(&desc->irq_data); } } /** * irq_cpu_offline - Invoke all irq_cpu_offline functions. * * Iterate through all irqs and invoke the chip.irq_cpu_offline() * for each. */ void irq_cpu_offline(void) { unsigned int irq; for_each_active_irq(irq) { struct irq_desc *desc = irq_to_desc(irq); struct irq_chip *chip; if (!desc) continue; guard(raw_spinlock_irqsave)(&desc->lock); chip = irq_data_get_irq_chip(&desc->irq_data); if (chip && chip->irq_cpu_offline && (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || !irqd_irq_disabled(&desc->irq_data))) chip->irq_cpu_offline(&desc->irq_data); } } #endif #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY #ifdef CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS /** * handle_fasteoi_ack_irq - irq handler for edge hierarchy stacked on * transparent controllers * * @desc: the interrupt description structure for this irq * * Like handle_fasteoi_irq(), but for use with hierarchy where the irq_chip * also needs to have its ->irq_ack() function called. */ void handle_fasteoi_ack_irq(struct irq_desc *desc) { struct irq_chip *chip = desc->irq_data.chip; guard(raw_spinlock)(&desc->lock); if (!irq_can_handle_pm(desc)) { cond_eoi_irq(chip, &desc->irq_data); return; } if (unlikely(!irq_can_handle_actions(desc))) { mask_irq(desc); cond_eoi_irq(chip, &desc->irq_data); return; } kstat_incr_irqs_this_cpu(desc); if (desc->istate & IRQS_ONESHOT) mask_irq(desc); desc->irq_data.chip->irq_ack(&desc->irq_data); handle_irq_event(desc); cond_unmask_eoi_irq(desc, chip); } EXPORT_SYMBOL_GPL(handle_fasteoi_ack_irq); /** * handle_fasteoi_mask_irq - irq handler for level hierarchy stacked on * transparent controllers * * @desc: the interrupt description structure for this irq * * Like handle_fasteoi_irq(), but for use with hierarchy where the irq_chip * also needs to have its ->irq_mask_ack() function called. */ void handle_fasteoi_mask_irq(struct irq_desc *desc) { struct irq_chip *chip = desc->irq_data.chip; guard(raw_spinlock)(&desc->lock); mask_ack_irq(desc); if (!irq_can_handle(desc)) { cond_eoi_irq(chip, &desc->irq_data); return; } kstat_incr_irqs_this_cpu(desc); handle_irq_event(desc); cond_unmask_eoi_irq(desc, chip); } EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq); #endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */ /** * irq_chip_set_parent_state - set the state of a parent interrupt. * * @data: Pointer to interrupt specific data * @which: State to be restored (one of IRQCHIP_STATE_*) * @val: Value corresponding to @which * * Conditional success, if the underlying irqchip does not implement it. */ int irq_chip_set_parent_state(struct irq_data *data, enum irqchip_irq_state which, bool val) { data = data->parent_data; if (!data || !data->chip->irq_set_irqchip_state) return 0; return data->chip->irq_set_irqchip_state(data, which, val); } EXPORT_SYMBOL_GPL(irq_chip_set_parent_state); /** * irq_chip_get_parent_state - get the state of a parent interrupt. * * @data: Pointer to interrupt specific data * @which: one of IRQCHIP_STATE_* the caller wants to know * @state: a pointer to a boolean where the state is to be stored * * Conditional success, if the underlying irqchip does not implement it. */ int irq_chip_get_parent_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { data = data->parent_data; if (!data || !data->chip->irq_get_irqchip_state) return 0; return data->chip->irq_get_irqchip_state(data, which, state); } EXPORT_SYMBOL_GPL(irq_chip_get_parent_state); /** * irq_chip_shutdown_parent - Shutdown the parent interrupt * @data: Pointer to interrupt specific data * * Invokes the irq_shutdown() callback of the parent if available or falls * back to irq_chip_disable_parent(). */ void irq_chip_shutdown_parent(struct irq_data *data) { struct irq_data *parent = data->parent_data; if (parent->chip->irq_shutdown) parent->chip->irq_shutdown(parent); else irq_chip_disable_parent(data); } EXPORT_SYMBOL_GPL(irq_chip_shutdown_parent); /** * irq_chip_startup_parent - Startup the parent interrupt * @data: Pointer to interrupt specific data * * Invokes the irq_startup() callback of the parent if available or falls * back to irq_chip_enable_parent(). */ unsigned int irq_chip_startup_parent(struct irq_data *data) { struct irq_data *parent = data->parent_data; if (parent->chip->irq_startup) return parent->chip->irq_startup(parent); irq_chip_enable_parent(data); return 0; } EXPORT_SYMBOL_GPL(irq_chip_startup_parent); /** * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if * NULL) * @data: Pointer to interrupt specific data */ void irq_chip_enable_parent(struct irq_data *data) { data = data->parent_data; if (data->chip->irq_enable) data->chip->irq_enable(data); else data->chip->irq_unmask(data); } EXPORT_SYMBOL_GPL(irq_chip_enable_parent); /** * irq_chip_disable_parent - Disable the parent interrupt (defaults to mask if * NULL) * @data: Pointer to interrupt specific data */ void irq_chip_disable_parent(struct irq_data *data) { data = data->parent_data; if (data->chip->irq_disable) data->chip->irq_disable(data); else data->chip->irq_mask(data); } EXPORT_SYMBOL_GPL(irq_chip_disable_parent); /** * irq_chip_ack_parent - Acknowledge the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_ack_parent(struct irq_data *data) { data = data->parent_data; data->chip->irq_ack(data); } EXPORT_SYMBOL_GPL(irq_chip_ack_parent); /** * irq_chip_mask_parent - Mask the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_mask_parent(struct irq_data *data) { data = data->parent_data; data->chip->irq_mask(data); } EXPORT_SYMBOL_GPL(irq_chip_mask_parent); /** * irq_chip_mask_ack_parent - Mask and acknowledge the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_mask_ack_parent(struct irq_data *data) { data = data->parent_data; data->chip->irq_mask_ack(data); } EXPORT_SYMBOL_GPL(irq_chip_mask_ack_parent); /** * irq_chip_unmask_parent - Unmask the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_unmask_parent(struct irq_data *data) { data = data->parent_data; data->chip->irq_unmask(data); } EXPORT_SYMBOL_GPL(irq_chip_unmask_parent); /** * irq_chip_eoi_parent - Invoke EOI on the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_eoi_parent(struct irq_data *data) { data = data->parent_data; data->chip->irq_eoi(data); } EXPORT_SYMBOL_GPL(irq_chip_eoi_parent); /** * irq_chip_set_affinity_parent - Set affinity on the parent interrupt * @data: Pointer to interrupt specific data * @dest: The affinity mask to set * @force: Flag to enforce setting (disable online checks) * * Conditional, as the underlying parent chip might not implement it. */ int irq_chip_set_affinity_parent(struct irq_data *data, const struct cpumask *dest, bool force) { data = data->parent_data; if (data->chip->irq_set_affinity) return data->chip->irq_set_affinity(data, dest, force); return -ENOSYS; } EXPORT_SYMBOL_GPL(irq_chip_set_affinity_parent); /** * irq_chip_set_type_parent - Set IRQ type on the parent interrupt * @data: Pointer to interrupt specific data * @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h * * Conditional, as the underlying parent chip might not implement it. */ int irq_chip_set_type_parent(struct irq_data *data, unsigned int type) { data = data->parent_data; if (data->chip->irq_set_type) return data->chip->irq_set_type(data, type); return -ENOSYS; } EXPORT_SYMBOL_GPL(irq_chip_set_type_parent); /** * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware * @data: Pointer to interrupt specific data * * Iterate through the domain hierarchy of the interrupt and check * whether a hw retrigger function exists. If yes, invoke it. */ int irq_chip_retrigger_hierarchy(struct irq_data *data) { for (data = data->parent_data; data; data = data->parent_data) if (data->chip && data->chip->irq_retrigger) return data->chip->irq_retrigger(data); return 0; } EXPORT_SYMBOL_GPL(irq_chip_retrigger_hierarchy); /** * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt * @data: Pointer to interrupt specific data * @vcpu_info: The vcpu affinity information */ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info) { data = data->parent_data; if (data->chip->irq_set_vcpu_affinity) return data->chip->irq_set_vcpu_affinity(data, vcpu_info); return -ENOSYS; } EXPORT_SYMBOL_GPL(irq_chip_set_vcpu_affinity_parent); /** * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt * @data: Pointer to interrupt specific data * @on: Whether to set or reset the wake-up capability of this irq * * Conditional, as the underlying parent chip might not implement it. */ int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) return 0; if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on); return -ENOSYS; } EXPORT_SYMBOL_GPL(irq_chip_set_wake_parent); /** * irq_chip_request_resources_parent - Request resources on the parent interrupt * @data: Pointer to interrupt specific data */ int irq_chip_request_resources_parent(struct irq_data *data) { data = data->parent_data; if (data->chip->irq_request_resources) return data->chip->irq_request_resources(data); /* no error on missing optional irq_chip::irq_request_resources */ return 0; } EXPORT_SYMBOL_GPL(irq_chip_request_resources_parent); /** * irq_chip_release_resources_parent - Release resources on the parent interrupt * @data: Pointer to interrupt specific data */ void irq_chip_release_resources_parent(struct irq_data *data) { data = data->parent_data; if (data->chip->irq_release_resources) data->chip->irq_release_resources(data); } EXPORT_SYMBOL_GPL(irq_chip_release_resources_parent); #endif /** * irq_chip_compose_msi_msg - Compose msi message for a irq chip * @data: Pointer to interrupt specific data * @msg: Pointer to the MSI message * * For hierarchical domains we find the first chip in the hierarchy * which implements the irq_compose_msi_msg callback. For non * hierarchical we use the top level chip. */ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct irq_data *pos; for (pos = NULL; !pos && data; data = irqd_get_parent_data(data)) { if (data->chip && data->chip->irq_compose_msi_msg) pos = data; } if (!pos) return -ENOSYS; pos->chip->irq_compose_msi_msg(pos, msg); return 0; } static struct device *irq_get_pm_device(struct irq_data *data) { if (data->domain) return data->domain->pm_dev; return NULL; } /** * irq_chip_pm_get - Enable power for an IRQ chip * @data: Pointer to interrupt specific data * * Enable the power to the IRQ chip referenced by the interrupt data * structure. */ int irq_chip_pm_get(struct irq_data *data) { struct device *dev = irq_get_pm_device(data); int retval = 0; if (IS_ENABLED(CONFIG_PM) && dev) retval = pm_runtime_resume_and_get(dev); return retval; } /** * irq_chip_pm_put - Disable power for an IRQ chip * @data: Pointer to interrupt specific data * * Disable the power to the IRQ chip referenced by the interrupt data * structure, belongs. Note that power will only be disabled, once this * function has been called for all IRQs that have called irq_chip_pm_get(). */ int irq_chip_pm_put(struct irq_data *data) { struct device *dev = irq_get_pm_device(data); int retval = 0; if (IS_ENABLED(CONFIG_PM) && dev) retval = pm_runtime_put(dev); return (retval < 0) ? retval : 0; } |
