| 3 3 3 3 3 3 3 3 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 36 2 17 19 20 18 17 1 18 19 45 45 45 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Helpers for formatting and printing strings * * Copyright 31 August 2008 James Bottomley * Copyright (C) 2013, Intel Corporation */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/limits.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/string_helpers.h> #include <kunit/test.h> #include <kunit/test-bug.h> /** * string_get_size - get the size in the specified units * @size: The size to be converted in blocks * @blk_size: Size of the block (use 1 for size in bytes) * @units: Units to use (powers of 1000 or 1024), whether to include space separator * @buf: buffer to format to * @len: length of buffer * * This function returns a string formatted to 3 significant figures * giving the size in the required units. @buf should have room for * at least 9 bytes and will always be zero terminated. * * Return value: number of characters of output that would have been written * (which may be greater than len, if output was truncated). */ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units, char *buf, int len) { enum string_size_units units_base = units & STRING_UNITS_MASK; static const char *const units_10[] = { "", "k", "M", "G", "T", "P", "E", "Z", "Y", }; static const char *const units_2[] = { "", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi", }; static const char *const *const units_str[] = { [STRING_UNITS_10] = units_10, [STRING_UNITS_2] = units_2, }; static const unsigned int divisor[] = { [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; static const unsigned int rounding[] = { 500, 50, 5 }; int i = 0, j; u32 remainder = 0, sf_cap; char tmp[8]; const char *unit; tmp[0] = '\0'; if (blk_size == 0) size = 0; if (size == 0) goto out; /* This is Napier's algorithm. Reduce the original block size to * * coefficient * divisor[units_base]^i * * we do the reduction so both coefficients are just under 32 bits so * that multiplying them together won't overflow 64 bits and we keep * as much precision as possible in the numbers. * * Note: it's safe to throw away the remainders here because all the * precision is in the coefficients. */ while (blk_size >> 32) { do_div(blk_size, divisor[units_base]); i++; } while (size >> 32) { do_div(size, divisor[units_base]); i++; } /* now perform the actual multiplication keeping i as the sum of the * two logarithms */ size *= blk_size; /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units_base]) { remainder = do_div(size, divisor[units_base]); i++; } /* work out in j how many digits of precision we need from the * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; if (units_base == STRING_UNITS_2) { /* express the remainder as a decimal. It's currently the * numerator of a fraction whose denominator is * divisor[units_base], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; remainder >>= 10; } /* add a 5 to the digit below what will be printed to ensure * an arithmetical round up and carry it through to size */ remainder += rounding[j]; if (remainder >= 1000) { remainder -= 1000; size += 1; } if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } out: if (i >= ARRAY_SIZE(units_2)) unit = "UNK"; else unit = units_str[units_base][i]; return snprintf(buf, len, "%u%s%s%s%s", (u32)size, tmp, (units & STRING_UNITS_NO_SPACE) ? "" : " ", unit, (units & STRING_UNITS_NO_BYTES) ? "" : "B"); } EXPORT_SYMBOL(string_get_size); /** * parse_int_array_user - Split string into a sequence of integers * @from: The user space buffer to read from * @count: The maximum number of bytes to read * @array: Returned pointer to sequence of integers * * On success @array is allocated and initialized with a sequence of * integers extracted from the @from plus an additional element that * begins the sequence and specifies the integers count. * * Caller takes responsibility for freeing @array when it is no longer * needed. */ int parse_int_array_user(const char __user *from, size_t count, int **array) { int *ints, nints; char *buf; int ret = 0; buf = memdup_user_nul(from, count); if (IS_ERR(buf)) return PTR_ERR(buf); get_options(buf, 0, &nints); if (!nints) { ret = -ENOENT; goto free_buf; } ints = kcalloc(nints + 1, sizeof(*ints), GFP_KERNEL); if (!ints) { ret = -ENOMEM; goto free_buf; } get_options(buf, nints + 1, ints); *array = ints; free_buf: kfree(buf); return ret; } EXPORT_SYMBOL(parse_int_array_user); static bool unescape_space(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case 'n': *p = '\n'; break; case 'r': *p = '\r'; break; case 't': *p = '\t'; break; case 'v': *p = '\v'; break; case 'f': *p = '\f'; break; default: return false; } *dst += 1; *src += 1; return true; } static bool unescape_octal(char **src, char **dst) { char *p = *dst, *q = *src; u8 num; if (isodigit(*q) == 0) return false; num = (*q++) & 7; while (num < 32 && isodigit(*q) && (q - *src < 3)) { num <<= 3; num += (*q++) & 7; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_hex(char **src, char **dst) { char *p = *dst, *q = *src; int digit; u8 num; if (*q++ != 'x') return false; num = digit = hex_to_bin(*q++); if (digit < 0) return false; digit = hex_to_bin(*q); if (digit >= 0) { q++; num = (num << 4) | digit; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_special(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case '\"': *p = '\"'; break; case '\\': *p = '\\'; break; case 'a': *p = '\a'; break; case 'e': *p = '\e'; break; default: return false; } *dst += 1; *src += 1; return true; } /** * string_unescape - unquote characters in the given string * @src: source buffer (escaped) * @dst: destination buffer (unescaped) * @size: size of the destination buffer (0 to unlimit) * @flags: combination of the flags. * * Description: * The function unquotes characters in the given string. * * Because the size of the output will be the same as or less than the size of * the input, the transformation may be performed in place. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will always be NULL-terminated. Source string must be * NULL-terminated as well. The supported flags are:: * * UNESCAPE_SPACE: * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * UNESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (1 to 3 digits) * UNESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) * UNESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * UNESCAPE_ANY: * all previous together * * Return: * The amount of the characters processed to the destination buffer excluding * trailing '\0' is returned. */ int string_unescape(char *src, char *dst, size_t size, unsigned int flags) { char *out = dst; while (*src && --size) { if (src[0] == '\\' && src[1] != '\0' && size > 1) { src++; size--; if (flags & UNESCAPE_SPACE && unescape_space(&src, &out)) continue; if (flags & UNESCAPE_OCTAL && unescape_octal(&src, &out)) continue; if (flags & UNESCAPE_HEX && unescape_hex(&src, &out)) continue; if (flags & UNESCAPE_SPECIAL && unescape_special