| 59 58 59 59 59 2 2 2 19 21 21 21 11 11 5 5 11 5 11 22 8 8 5 5 5 4 4 3 4 3 22 21 21 11 11 3 11 11 11 10 11 10 10 25 25 25 12 13 4 7 4 4 4 4 5 5 5 5 5 22 22 22 22 5 4 2 2 2 2 2 2 2 2 2 2 2 1 1 2 1 2 2 2 2 2 3 5 4 5 21 22 20 5 5 5 5 22 22 22 15 22 22 22 1 11 5 4 22 22 22 20 2 5 4 2 2 2 3 1 1 1 2 2 10 8 20 20 20 20 20 20 20 20 20 20 5 5 3 1 1 1 2 5 1 22 1 2 1 2 1 1 2 21 5 1 2 3 21 20 19 20 5 5 2 4 1 3 22 20 20 20 22 2 22 21 10 12 25 12 22 22 22 22 22 1 22 2 2 3 2 2 4 13 5 4 4 14 2 4 18 30 29 28 3 6 25 22 3 18 7 7 22 22 7 15 22 14 14 4 10 8 3 4 8 12 1 1 2 2 2 13 14 5 1 12 16 9 13 16 16 6 6 18 18 3 1 3 2 19 5 1 4 4 7 2 4 78 1 1 15 69 1 8 13 13 8 24 24 26 17 3 4 7 2 7 5 8 5 45 1 30 19 24 63 217 59 56 3 3 2 54 56 56 45 45 1 1 65 2 61 3 62 1 11 1 1 12 12 49 3 56 3 57 66 2 5 2 57 54 5 59 5 54 55 3 58 3 2 53 11 1 36 8 45 44 2 3 1 66 68 71 68 71 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared application/kernel submission and completion ring pairs, for * supporting fast/efficient IO. * * A note on the read/write ordering memory barriers that are matched between * the application and kernel side. * * After the application reads the CQ ring tail, it must use an * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses * before writing the tail (using smp_load_acquire to read the tail will * do). It also needs a smp_mb() before updating CQ head (ordering the * entry load(s) with the head store), pairing with an implicit barrier * through a control-dependency in io_get_cqe (smp_store_release to * store head will do). Failure to do so could lead to reading invalid * CQ entries. * * Likewise, the application must use an appropriate smp_wmb() before * writing the SQ tail (ordering SQ entry stores with the tail store), * which pairs with smp_load_acquire in io_get_sqring (smp_store_release * to store the tail will do). And it needs a barrier ordering the SQ * head load before writing new SQ entries (smp_load_acquire to read * head will do). * * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* * updating the SQ tail; a full memory barrier smp_mb() is needed * between. * * Also see the examples in the liburing library: * * git://git.kernel.org/pub/scm/linux/kernel/git/axboe/liburing.git * * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens * from data shared between the kernel and application. This is done both * for ordering purposes, but also to ensure that once a value is loaded from * data that the application could potentially modify, it remains stable. * * Copyright (C) 2018-2019 Jens Axboe * Copyright (c) 2018-2019 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <net/compat.h> #include <linux/refcount.h> #include <linux/uio.h> #include <linux/bits.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/bvec.h> #include <linux/net.h> #include <net/sock.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include <linux/fsnotify.h> #include <linux/fadvise.h> #include <linux/task_work.h> #include <linux/io_uring.h> #include <linux/io_uring/cmd.h> #include <linux/audit.h> #include <linux/security.h> #include <linux/jump_label.h> #include <asm/shmparam.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> #include <uapi/linux/io_uring.h> #include "io-wq.h" #include "filetable.h" #include "io_uring.h" #include "opdef.h" #include "refs.h" #include "tctx.h" #include "register.h" #include "sqpoll.h" #include "fdinfo.h" #include "kbuf.h" #include "rsrc.h" #include "cancel.h" #include "net.h" #include "notif.h" #include "waitid.h" #include "futex.h" #include "napi.h" #include "uring_cmd.h" #include "msg_ring.h" #include "memmap.h" #include "zcrx.h" #include "timeout.h" #include "poll.h" #include "rw.h" #include "alloc_cache.h" #include "eventfd.h" #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \ IOSQE_IO_HARDLINK | IOSQE_ASYNC) #define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ REQ_F_INFLIGHT | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | IO_REQ_LINK_FLAGS | \ REQ_F_REISSUE | REQ_F_POLLED | \ IO_REQ_CLEAN_FLAGS) #define IO_TCTX_REFS_CACHE_NR (1U << 10) #define IO_COMPL_BATCH 32 #define IO_REQ_ALLOC_BATCH 8 #define IO_LOCAL_TW_DEFAULT_MAX 20 struct io_defer_entry { struct list_head list; struct io_kiocb *req; }; /* requests with any of those set should undergo io_disarm_next() */ #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) /* * No waiters. It's larger than any valid value of the tw counter * so that tests against ->cq_wait_nr would fail and skip wake_up(). */ #define IO_CQ_WAKE_INIT (-1U) /* Forced wake up if there is a waiter regardless of ->cq_wait_nr */ #define IO_CQ_WAKE_FORCE (IO_CQ_WAKE_INIT >> 1) static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all, bool is_sqpoll_thread); static void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags); static void __io_req_caches_free(struct io_ring_ctx *ctx); static __read_mostly DEFINE_STATIC_KEY_FALSE(io_key_has_sqarray); struct kmem_cache *req_cachep; static struct workqueue_struct *iou_wq __ro_after_init; static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; #ifdef CONFIG_SYSCTL static const struct ctl_table kernel_io_uring_disabled_table[] = { { .procname = "io_uring_disabled", .data = &sysctl_io_uring_disabled, .maxlen = sizeof(sysctl_io_uring_disabled), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "io_uring_group", .data = &sysctl_io_uring_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, }; #endif static void io_poison_cached_req(struct io_kiocb *req) { req->ctx = IO_URING_PTR_POISON; req->tctx = IO_URING_PTR_POISON; req->file = IO_URING_PTR_POISON; req->creds = IO_URING_PTR_POISON; req->io_task_work.func = IO_URING_PTR_POISON; req->apoll = IO_URING_PTR_POISON; } static void io_poison_req(struct io_kiocb *req) { io_poison_cached_req(req); req->async_data = IO_URING_PTR_POISON; req->kbuf = IO_URING_PTR_POISON; req->comp_list.next = IO_URING_PTR_POISON; req->file_node = IO_URING_PTR_POISON; req->link = IO_URING_PTR_POISON; } static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) { return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx) { return READ_ONCE(ctx->rings->cq.tail) - READ_ONCE(ctx->rings->cq.head); } static bool io_match_linked(struct io_kiocb *head) { struct io_kiocb *req; io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; } return false; } /* * As io_match_task() but protected against racing with linked timeouts. * User must not hold timeout_lock. */ bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx, bool cancel_all) { bool matched; if (tctx && head->tctx != tctx) return false; if (cancel_all) return true; if (head->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ raw_spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); raw_spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } return matched; } static inline void req_fail_link_node(struct io_kiocb *req, int res) { req_set_fail(req); io_req_set_res(req, res, 0); } static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx) { if (IS_ENABLED(CONFIG_KASAN)) io_poison_cached_req(req); wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); } static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); complete(&ctx->ref_comp); } static __cold void io_fallback_req_func(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, fallback_work.work); struct llist_node *node = llist_del_all(&ctx->fallback_llist); struct io_kiocb *req, *tmp; struct io_tw_state ts = {}; percpu_ref_get(&ctx->refs); mutex_lock(&ctx->uring_lock); llist_for_each_entry_safe(req, tmp, node, io_task_work.node) req->io_task_work.func(req, ts); io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); percpu_ref_put(&ctx->refs); } static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits) { unsigned int hash_buckets; int i; do { hash_buckets = 1U << bits; table->hbs = kvmalloc_array(hash_buckets, sizeof(table->hbs[0]), GFP_KERNEL_ACCOUNT); if (table->hbs) break; if (bits == 1) return -ENOMEM; bits--; } while (1); table->hash_bits = bits; for (i = 0; i < hash_buckets; i++) INIT_HLIST_HEAD(&table->hbs[i].list); return 0; } static void io_free_alloc_caches(struct io_ring_ctx *ctx) { io_alloc_cache_free(&ctx->apoll_cache, kfree); io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); io_alloc_cache_free(&ctx->cmd_cache, io_cmd_cache_free); io_futex_cache_free(ctx); io_rsrc_cache_free(ctx); } static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; int hash_bits; bool ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; xa_init(&ctx->io_bl_xa); /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread, but * don't keep too many buckets to not overconsume memory. */ hash_bits = ilog2(p->cq_entries) - 5; hash_bits = clamp(hash_bits, 1, 8); if (io_alloc_hash_table(&ctx->cancel_table, hash_bits)) goto err; if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, 0, GFP_KERNEL)) goto err; ctx->flags = p->flags; ctx->hybrid_poll_time = LLONG_MAX; atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT); init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); INIT_LIST_HEAD(&ctx->cq_overflow_list); ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX, sizeof(struct async_poll), 0); ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_msghdr), offsetof(struct io_async_msghdr, clear)); ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_rw), offsetof(struct io_async_rw, clear)); ret |= io_alloc_cache_init(&ctx->cmd_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_cmd), sizeof(struct io_async_cmd)); ret |= io_futex_cache_init(ctx); ret |= io_rsrc_cache_init(ctx); if (ret) goto free_ref; init_completion(&ctx->ref_comp); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->cq_wait); init_waitqueue_head(&ctx->poll_wq); spin_lock_init(&ctx->completion_lock); raw_spin_lock_init(&ctx->timeout_lock); INIT_WQ_LIST(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); INIT_LIST_HEAD(&ctx->ltimeout_list); init_llist_head(&ctx->work_llist); INIT_LIST_HEAD(&ctx->tctx_list); ctx->submit_state.free_list.next = NULL; INIT_HLIST_HEAD(&ctx->waitid_list); xa_init_flags(&ctx->zcrx_ctxs, XA_FLAGS_ALLOC); #ifdef CONFIG_FUTEX INIT_HLIST_HEAD(&ctx->futex_list); #endif INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd); io_napi_init(ctx); mutex_init(&ctx->mmap_lock); return ctx; free_ref: percpu_ref_exit(&ctx->refs); err: io_free_alloc_caches(ctx); kvfree(ctx->cancel_table.hbs); xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; } static void io_clean_op(struct io_kiocb *req) { if (unlikely(req->flags & REQ_F_BUFFER_SELECTED)) io_kbuf_drop_legacy(req); if (req->flags & REQ_F_NEED_CLEANUP) { const struct io_cold_def *def = &io_cold_defs[req->opcode]; if (def->cleanup) def->cleanup(req); } if (req->flags & REQ_F_INFLIGHT) atomic_dec(&req->tctx->inflight_tracked); if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { kfree(req->async_data); req->async_data = NULL; } req->flags &= ~IO_REQ_CLEAN_FLAGS; } /* * Mark the request as inflight, so that file cancelation will find it. * Can be used if the file is an io_uring instance, or if the request itself * relies on ->mm being alive for the duration of the request. */ inline void io_req_track_inflight(struct io_kiocb *req) { if (!(req->flags & REQ_F_INFLIGHT)) { req->flags |= REQ_F_INFLIGHT; atomic_inc(&req->tctx->inflight_tracked); } } static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) return NULL; req->flags &= ~REQ_F_ARM_LTIMEOUT; req->flags |= REQ_F_LINK_TIMEOUT; /* linked timeouts should have two refs once prep'ed */ io_req_set_refcount(req); __io_req_set_refcount(req->link, 2); return req->link; } static void io_prep_async_work(struct io_kiocb *req) { const struct io_issue_def *def = &io_issue_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; if (!(req->flags & REQ_F_CREDS)) { req->flags |= REQ_F_CREDS; req->creds = get_current_cred(); } req->work.list.next = NULL; atomic_set(&req->work.flags, 0); if (req->flags & REQ_F_FORCE_ASYNC) atomic_or(IO_WQ_WORK_CONCURRENT, &req->work.flags); if (req->file && !(req->flags & REQ_F_FIXED_FILE)) req->flags |= io_file_get_flags(req->file); if (req->file && (req->flags & REQ_F_ISREG)) { bool should_hash = def->hash_reg_file; /* don't serialize this request if the fs doesn't need it */ if (should_hash && (req->file->f_flags & O_DIRECT) && (req->file->f_op->fop_flags & FOP_DIO_PARALLEL_WRITE)) should_hash = false; if (should_hash || (ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { if (def->unbound_nonreg_file) atomic_or(IO_WQ_WORK_UNBOUND, &req->work.flags); } } static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; raw_spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); raw_spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); } } static void io_queue_iowq(struct io_kiocb *req) { struct io_uring_task *tctx = req->tctx; BUG_ON(!tctx); if ((current->flags & PF_KTHREAD) || !tctx->io_wq) { io_req_task_queue_fail(req, -ECANCELED); return; } /* init ->work of the whole link before punting */ io_prep_async_link(req); /* * Not expected to happen, but if we do have a bug where this _can_ * happen, catch it here and ensure the request is marked as * canceled. That will make io-wq go through the usual work cancel * procedure rather than attempt to run this request (or create a new * worker for it). */ if (WARN_ON_ONCE(!same_thread_group(tctx->task, current))) atomic_or(IO_WQ_WORK_CANCEL, &req->work.flags); trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work)); io_wq_enqueue(tctx->io_wq, &req->work); } static void io_req_queue_iowq_tw(struct io_kiocb *req, io_tw_token_t tw) { io_queue_iowq(req); } void io_req_queue_iowq(struct io_kiocb *req) { req->io_task_work.func = io_req_queue_iowq_tw; io_req_task_work_add(req); } static unsigned io_linked_nr(struct io_kiocb *req) { struct io_kiocb *tmp; unsigned nr = 0; io_for_each_link(tmp, req) nr++; return nr; } static __cold noinline void io_queue_deferred(struct io_ring_ctx *ctx) { bool drain_seen = false, first = true; lockdep_assert_held(&ctx->uring_lock); __io_req_caches_free(ctx); while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); drain_seen |= de->req->flags & REQ_F_IO_DRAIN; if ((drain_seen || first) && ctx->nr_req_allocated != ctx->nr_drained) return; list_del_init(&de->list); ctx->nr_drained -= io_linked_nr(de->req); io_req_task_queue(de->req); kfree(de); first = false; } } void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { if (ctx->poll_activated) io_poll_wq_wake(ctx); if (ctx->off_timeout_used) io_flush_timeouts(ctx); if (ctx->has_evfd) io_eventfd_signal(ctx, true); } static inline void __io_cq_lock(struct io_ring_ctx *ctx) { if (!ctx->lockless_cq) spin_lock(&ctx->completion_lock); } static inline void io_cq_lock(struct io_ring_ctx *ctx) __acquires(ctx->completion_lock) { spin_lock(&ctx->completion_lock); } static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx) { io_commit_cqring(ctx); if (!ctx->task_complete) { if (!ctx->lockless_cq) spin_unlock(&ctx->completion_lock); /* IOPOLL rings only need to wake up if it's also SQPOLL */ if (!ctx->syscall_iopoll) io_cqring_wake(ctx); } io_commit_cqring_flush(ctx); } static void io_cq_unlock_post(struct io_ring_ctx *ctx) __releases(ctx->completion_lock) { io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_wake(ctx); io_commit_cqring_flush(ctx); } static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying) { lockdep_assert_held(&ctx->uring_lock); /* don't abort if we're dying, entries must get freed */ if (!dying && __io_cqring_events(ctx) == ctx->cq_entries) return; io_cq_lock(ctx); while (!list_empty(&ctx->cq_overflow_list)) { size_t cqe_size = sizeof(struct io_uring_cqe); struct io_uring_cqe *cqe; struct io_overflow_cqe *ocqe; bool is_cqe32 = false; ocqe = list_first_entry(&ctx->cq_overflow_list, struct io_overflow_cqe, list); if (ocqe->cqe.flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32) { is_cqe32 = true; cqe_size <<= 1; } if (ctx->flags & IORING_SETUP_CQE32) is_cqe32 = false; if (!dying) { if (!io_get_cqe_overflow(ctx, &cqe, true, is_cqe32)) break; memcpy(cqe, &ocqe->cqe, cqe_size); } list_del(&ocqe->list); kfree(ocqe); /* * For silly syzbot cases that deliberately overflow by huge * amounts, check if we need to resched and drop and * reacquire the locks if so. Nothing real would ever hit this. * Ideally we'd have a non-posting unlock for this, but hard * to care for a non-real case. */ if (need_resched()) { ctx->cqe_sentinel = ctx->cqe_cached; io_cq_unlock_post(ctx); mutex_unlock(&ctx->uring_lock); cond_resched(); mutex_lock(&ctx->uring_lock); io_cq_lock(ctx); } } if (list_empty(&ctx->cq_overflow_list)) { clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } io_cq_unlock_post(ctx); } static void io_cqring_overflow_kill(struct io_ring_ctx *ctx) { if (ctx->rings) __io_cqring_overflow_flush(ctx, true); } static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); __io_cqring_overflow_flush(ctx, false); mutex_unlock(&ctx->uring_lock); } /* must to be called somewhat shortly after putting a request */ static inline void io_put_task(struct io_kiocb *req) { struct io_uring_task *tctx = req->tctx; if (likely(tctx->task == current)) { tctx->cached_refs++; } else { percpu_counter_sub(&tctx->inflight, 1); if (unlikely(atomic_read(&tctx->in_cancel))) wake_up(&tctx->wait); put_task_struct(tctx->task); } } void io_task_refs_refill(struct io_uring_task *tctx) { unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; percpu_counter_add(&tctx->inflight, refill); refcount_add(refill, ¤t->usage); tctx->cached_refs += refill; } static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; unsigned int refs = tctx->cached_refs; if (refs) { tctx->cached_refs = 0; percpu_counter_sub(&tctx->inflight, refs); put_task_struct_many(task, refs); } } static __cold bool io_cqring_add_overflow(struct io_ring_ctx *ctx, struct io_overflow_cqe *ocqe) { lockdep_assert_held(&ctx->completion_lock); if (!ocqe) { struct io_rings *r = ctx->rings; /* * If we're in ring overflow flush mode, or in task cancel mode, * or cannot allocate an overflow entry, then we need to drop it * on the floor. */ WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq); return false; } if (list_empty(&ctx->cq_overflow_list)) { set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags); } list_add_tail(&ocqe->list, &ctx->cq_overflow_list); return true; } static struct io_overflow_cqe *io_alloc_ocqe(struct io_ring_ctx *ctx, struct io_cqe *cqe, struct io_big_cqe *big_cqe, gfp_t gfp) { struct io_overflow_cqe *ocqe; size_t ocq_size = sizeof(struct io_overflow_cqe); bool is_cqe32 = false; if (cqe->flags & IORING_CQE_F_32 || ctx->flags & IORING_SETUP_CQE32) { is_cqe32 = true; ocq_size += sizeof(struct io_uring_cqe); } ocqe = kzalloc(ocq_size, gfp | __GFP_ACCOUNT); trace_io_uring_cqe_overflow(ctx, cqe->user_data, cqe->res, cqe->flags, ocqe); if (ocqe) { ocqe->cqe.user_data = cqe->user_data; ocqe->cqe.res = cqe->res; ocqe->cqe.flags = cqe->flags; if (is_cqe32 && big_cqe) { ocqe->cqe.big_cqe[0] = big_cqe->extra1; ocqe->cqe.big_cqe[1] = big_cqe->extra2; } } if (big_cqe) big_cqe->extra1 = big_cqe->extra2 = 0; return ocqe; } /* * Fill an empty dummy CQE, in case alignment is off for posting a 32b CQE * because the ring is a single 16b entry away from wrapping. */ static bool io_fill_nop_cqe(struct io_ring_ctx *ctx, unsigned int off) { if (__io_cqring_events(ctx) < ctx->cq_entries) { struct io_uring_cqe *cqe = &ctx->rings->cqes[off]; cqe->user_data = 0; cqe->res = 0; cqe->flags = IORING_CQE_F_SKIP; ctx->cached_cq_tail++; return true; } return false; } /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32) { struct io_rings *rings = ctx->rings; unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); unsigned int free, queued, len; /* * Posting into the CQ when there are pending overflowed CQEs may break * ordering guarantees, which will affect links, F_MORE users and more. * Force overflow the completion. */ if (!overflow && (ctx->check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))) return false; /* * Post dummy CQE if a 32b CQE is needed and there's only room for a * 16b CQE before the ring wraps. */ if (cqe32 && off + 1 == ctx->cq_entries) { if (!io_fill_nop_cqe(ctx, off)) return false; off = 0; } /* userspace may cheat modifying the tail, be safe and do min */ queued = min(__io_cqring_events(ctx), ctx->cq_entries); free = ctx->cq_entries - queued; /* we need a contiguous range, limit based on the current array offset */ len = min(free, ctx->cq_entries - off); if (len < (cqe32 + 1)) return false; if (ctx->flags & IORING_SETUP_CQE32) { off <<= 1; len <<= 1; } ctx->cqe_cached = &rings->cqes[off]; ctx->cqe_sentinel = ctx->cqe_cached + len; return true; } static bool io_fill_cqe_aux32(struct io_ring_ctx *ctx, struct io_uring_cqe src_cqe[2]) { struct io_uring_cqe *cqe; if (WARN_ON_ONCE(!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED)))) return false; if (unlikely(!io_get_cqe(ctx, &cqe, true))) return false; memcpy(cqe, src_cqe, 2 * sizeof(*cqe)); trace_io_uring_complete(ctx, NULL, cqe); return true; } static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { bool cqe32 = cflags & IORING_CQE_F_32; struct io_uring_cqe *cqe; if (likely(io_get_cqe(ctx, &cqe, cqe32))) { WRITE_ONCE(cqe->user_data, user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, cflags); if (cqe32) { WRITE_ONCE(cqe->big_cqe[0], 0); WRITE_ONCE(cqe->big_cqe[1], 0); } trace_io_uring_complete(ctx, NULL, cqe); return true; } return false; } static inline struct io_cqe io_init_cqe(u64 user_data, s32 res, u32 cflags) { return (struct io_cqe) { .user_data = user_data, .res = res, .flags = cflags }; } static __cold void io_cqe_overflow(struct io_ring_ctx *ctx, struct io_cqe *cqe, struct io_big_cqe *big_cqe) { struct io_overflow_cqe *ocqe; ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_KERNEL); spin_lock(&ctx->completion_lock); io_cqring_add_overflow(ctx, ocqe); spin_unlock(&ctx->completion_lock); } static __cold bool io_cqe_overflow_locked(struct io_ring_ctx *ctx, struct io_cqe *cqe, struct io_big_cqe *big_cqe) { struct io_overflow_cqe *ocqe; ocqe = io_alloc_ocqe(ctx, cqe, big_cqe, GFP_ATOMIC); return io_cqring_add_overflow(ctx, ocqe); } bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { bool filled; io_cq_lock(ctx); filled = io_fill_cqe_aux(ctx, user_data, res, cflags); if (unlikely(!filled)) { struct io_cqe cqe = io_init_cqe(user_data, res, cflags); filled = io_cqe_overflow_locked(ctx, &cqe, NULL); } io_cq_unlock_post(ctx); return filled; } /* * Must be called from inline task_work so we now a flush will happen later, * and obviously with ctx->uring_lock held (tw always has that). */ void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { lockdep_assert_held(&ctx->uring_lock); lockdep_assert(ctx->lockless_cq); if (!io_fill_cqe_aux(ctx, user_data, res, cflags)) { struct io_cqe cqe = io_init_cqe(user_data, res, cflags); io_cqe_overflow(ctx, &cqe, NULL); } ctx->submit_state.cq_flush = true; } /* * A helper for multishot requests posting additional CQEs. * Should only be used from a task_work including IO_URING_F_MULTISHOT. */ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags) { struct io_ring_ctx *ctx = req->ctx; bool posted; /* * If multishot has already posted deferred completions, ensure that * those are flushed first before posting this one. If not, CQEs * could get reordered. */ if (!wq_list_empty(&ctx->submit_state.compl_reqs)) __io_submit_flush_completions(ctx); lockdep_assert(!io_wq_current_is_worker()); lockdep_assert_held(&ctx->uring_lock); if (!ctx->lockless_cq) { spin_lock(&ctx->completion_lock); posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags); spin_unlock(&ctx->completion_lock); } else { posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags); } ctx->submit_state.cq_flush = true; return posted; } /* * A helper for multishot requests posting additional CQEs. * Should only be used from a task_work including IO_URING_F_MULTISHOT. */ bool io_req_post_cqe32(struct io_kiocb *req, struct io_uring_cqe cqe[2]) { struct io_ring_ctx *ctx = req->ctx; bool posted; lockdep_assert(!io_wq_current_is_worker()); lockdep_assert_held(&ctx->uring_lock); cqe[0].user_data = req->cqe.user_data; if (!ctx->lockless_cq) { spin_lock(&ctx->completion_lock); posted = io_fill_cqe_aux32(ctx, cqe); spin_unlock(&ctx->completion_lock); } else { posted = io_fill_cqe_aux32(ctx, cqe); } ctx->submit_state.cq_flush = true; return posted; } static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; bool completed = true; /* * All execution paths but io-wq use the deferred completions by * passing IO_URING_F_COMPLETE_DEFER and thus should not end up here. */ if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_IOWQ))) return; /* * Handle special CQ sync cases via task_work. DEFER_TASKRUN requires * the submitter task context, IOPOLL protects with uring_lock. */ if (ctx->lockless_cq || (req->flags & REQ_F_REISSUE)) { defer_complete: req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); return; } io_cq_lock(ctx); if (!(req->flags & REQ_F_CQE_SKIP)) completed = io_fill_cqe_req(ctx, req); io_cq_unlock_post(ctx); if (!completed) goto defer_complete; /* * We don't free the request here because we know it's called from * io-wq only, which holds a reference, so it cannot be the last put. */ req_ref_put(req); } void io_req_defer_failed(struct io_kiocb *req, s32 res) __must_hold(&ctx->uring_lock) { const struct io_cold_def *def = &io_cold_defs[req->opcode]; lockdep_assert_held(&req->ctx->uring_lock); req_set_fail(req); io_req_set_res(req, res, io_put_kbuf(req, res, NULL)); if (def->fail) def->fail(req); io_req_complete_defer(req); } /* * A request might get retired back into the request caches even before opcode * handlers and io_issue_sqe() are done with it, e.g. inline completion path. * Because of that, io_alloc_req() should be called only under ->uring_lock * and with extra caution to not get a request that is still worked on. */ __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO; void *reqs[IO_REQ_ALLOC_BATCH]; int ret; ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); /* * Bulk alloc is all-or-nothing. If we fail to get a batch, * retry single alloc to be on the safe side. */ if (unlikely(ret <= 0)) { reqs[0] = kmem_cache_alloc(req_cachep, gfp); if (!reqs[0]) return false; ret = 1; } percpu_ref_get_many(&ctx->refs, ret); ctx->nr_req_allocated += ret; while (ret--) { struct io_kiocb *req = reqs[ret]; io_req_add_to_cache(req, ctx); } return true; } __cold void io_free_req(struct io_kiocb *req) { /* refs were already put, restore them for io_req_task_complete() */ req->flags &= ~REQ_F_REFCOUNT; /* we only want to free it, don't post CQEs */ req->flags |= REQ_F_CQE_SKIP; req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); } static void __io_req_find_next_prep(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; spin_lock(&ctx->completion_lock); io_disarm_next(req); spin_unlock(&ctx->completion_lock); } static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt; /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other * dependencies to the next request. In case of failure, fail the rest * of the chain. */ if (unlikely(req->flags & IO_DISARM_MASK)) __io_req_find_next_prep(req); nxt = req->link; req->link = NULL; return nxt; } static void ctx_flush_and_put(struct io_ring_ctx *ctx, io_tw_token_t tw) { if (!ctx) return; if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); percpu_ref_put(&ctx->refs); } /* * Run queued task_work, returning the number of entries processed in *count. * If more entries than max_entries are available, stop processing once this * is reached and return the rest of the list. */ struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries) { struct io_ring_ctx *ctx = NULL; struct io_tw_state ts = { }; do { struct llist_node *next = node->next; struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); if (req->ctx != ctx) { ctx_flush_and_put(ctx, ts); ctx = req->ctx; mutex_lock(&ctx->uring_lock); percpu_ref_get(&ctx->refs); } INDIRECT_CALL_2(req->io_task_work.func, io_poll_task_func, io_req_rw_complete, req, ts); node = next; (*count)++; if (unlikely(need_resched())) { ctx_flush_and_put(ctx, ts); ctx = NULL; cond_resched(); } } while (node && *count < max_entries); ctx_flush_and_put(ctx, ts); return node; } static __cold void __io_fallback_tw(struct llist_node *node, bool sync) { struct io_ring_ctx *last_ctx = NULL; struct io_kiocb *req; while (node) { req = container_of(node, struct io_kiocb, io_task_work.node); node = node->next; if (last_ctx != req->ctx) { if (last_ctx) { if (sync) flush_delayed_work(&last_ctx->fallback_work); percpu_ref_put(&last_ctx->refs); } last_ctx = req->ctx; percpu_ref_get(&last_ctx->refs); } if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist)) schedule_delayed_work(&last_ctx->fallback_work, 1); } if (last_ctx) { if (sync) flush_delayed_work(&last_ctx->fallback_work); percpu_ref_put(&last_ctx->refs); } } static void io_fallback_tw(struct io_uring_task *tctx, bool sync) { struct llist_node *node = llist_del_all(&tctx->task_list); __io_fallback_tw(node, sync); } struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count) { struct llist_node *node; if (unlikely(current->flags & PF_EXITING)) { io_fallback_tw(tctx, true); return NULL; } node = llist_del_all(&tctx->task_list); if (node) { node = llist_reverse_order(node); node = io_handle_tw_list(node, count, max_entries); } /* relaxed read is enough as only the task itself sets ->in_cancel */ if (unlikely(atomic_read(&tctx->in_cancel))) io_uring_drop_tctx_refs(current); trace_io_uring_task_work_run(tctx, *count); return node; } void tctx_task_work(struct callback_head *cb) { struct io_uring_task *tctx; struct llist_node *ret; unsigned int count = 0; tctx = container_of(cb, struct io_uring_task, task_work); ret = tctx_task_work_run(tctx, UINT_MAX, &count); /* can't happen */ WARN_ON_ONCE(ret); } static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; unsigned nr_wait, nr_tw, nr_tw_prev; struct llist_node *head; /* See comment above IO_CQ_WAKE_INIT */ BUILD_BUG_ON(IO_CQ_WAKE_FORCE <= IORING_MAX_CQ_ENTRIES); /* * We don't know how many reuqests is there in the link and whether * they can even be queued lazily, fall back to non-lazy. */ if (req->flags & IO_REQ_LINK_FLAGS) flags &= ~IOU_F_TWQ_LAZY_WAKE; guard(rcu)(); head = READ_ONCE(ctx->work_llist.first); do { nr_tw_prev = 0; if (head) { struct io_kiocb *first_req = container_of(head, struct io_kiocb, io_task_work.node); /* * Might be executed at any moment, rely on * SLAB_TYPESAFE_BY_RCU to keep it alive. */ nr_tw_prev = READ_ONCE(first_req->nr_tw); } /* * Theoretically, it can overflow, but that's fine as one of * previous adds should've tried to wake the task. */ nr_tw = nr_tw_prev + 1; if (!(flags & IOU_F_TWQ_LAZY_WAKE)) nr_tw = IO_CQ_WAKE_FORCE; req->nr_tw = nr_tw; req->io_task_work.node.next = head; } while (!try_cmpxchg(&ctx->work_llist.first, &head, &req->io_task_work.node)); /* * cmpxchg implies a full barrier, which pairs with the barrier * in set_current_state() on the io_cqring_wait() side. It's used * to ensure that either we see updated ->cq_wait_nr, or waiters * going to sleep will observe the work added to the list, which * is similar to the wait/wawke task state sync. */ if (!head) { if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); if (ctx->has_evfd) io_eventfd_signal(ctx, false); } nr_wait = atomic_read(&ctx->cq_wait_nr); /* not enough or no one is waiting */ if (nr_tw < nr_wait) return; /* the previous add has already woken it up */ if (nr_tw_prev >= nr_wait) return; wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE); } static void io_req_normal_work_add(struct io_kiocb *req) { struct io_uring_task *tctx = req->tctx; struct io_ring_ctx *ctx = req->ctx; /* task_work already pending, we're done */ if (!llist_add(&req->io_task_work.node, &tctx->task_list)) return; if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); /* SQPOLL doesn't need the task_work added, it'll run it itself */ if (ctx->flags & IORING_SETUP_SQPOLL) { __set_notify_signal(tctx->task); return; } if (likely(!task_work_add(tctx->task, &tctx->task_work, ctx->notify_method))) return; io_fallback_tw(tctx, false); } void __io_req_task_work_add(struct io_kiocb *req, unsigned flags) { if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN) io_req_local_work_add(req, flags); else io_req_normal_work_add(req); } void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags) { if (WARN_ON_ONCE(!(req->ctx->flags & IORING_SETUP_DEFER_TASKRUN))) return; __io_req_task_work_add(req, flags); } static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx) { struct llist_node *node = llist_del_all(&ctx->work_llist); __io_fallback_tw(node, false); node = llist_del_all(&ctx->retry_llist); __io_fallback_tw(node, false); } static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events, int min_events) { if (!io_local_work_pending(ctx)) return false; if (events < min_events) return true; if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); return false; } static int __io_run_local_work_loop(struct llist_node **node, io_tw_token_t tw, int events) { int ret = 0; while (*node) { struct llist_node *next = (*node)->next; struct io_kiocb *req = container_of(*node, struct io_kiocb, io_task_work.node); INDIRECT_CALL_2(req->io_task_work.func, io_poll_task_func, io_req_rw_complete, req, tw); *node = next; if (++ret >= events) break; } return ret; } static int __io_run_local_work(struct io_ring_ctx *ctx, io_tw_token_t tw, int min_events, int max_events) { struct llist_node *node; unsigned int loops = 0; int ret = 0; if (WARN_ON_ONCE(ctx->submitter_task != current)) return -EEXIST; if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); again: min_events -= ret; ret = __io_run_local_work_loop(&ctx->retry_llist.first, tw, max_events); if (ctx->retry_llist.first) goto retry_done; /* * llists are in reverse order, flip it back the right way before * running the pending items. */ node = llist_reverse_order(llist_del_all(&ctx->work_llist)); ret += __io_run_local_work_loop(&node, tw, max_events - ret); ctx->retry_llist.first = node; loops++; if (io_run_local_work_continue(ctx, ret, min_events)) goto again; retry_done: io_submit_flush_completions(ctx); if (io_run_local_work_continue(ctx, ret, min_events)) goto again; trace_io_uring_local_work_run(ctx, ret, loops); return ret; } static inline int io_run_local_work_locked(struct io_ring_ctx *ctx, int min_events) { struct io_tw_state ts = {}; if (!io_local_work_pending(ctx)) return 0; return __io_run_local_work(ctx, ts, min_events, max(IO_LOCAL_TW_DEFAULT_MAX, min_events)); } static int io_run_local_work(struct io_ring_ctx *ctx, int min_events, int max_events) { struct io_tw_state ts = {}; int ret; mutex_lock(&ctx->uring_lock); ret = __io_run_local_work(ctx, ts, min_events, max_events); mutex_unlock(&ctx->uring_lock); return ret; } static void io_req_task_cancel(struct io_kiocb *req, io_tw_token_t tw) { io_tw_lock(req->ctx, tw); io_req_defer_failed(req, req->cqe.res); } void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw) { struct io_ring_ctx *ctx = req->ctx; io_tw_lock(ctx, tw); if (unlikely(io_should_terminate_tw(ctx))) io_req_defer_failed(req, -EFAULT); else if (req->flags & REQ_F_FORCE_ASYNC) io_queue_iowq(req); else io_queue_sqe(req, 0); } void io_req_task_queue_fail(struct io_kiocb *req, int ret) { io_req_set_res(req, ret, 0); req->io_task_work.func = io_req_task_cancel; io_req_task_work_add(req); } void io_req_task_queue(struct io_kiocb *req) { req->io_task_work.func = io_req_task_submit; io_req_task_work_add(req); } void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); if (nxt) io_req_task_queue(nxt); } static inline void io_req_put_rsrc_nodes(struct io_kiocb *req) { if (req->file_node) { io_put_rsrc_node(req->ctx, req->file_node); req->file_node = NULL; } if (req->flags & REQ_F_BUF_NODE) io_put_rsrc_node(req->ctx, req->buf_node); } static void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) __must_hold(&ctx->uring_lock) { do { struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) { if (req->flags & REQ_F_REISSUE) { node = req->comp_list.next; req->flags &= ~REQ_F_REISSUE; io_queue_iowq(req); continue; } if (req->flags & REQ_F_REFCOUNT) { node = req->comp_list.next; if (!req_ref_put_and_test(req)) continue; } if ((req->flags & REQ_F_POLLED) && req->apoll) { struct async_poll *apoll = req->apoll; if (apoll->double_poll) kfree(apoll->double_poll); io_cache_free(&ctx->apoll_cache, apoll); req->flags &= ~REQ_F_POLLED; } if (req->flags & IO_REQ_LINK_FLAGS) io_queue_next(req); if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) io_clean_op(req); } io_put_file(req); io_req_put_rsrc_nodes(req); io_put_task(req); node = req->comp_list.next; io_req_add_to_cache(req, ctx); } while (node); } void __io_submit_flush_completions(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { struct io_submit_state *state = &ctx->submit_state; struct io_wq_work_node *node; __io_cq_lock(ctx); __wq_list_for_each(node, &state->compl_reqs) { struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); /* * Requests marked with REQUEUE should not post a CQE, they * will go through the io-wq retry machinery and post one * later. */ if (!(req->flags & (REQ_F_CQE_SKIP | REQ_F_REISSUE)) && unlikely(!io_fill_cqe_req(ctx, req))) { if (ctx->lockless_cq) io_cqe_overflow(ctx, &req->cqe, &req->big_cqe); else io_cqe_overflow_locked(ctx, &req->cqe, &req->big_cqe); } } __io_cq_unlock_post(ctx); if (!wq_list_empty(&state->compl_reqs)) { io_free_batch_list(ctx, state->compl_reqs.first); INIT_WQ_LIST(&state->compl_reqs); } if (unlikely(ctx->drain_active)) io_queue_deferred(ctx); ctx->submit_state.cq_flush = false; } static unsigned io_cqring_events(struct io_ring_ctx *ctx) { /* See comment at the top of this file */ smp_rmb(); return __io_cqring_events(ctx); } /* * We can't just wait for polled events to come to us, we have to actively * find and complete them. */ static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) { if (!(ctx->flags & IORING_SETUP_IOPOLL)) return; mutex_lock(&ctx->uring_lock); while (!wq_list_empty(&ctx->iopoll_list)) { /* let it sleep and repeat later if can't complete a request */ if (io_do_iopoll(ctx, true) == 0) break; /* * Ensure we allow local-to-the-cpu processing to take place, * in this case we need to ensure that we reap all events. * Also let task_work, etc. to progress by releasing the mutex */ if (need_resched()) { mutex_unlock(&ctx->uring_lock); cond_resched(); mutex_lock(&ctx->uring_lock); } } mutex_unlock(&ctx->uring_lock); if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) io_move_task_work_from_local(ctx); } static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned int min_events) { unsigned int nr_events = 0; unsigned long check_cq; min_events = min(min_events, ctx->cq_entries); lockdep_assert_held(&ctx->uring_lock); if (!io_allowed_run_tw(ctx)) return -EEXIST; check_cq = READ_ONCE(ctx->check_cq); if (unlikely(check_cq)) { if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) __io_cqring_overflow_flush(ctx, false); /* * Similarly do not spin if we have not informed the user of any * dropped CQE. */ if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) return -EBADR; } /* * Don't enter poll loop if we already have events pending. * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ if (io_cqring_events(ctx)) return 0; do { int ret = 0; /* * If a submit got punted to a workqueue, we can have the * application entering polling for a command before it gets * issued. That app will hold the uring_lock for the duration * of the poll right here, so we need to take a breather every * now and then to ensure that the issue has a chance to add * the poll to the issued list. Otherwise we can spin here * forever, while the workqueue is stuck trying to acquire the * very same mutex. */ if (wq_list_empty(&ctx->iopoll_list) || io_task_work_pending(ctx)) { u32 tail = ctx->cached_cq_tail; (void) io_run_local_work_locked(ctx, min_events); if (task_work_pending(current) || wq_list_empty(&ctx->iopoll_list)) { mutex_unlock(&ctx->uring_lock); io_run_task_work(); mutex_lock(&ctx->uring_lock); } /* some requests don't go through iopoll_list */ if (tail != ctx->cached_cq_tail || wq_list_empty(&ctx->iopoll_list)) break; } ret = io_do_iopoll(ctx, !min_events); if (unlikely(ret < 0)) return ret; if (task_sigpending(current)) return -EINTR; if (need_resched()) break; nr_events += ret; } while (nr_events < min_events); return 0; } void io_req_task_complete(struct io_kiocb *req, io_tw_token_t tw) { io_req_complete_defer(req); } /* * After the iocb has been issued, it's safe to be found on the poll list. * Adding the kiocb to the list AFTER submission ensures that we don't * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; /* workqueue context doesn't hold uring_lock, grab it now */ if (unlikely(needs_lock)) mutex_lock(&ctx->uring_lock); /* * Track whether we have multiple files in our lists. This will impact * how we do polling eventually, not spinning if we're on potentially * different devices. */ if (wq_list_empty(&ctx->iopoll_list)) { ctx->poll_multi_queue = false; } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; list_req = container_of(ctx->iopoll_list.first, struct io_kiocb, comp_list); if (list_req->file != req->file) ctx->poll_multi_queue = true; } /* * For fast devices, IO may have already completed. If it has, add * it to the front so we find it first. */ if (READ_ONCE(req->iopoll_completed)) wq_list_add_head(&req->comp_list, &ctx->iopoll_list); else wq_list_add_tail(&req->comp_list, &ctx->iopoll_list); if (unlikely(needs_lock)) { /* * If IORING_SETUP_SQPOLL is enabled, sqes are either handle * in sq thread task context or in io worker task context. If * current task context is sq thread, we don't need to check * whether should wake up sq thread. */ if ((ctx->flags & IORING_SETUP_SQPOLL) && wq_has_sleeper(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); mutex_unlock(&ctx->uring_lock); } } io_req_flags_t io_file_get_flags(struct file *file) { io_req_flags_t res = 0; BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1); if (S_ISREG(file_inode(file)->i_mode)) res |= REQ_F_ISREG; if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT)) res |= REQ_F_SUPPORT_NOWAIT; return res; } static __cold void io_drain_req(struct io_kiocb *req) __must_hold(&ctx->uring_lock) { struct io_ring_ctx *ctx = req->ctx; bool drain = req->flags & IOSQE_IO_DRAIN; struct io_defer_entry *de; de = kmalloc(sizeof(*de), GFP_KERNEL_ACCOUNT); if (!de) { io_req_defer_failed(req, -ENOMEM); return; } io_prep_async_link(req); trace_io_uring_defer(req); de->req = req; ctx->nr_drained += io_linked_nr(req); list_add_tail(&de->list, &ctx->defer_list); io_queue_deferred(ctx); if (!drain && list_empty(&ctx->defer_list)) ctx->drain_active = false; } static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def, unsigned int issue_flags) { if (req->file || !def->needs_file) return true; if (req->flags & REQ_F_FIXED_FILE) req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags); else req->file = io_file_get_normal(req, req->cqe.fd); return !!req->file; } #define REQ_ISSUE_SLOW_FLAGS (REQ_F_CREDS | REQ_F_ARM_LTIMEOUT) static inline int __io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags, const struct io_issue_def *def) { const struct cred *creds = NULL; struct io_kiocb *link = NULL; int ret; if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) { if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) creds = override_creds(req->creds); if (req->flags & REQ_F_ARM_LTIMEOUT) link = __io_prep_linked_timeout(req); } if (!def->audit_skip) audit_uring_entry(req->opcode); ret = def->issue(req, issue_flags); if (!def->audit_skip) audit_uring_exit(!ret, ret); if (unlikely(creds || link)) { if (creds) revert_creds(creds); if (link) io_queue_linked_timeout(link); } return ret; } static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct io_issue_def *def = &io_issue_defs[req->opcode]; int ret; if (unlikely(!io_assign_file(req, def, issue_flags))) return -EBADF; ret = __io_issue_sqe(req, issue_flags, def); if (ret == IOU_COMPLETE) { if (issue_flags & IO_URING_F_COMPLETE_DEFER) io_req_complete_defer(req); else io_req_complete_post(req, issue_flags); return 0; } if (ret == IOU_ISSUE_SKIP_COMPLETE) { ret = 0; /* If the op doesn't have a file, we're not polling for it */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue) io_iopoll_req_issued(req, issue_flags); } return ret; } int io_poll_issue(struct io_kiocb *req, io_tw_token_t tw) { const unsigned int issue_flags = IO_URING_F_NONBLOCK | IO_URING_F_MULTISHOT | IO_URING_F_COMPLETE_DEFER; int ret; io_tw_lock(req->ctx, tw); WARN_ON_ONCE(!req->file); if (WARN_ON_ONCE(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EFAULT; ret = __io_issue_sqe(req, issue_flags, &io_issue_defs[req->opcode]); WARN_ON_ONCE(ret == IOU_ISSUE_SKIP_COMPLETE); return ret; } struct io_wq_work *io_wq_free_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_kiocb *nxt = NULL; if (req_ref_put_and_test_atomic(req)) { if (req->flags & IO_REQ_LINK_FLAGS) nxt = io_req_find_next(req); io_free_req(req); } return nxt ? &nxt->work : NULL; } void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); const struct io_issue_def *def = &io_issue_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED | IO_URING_F_IOWQ; bool needs_poll = false; int ret = 0, err = -ECANCELED; /* one will be dropped by io_wq_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) __io_req_set_refcount(req, 2); else req_ref_get(req); /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) { fail: io_req_task_queue_fail(req, err); return; } if (!io_assign_file(req, def, issue_flags)) { err = -EBADF; atomic_or(IO_WQ_WORK_CANCEL, &work->flags); goto fail; } /* * If DEFER_TASKRUN is set, it's only allowed to post CQEs from the * submitter task context. Final request completions are handed to the * right context, however this is not the case of auxiliary CQEs, * which is the main mean of operation for multishot requests. * Don't allow any multishot execution from io-wq. It's more restrictive * than necessary and also cleaner. */ if (req->flags & (REQ_F_MULTISHOT|REQ_F_APOLL_MULTISHOT)) { err = -EBADFD; if (!io_file_can_poll(req)) goto fail; if (req->file->f_flags & O_NONBLOCK || req->file->f_mode & FMODE_NOWAIT) { err = -ECANCELED; if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK) goto fail; return; } else { req->flags &= ~(REQ_F_APOLL_MULTISHOT|REQ_F_MULTISHOT); } } if (req->flags & REQ_F_FORCE_ASYNC) { bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && io_file_can_poll(req)) { needs_poll = true; issue_flags |= IO_URING_F_NONBLOCK; } } do { ret = io_issue_sqe(req, issue_flags); if (ret != -EAGAIN) break; /* * If REQ_F_NOWAIT is set, then don't wait or retry with * poll. -EAGAIN is final for that case. */ if (req->flags & REQ_F_NOWAIT) break; /* * We can get EAGAIN for iopolled IO even though we're * forcing a sync submission from here, since we can't * wait for request slots on the block side. */ if (!needs_poll) { if (!(req->ctx->flags & IORING_SETUP_IOPOLL)) break; if (io_wq_worker_stopped()) break; cond_resched(); continue; } if (io_arm_poll_handler(req, issue_flags) == IO_APOLL_OK) return; /* aborted or ready, in either case retry blocking */ needs_poll = false; issue_flags &= ~IO_URING_F_NONBLOCK; } while (1); /* avoid locking problems by failing it from a clean context */ if (ret) io_req_task_queue_fail(req, ret); } inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_rsrc_node *node; struct file *file = NULL; io_ring_submit_lock(ctx, issue_flags); node = io_rsrc_node_lookup(&ctx->file_table.data, fd); if (node) { node->refs++; req->file_node = node; req->flags |= io_slot_flags(node); file = io_slot_file(node); } io_ring_submit_unlock(ctx, issue_flags); return file; } struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); trace_io_uring_file_get(req, fd); /* we don't allow fixed io_uring files */ if (file && io_is_uring_fops(file)) io_req_track_inflight(req); return file; } static int io_req_sqe_copy(struct io_kiocb *req, unsigned int issue_flags) { const struct io_cold_def *def = &io_cold_defs[req->opcode]; if (req->flags & REQ_F_SQE_COPIED) return 0; req->flags |= REQ_F_SQE_COPIED; if (!def->sqe_copy) return 0; if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_INLINE))) return -EFAULT; def->sqe_copy(req); return 0; } static void io_queue_async(struct io_kiocb *req, unsigned int issue_flags, int ret) __must_hold(&req->ctx->uring_lock) { if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { fail: io_req_defer_failed(req, ret); return; } ret = io_req_sqe_copy(req, issue_flags); if (unlikely(ret)) goto fail; switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: io_req_task_queue(req); break; case IO_APOLL_ABORTED: io_queue_iowq(req); break; case IO_APOLL_OK: break; } } static inline void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags) __must_hold(&req->ctx->uring_lock) { unsigned int issue_flags = IO_URING_F_NONBLOCK | IO_URING_F_COMPLETE_DEFER | extra_flags; int ret; ret = io_issue_sqe(req, issue_flags); /* * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ if (unlikely(ret)) io_queue_async(req, issue_flags, ret); } static void io_queue_sqe_fallback(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { if (unlikely(req->flags & REQ_F_FAIL)) { /* * We don't submit, fail them all, for that replace hardlinks * with normal links. Extra REQ_F_LINK is tolerated. */ req->flags &= ~REQ_F_HARDLINK; req->flags |= REQ_F_LINK; io_req_defer_failed(req, req->cqe.res); } else { /* can't fail with IO_URING_F_INLINE */ io_req_sqe_copy(req, IO_URING_F_INLINE); if (unlikely(req->ctx->drain_active)) io_drain_req(req); else io_queue_iowq(req); } } /* * Check SQE restrictions (opcode and flags). * * Returns 'true' if SQE is allowed, 'false' otherwise. */ static inline bool io_check_restriction(struct io_ring_ctx *ctx, struct io_kiocb *req, unsigned int sqe_flags) { if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) return false; if ((sqe_flags & ctx->restrictions.sqe_flags_required) != ctx->restrictions.sqe_flags_required) return false; if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | ctx->restrictions.sqe_flags_required)) return false; return true; } static void io_init_drain(struct io_ring_ctx *ctx) { struct io_kiocb *head = ctx->submit_state.link.head; ctx->drain_active = true; if (head) { /* * If we need to drain a request in the middle of a link, drain * the head request and the next request/link after the current * link. Considering sequential execution of links, * REQ_F_IO_DRAIN will be maintained for every request of our * link. */ head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; ctx->drain_next = true; } } static __cold int io_init_fail_req(struct io_kiocb *req, int err) { /* ensure per-opcode data is cleared if we fail before prep */ memset(&req->cmd.data, 0, sizeof(req->cmd.data)); return err; } static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { const struct io_issue_def *def; unsigned int sqe_flags; int personality; u8 opcode; req->ctx = ctx; req->opcode = opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ sqe_flags = READ_ONCE(sqe->flags); req->flags = (__force io_req_flags_t) sqe_flags; req->cqe.user_data = READ_ONCE(sqe->user_data); req->file = NULL; req->tctx = current->io_uring; req->cancel_seq_set = false; req->async_data = NULL; if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; return io_init_fail_req(req, -EINVAL); } opcode = array_index_nospec(opcode, IORING_OP_LAST); def = &io_issue_defs[opcode]; if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { /* enforce forwards compatibility on users */ if (sqe_flags & ~SQE_VALID_FLAGS) return io_init_fail_req(req, -EINVAL); if (sqe_flags & IOSQE_BUFFER_SELECT) { if (!def->buffer_select) return io_init_fail_req(req, -EOPNOTSUPP); req->buf_index = READ_ONCE(sqe->buf_group); } if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS) ctx->drain_disabled = true; if (sqe_flags & IOSQE_IO_DRAIN) { if (ctx->drain_disabled) return io_init_fail_req(req, -EOPNOTSUPP); io_init_drain(ctx); } } if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) return io_init_fail_req(req, -EACCES); /* knock it to the slow queue path, will be drained there */ if (ctx->drain_active) req->flags |= REQ_F_FORCE_ASYNC; /* if there is no link, we're at "next" request and need to drain */ if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) { ctx->drain_next = false; ctx->drain_active = true; req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC; } } if (!def->ioprio && sqe->ioprio) return io_init_fail_req(req, -EINVAL); if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL)) return io_init_fail_req(req, -EINVAL); if (def->needs_file) { struct io_submit_state *state = &ctx->submit_state; req->cqe.fd = READ_ONCE(sqe->fd); /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. */ if (state->need_plug && def->plug) { state->plug_started = true; state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } } personality = READ_ONCE(sqe->personality); if (personality) { int ret; req->creds = xa_load(&ctx->personalities, personality); if (!req->creds) return io_init_fail_req(req, -EINVAL); get_cred(req->creds); ret = security_uring_override_creds(req->creds); if (ret) { put_cred(req->creds); return io_init_fail_req(req, ret); } req->flags |= REQ_F_CREDS; } return def->prep(req, sqe); } static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe, struct io_kiocb *req, int ret) { struct io_ring_ctx *ctx = req->ctx; struct io_submit_link *link = &ctx->submit_state.link; struct io_kiocb *head = link->head; trace_io_uring_req_failed(sqe, req, ret); /* * Avoid breaking links in the middle as it renders links with SQPOLL * unusable. Instead of failing eagerly, continue assembling the link if * applicable and mark the head with REQ_F_FAIL. The link flushing code * should find the flag and handle the rest. */ req_fail_link_node(req, ret); if (head && !(head->flags & REQ_F_FAIL)) req_fail_link_node(head, -ECANCELED); if (!(req->flags & IO_REQ_LINK_FLAGS)) { if (head) { link->last->link = req; link->head = NULL; req = head; } io_queue_sqe_fallback(req); return ret; } if (head) link->last->link = req; else link->head = req; link->last = req; return 0; } static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { struct io_submit_link *link = &ctx->submit_state.link; int ret; ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) return io_submit_fail_init(sqe, req, ret); trace_io_uring_submit_req(req); /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be * submitted sync once the chain is complete. If none of those * conditions are true (normal request), then just queue it. */ if (unlikely(link->head)) { trace_io_uring_link(req, link->last); io_req_sqe_copy(req, IO_URING_F_INLINE); link->last->link = req; link->last = req; if (req->flags & IO_REQ_LINK_FLAGS) return 0; /* last request of the link, flush it */ req = link->head; link->head = NULL; if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)) goto fallback; } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS | REQ_F_FORCE_ASYNC | REQ_F_FAIL))) { if (req->flags & IO_REQ_LINK_FLAGS) { link->head = req; link->last = req; } else { fallback: io_queue_sqe_fallback(req); } return 0; } io_queue_sqe(req, IO_URING_F_INLINE); return 0; } /* * Batched submission is done, ensure local IO is flushed out. */ static void io_submit_state_end(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; if (unlikely(state->link.head)) io_queue_sqe_fallback(state->link.head); /* flush only after queuing links as they can generate completions */ io_submit_flush_completions(ctx); if (state->plug_started) blk_finish_plug(&state->plug); } /* * Start submission side cache. */ static void io_submit_state_start(struct io_submit_state *state, unsigned int max_ios) { state->plug_started = false; state->need_plug = max_ios > 2; state->submit_nr = max_ios; /* set only head, no need to init link_last in advance */ state->link.head = NULL; } static void io_commit_sqring(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; /* * Ensure any loads from the SQEs are done at this point, * since once we write the new head, the application could * write new data to them. */ smp_store_release(&rings->sq.head, ctx->cached_sq_head); } /* * Fetch an sqe, if one is available. Note this returns a pointer to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later * used, it's important that those reads are done through READ_ONCE() to * prevent a re-load down the line. */ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe) { unsigned mask = ctx->sq_entries - 1; unsigned head = ctx->cached_sq_head++ & mask; if (static_branch_unlikely(&io_key_has_sqarray) && (!(ctx->flags & IORING_SETUP_NO_SQARRAY))) { head = READ_ONCE(ctx->sq_array[head]); if (unlikely(head >= ctx->sq_entries)) { WRITE_ONCE(ctx->rings->sq_dropped, READ_ONCE(ctx->rings->sq_dropped) + 1); return false; } head = array_index_nospec(head, ctx->sq_entries); } /* * The cached sq head (or cq tail) serves two purposes: * * 1) allows us to batch the cost of updating the user visible * head updates. * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ /* double index for 128-byte SQEs, twice as long */ if (ctx->flags & IORING_SETUP_SQE128) head <<= 1; *sqe = &ctx->sq_sqes[head]; return true; } int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) __must_hold(&ctx->uring_lock) { unsigned int entries = io_sqring_entries(ctx); unsigned int left; int ret; if (unlikely(!entries)) return 0; /* make sure SQ entry isn't read before tail */ ret = left = min(nr, entries); io_get_task_refs(left); io_submit_state_start(&ctx->submit_state, left); do { const struct io_uring_sqe *sqe; struct io_kiocb *req; if (unlikely(!io_alloc_req(ctx, &req))) break; if (unlikely(!io_get_sqe(ctx, &sqe))) { io_req_add_to_cache(req, ctx); break; } /* * Continue submitting even for sqe failure if the * ring was setup with IORING_SETUP_SUBMIT_ALL */ if (unlikely(io_submit_sqe(ctx, req, sqe)) && !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) { left--; break; } } while (--left); if (unlikely(left)) { ret -= left; /* try again if it submitted nothing and can't allocate a req */ if (!ret && io_req_cache_empty(ctx)) ret = -EAGAIN; current->io_uring->cached_refs += left; } io_submit_state_end(ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); return ret; } static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, int wake_flags, void *key) { struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); /* * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ if (io_should_wake(iowq) || io_has_work(iowq->ctx)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } int io_run_task_work_sig(struct io_ring_ctx *ctx) { if (io_local_work_pending(ctx)) { __set_current_state(TASK_RUNNING); if (io_run_local_work(ctx, INT_MAX, IO_LOCAL_TW_DEFAULT_MAX) > 0) return 0; } if (io_run_task_work() > 0) return 0; if (task_sigpending(current)) return -EINTR; return 0; } static bool current_pending_io(void) { struct io_uring_task *tctx = current->io_uring; if (!tctx) return false; return percpu_counter_read_positive(&tctx->inflight); } static enum hrtimer_restart io_cqring_timer_wakeup(struct hrtimer *timer) { struct io_wait_queue *iowq = container_of(timer, struct io_wait_queue, t); WRITE_ONCE(iowq->hit_timeout, 1); iowq->min_timeout = 0; wake_up_process(iowq->wq.private); return HRTIMER_NORESTART; } /* * Doing min_timeout portion. If we saw any timeouts, events, or have work, * wake up. If not, and we have a normal timeout, switch to that and keep * sleeping. */ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer) { struct io_wait_queue *iowq = container_of(timer, struct io_wait_queue, t); struct io_ring_ctx *ctx = iowq->ctx; /* no general timeout, or shorter (or equal), we are done */ if (iowq->timeout == KTIME_MAX || ktime_compare(iowq->min_timeout, iowq->timeout) >= 0) goto out_wake; /* work we may need to run, wake function will see if we need to wake */ if (io_has_work(ctx)) goto out_wake; /* got events since we started waiting, min timeout is done */ if (iowq->cq_min_tail != READ_ONCE(ctx->rings->cq.tail)) goto out_wake; /* if we have any events and min timeout expired, we're done */ if (io_cqring_events(ctx)) goto out_wake; /* * If using deferred task_work running and application is waiting on * more than one request, ensure we reset it now where we are switching * to normal sleeps. Any request completion post min_wait should wake * the task and return. */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, 1); smp_mb(); if (!llist_empty(&ctx->work_llist)) goto out_wake; } hrtimer_update_function(&iowq->t, io_cqring_timer_wakeup); hrtimer_set_expires(timer, iowq->timeout); return HRTIMER_RESTART; out_wake: return io_cqring_timer_wakeup(timer); } static int io_cqring_schedule_timeout(struct io_wait_queue *iowq, clockid_t clock_id, ktime_t start_time) { ktime_t timeout; if (iowq->min_timeout) { timeout = ktime_add_ns(iowq->min_timeout, start_time); hrtimer_setup_on_stack(&iowq->t, io_cqring_min_timer_wakeup, clock_id, HRTIMER_MODE_ABS); } else { timeout = iowq->timeout; hrtimer_setup_on_stack(&iowq->t, io_cqring_timer_wakeup, clock_id, HRTIMER_MODE_ABS); } hrtimer_set_expires_range_ns(&iowq->t, timeout, 0); hrtimer_start_expires(&iowq->t, HRTIMER_MODE_ABS); if (!READ_ONCE(iowq->hit_timeout)) schedule(); hrtimer_cancel(&iowq->t); destroy_hrtimer_on_stack(&iowq->t); __set_current_state(TASK_RUNNING); return READ_ONCE(iowq->hit_timeout) ? -ETIME : 0; } struct ext_arg { size_t argsz; struct timespec64 ts; const sigset_t __user *sig; ktime_t min_time; bool ts_set; bool iowait; }; static int __io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct ext_arg *ext_arg, ktime_t start_time) { int ret = 0; /* * Mark us as being in io_wait if we have pending requests, so cpufreq * can take into account that the task is waiting for IO - turns out * to be important for low QD IO. */ if (ext_arg->iowait && current_pending_io()) current->in_iowait = 1; if (iowq->timeout != KTIME_MAX || iowq->min_timeout) ret = io_cqring_schedule_timeout(iowq, ctx->clockid, start_time); else schedule(); current->in_iowait = 0; return ret; } /* If this returns > 0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct ext_arg *ext_arg, ktime_t start_time) { if (unlikely(READ_ONCE(ctx->check_cq))) return 1; if (unlikely(io_local_work_pending(ctx))) return 1; if (unlikely(task_work_pending(current))) return 1; if (unlikely(task_sigpending(current))) return -EINTR; if (unlikely(io_should_wake(iowq))) return 0; return __io_cqring_wait_schedule(ctx, iowq, ext_arg, start_time); } /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. */ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, struct ext_arg *ext_arg) { struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; ktime_t start_time; int ret; min_events = min_t(int, min_events, ctx->cq_entries); if (!io_allowed_run_tw(ctx)) return -EEXIST; if (io_local_work_pending(ctx)) io_run_local_work(ctx, min_events, max(IO_LOCAL_TW_DEFAULT_MAX, min_events)); io_run_task_work(); if (unlikely(test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))) io_cqring_do_overflow_flush(ctx); if (__io_cqring_events_user(ctx) >= min_events) return 0; init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); iowq.ctx = ctx; iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; iowq.cq_min_tail = READ_ONCE(ctx->rings->cq.tail); iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); iowq.hit_timeout = 0; iowq.min_timeout = ext_arg->min_time; iowq.timeout = KTIME_MAX; start_time = io_get_time(ctx); if (ext_arg->ts_set) { iowq.timeout = timespec64_to_ktime(ext_arg->ts); if (!(flags & IORING_ENTER_ABS_TIMER)) iowq.timeout = ktime_add(iowq.timeout, start_time); } if (ext_arg->sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) ret = set_compat_user_sigmask((const compat_sigset_t __user *)ext_arg->sig, ext_arg->argsz); else #endif ret = set_user_sigmask(ext_arg->sig, ext_arg->argsz); if (ret) return ret; } io_napi_busy_loop(ctx, &iowq); trace_io_uring_cqring_wait(ctx, min_events); do { unsigned long check_cq; int nr_wait; /* if min timeout has been hit, don't reset wait count */ if (!iowq.hit_timeout) nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail); else nr_wait = 1; if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, nr_wait); set_current_state(TASK_INTERRUPTIBLE); } else { prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); } ret = io_cqring_wait_schedule(ctx, &iowq, ext_arg, start_time); __set_current_state(TASK_RUNNING); atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT); /* * Run task_work after scheduling and before io_should_wake(). * If we got woken because of task_work being processed, run it * now rather than let the caller do another wait loop. */ if (io_local_work_pending(ctx)) io_run_local_work(ctx, nr_wait, nr_wait); io_run_task_work(); /* * Non-local task_work will be run on exit to userspace, but * if we're using DEFER_TASKRUN, then we could have waited * with a timeout for a number of requests. If the timeout * hits, we could have some requests ready to process. Ensure * this break is _after_ we have run task_work, to avoid * deferring running potentially pending requests until the * next time we wait for events. */ if (ret < 0) break; check_cq = READ_ONCE(ctx->check_cq); if (unlikely(check_cq)) { /* let the caller flush overflows, retry */ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) io_cqring_do_overflow_flush(ctx); if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) { ret = -EBADR; break; } } if (io_should_wake(&iowq)) { ret = 0; break; } cond_resched(); } while (1); if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) finish_wait(&ctx->cq_wait, &iowq.wq); restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } static void io_rings_free(struct io_ring_ctx *ctx) { io_free_region(ctx, &ctx->sq_region); io_free_region(ctx, &ctx->ring_region); ctx->rings = NULL; ctx->sq_sqes = NULL; } unsigned long rings_size(unsigned int flags, unsigned int sq_entries, unsigned int cq_entries, size_t *sq_offset) { struct io_rings *rings; size_t off, sq_array_size; off = struct_size(rings, cqes, cq_entries); if (off == SIZE_MAX) return SIZE_MAX; if (flags & IORING_SETUP_CQE32) { if (check_shl_overflow(off, 1, &off)) return SIZE_MAX; } if (flags & IORING_SETUP_CQE_MIXED) { if (cq_entries < 2) return SIZE_MAX; } #ifdef CONFIG_SMP off = ALIGN(off, SMP_CACHE_BYTES); if (off == 0) return SIZE_MAX; #endif if (flags & IORING_SETUP_NO_SQARRAY) { *sq_offset = SIZE_MAX; return off; } *sq_offset = off; sq_array_size = array_size(sizeof(u32), sq_entries); if (sq_array_size == SIZE_MAX) return SIZE_MAX; if (check_add_overflow(off, sq_array_size, &off)) return SIZE_MAX; return off; } static __cold void __io_req_caches_free(struct io_ring_ctx *ctx) { struct io_kiocb *req; int nr = 0; while (!io_req_cache_empty(ctx)) { req = io_extract_req(ctx); io_poison_req(req); kmem_cache_free(req_cachep, req); nr++; } if (nr) { ctx->nr_req_allocated -= nr; percpu_ref_put_many(&ctx->refs, nr); } } static __cold void io_req_caches_free(struct io_ring_ctx *ctx) { guard(mutex)(&ctx->uring_lock); __io_req_caches_free(ctx); } static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); mutex_lock(&ctx->uring_lock); io_sqe_buffers_unregister(ctx); io_sqe_files_unregister(ctx); io_unregister_zcrx_ifqs(ctx); io_cqring_overflow_kill(ctx); io_eventfd_unregister(ctx); io_free_alloc_caches(ctx); io_destroy_buffers(ctx); io_free_region(ctx, &ctx->param_region); mutex_unlock(&ctx->uring_lock); if (ctx->sq_creds) put_cred(ctx->sq_creds); if (ctx->submitter_task) put_task_struct(ctx->submitter_task); WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); if (ctx->mm_account) { mmdrop(ctx->mm_account); ctx->mm_account = NULL; } io_rings_free(ctx); if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) static_branch_dec(&io_key_has_sqarray); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); io_req_caches_free(ctx); WARN_ON_ONCE(ctx->nr_req_allocated); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); io_napi_free(ctx); kvfree(ctx->cancel_table.hbs); xa_destroy(&ctx->io_bl_xa); kfree(ctx); } static __cold void io_activate_pollwq_cb(struct callback_head *cb) { struct io_ring_ctx *ctx = container_of(cb, struct io_ring_ctx, poll_wq_task_work); mutex_lock(&ctx->uring_lock); ctx->poll_activated = true; mutex_unlock(&ctx->uring_lock); /* * Wake ups for some events between start of polling and activation * might've been lost due to loose synchronisation. */ wake_up_all(&ctx->poll_wq); percpu_ref_put(&ctx->refs); } __cold void io_activate_pollwq(struct io_ring_ctx *ctx) { spin_lock(&ctx->completion_lock); /* already activated or in progress */ if (ctx->poll_activated || ctx->poll_wq_task_work.func) goto out; if (WARN_ON_ONCE(!ctx->task_complete)) goto out; if (!ctx->submitter_task) goto out; /* * with ->submitter_task only the submitter task completes requests, we * only need to sync with it, which is done by injecting a tw */ init_task_work(&ctx->poll_wq_task_work, io_activate_pollwq_cb); percpu_ref_get(&ctx->refs); if (task_work_add(ctx->submitter_task, &ctx->poll_wq_task_work, TWA_SIGNAL)) percpu_ref_put(&ctx->refs); out: spin_unlock(&ctx->completion_lock); } static __poll_t io_uring_poll(struct file *file, poll_table *wait) { struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; if (unlikely(!ctx->poll_activated)) io_activate_pollwq(ctx); /* * provides mb() which pairs with barrier from wq_has_sleeper * call in io_commit_cqring */ poll_wait(file, &ctx->poll_wq, wait); if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Don't flush cqring overflow list here, just do a simple check. * Otherwise there could possible be ABBA deadlock: * CPU0 CPU1 * ---- ---- * lock(&ctx->uring_lock); * lock(&ep->mtx); * lock(&ctx->uring_lock); * lock(&ep->mtx); * * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushes them to do the flush. */ if (__io_cqring_events_user(ctx) || io_has_work(ctx)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } struct io_tctx_exit { struct callback_head task_work; struct completion completion; struct io_ring_ctx *ctx; }; static __cold void io_tctx_exit_cb(struct callback_head *cb) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_exit *work; work = container_of(cb, struct io_tctx_exit, task_work); /* * When @in_cancel, we're in cancellation and it's racy to remove the * node. It'll be removed by the end of cancellation, just ignore it. * tctx can be NULL if the queueing of this task_work raced with * work cancelation off the exec path. */ if (tctx && !atomic_read(&tctx->in_cancel)) io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); return req->ctx == data; } static __cold void io_ring_exit_work(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); unsigned long timeout = jiffies + HZ * 60 * 5; unsigned long interval = HZ / 20; struct io_tctx_exit exit; struct io_tctx_node *node; int ret; /* * If we're doing polled IO and end up having requests being * submitted async (out-of-line), then completions can come in while * we're waiting for refs to drop. We need to reap these manually, * as nobody else will be looking for them. */ do { if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) { mutex_lock(&ctx->uring_lock); io_cqring_overflow_kill(ctx); mutex_unlock(&ctx->uring_lock); } if (!xa_empty(&ctx->zcrx_ctxs)) { mutex_lock(&ctx->uring_lock); io_shutdown_zcrx_ifqs(ctx); mutex_unlock(&ctx->uring_lock); } if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) io_move_task_work_from_local(ctx); /* The SQPOLL thread never reaches this path */ while (io_uring_try_cancel_requests(ctx, NULL, true, false)) cond_resched(); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; struct task_struct *tsk; io_sq_thread_park(sqd); tsk = sqpoll_task_locked(sqd); if (tsk && tsk->io_uring && tsk->io_uring->io_wq) io_wq_cancel_cb(tsk->io_uring->io_wq, io_cancel_ctx_cb, ctx, true); io_sq_thread_unpark(sqd); } io_req_caches_free(ctx); if (WARN_ON_ONCE(time_after(jiffies, timeout))) { /* there is little hope left, don't run it too often */ interval = HZ * 60; } /* * This is really an uninterruptible wait, as it has to be * complete. But it's also run from a kworker, which doesn't * take signals, so it's fine to make it interruptible. This * avoids scenarios where we knowingly can wait much longer * on completions, for example if someone does a SIGSTOP on * a task that needs to finish task_work to make this loop * complete. That's a synthetic situation that should not * cause a stuck task backtrace, and hence a potential panic * on stuck tasks if that is enabled. */ } while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval)); init_completion(&exit.completion); init_task_work(&exit.task_work, io_tctx_exit_cb); exit.ctx = ctx; mutex_lock(&ctx->uring_lock); while (!list_empty(&ctx->tctx_list)) { WARN_ON_ONCE(time_after(jiffies, timeout)); node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, ctx_node); /* don't spin on a single task if cancellation failed */ list_rotate_left(&ctx->tctx_list); ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); if (WARN_ON_ONCE(ret)) continue; mutex_unlock(&ctx->uring_lock); /* * See comment above for * wait_for_completion_interruptible_timeout() on why this * wait is marked as interruptible. */ wait_for_completion_interruptible(&exit.completion); mutex_lock(&ctx->uring_lock); } mutex_unlock(&ctx->uring_lock); spin_lock(&ctx->completion_lock); spin_unlock(&ctx->completion_lock); /* pairs with RCU read section in io_req_local_work_add() */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) synchronize_rcu(); io_ring_ctx_free(ctx); } static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; struct creds *creds; mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); xa_for_each(&ctx->personalities, index, creds) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); flush_delayed_work(&ctx->fallback_work); INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* * Use system_dfl_wq to avoid spawning tons of event kworkers * if we're exiting a ton of rings at the same time. It just adds * noise and overhead, there's no discernable change in runtime * over using system_percpu_wq. */ queue_work(iou_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) { struct io_ring_ctx *ctx = file->private_data; file->private_data = NULL; io_ring_ctx_wait_and_kill(ctx); return 0; } struct io_task_cancel { struct io_uring_task *tctx; bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; return io_match_task_safe(req, cancel->tctx, cancel->all); } static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all) { struct io_defer_entry *de; LIST_HEAD(list); list_for_each_entry_reverse(de, &ctx->defer_list, list) { if (io_match_task_safe(de->req, tctx, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } if (list_empty(&list)) return false; while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); list_del_init(&de->list); ctx->nr_drained -= io_linked_nr(de->req); io_req_task_queue_fail(de->req, -ECANCELED); kfree(de); } return true; } static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { struct io_tctx_node *node; enum io_wq_cancel cret; bool ret = false; mutex_lock(&ctx->uring_lock); list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; /* * io_wq will stay alive while we hold uring_lock, because it's * killed after ctx nodes, which requires to take the lock. */ if (!tctx || !tctx->io_wq) continue; cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } mutex_unlock(&ctx->uring_lock); return ret; } static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all, bool is_sqpoll_thread) { struct io_task_cancel cancel = { .tctx = tctx, .all = cancel_all, }; enum io_wq_cancel cret; bool ret = false; /* set it so io_req_local_work_add() would wake us up */ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { atomic_set(&ctx->cq_wait_nr, 1); smp_mb( |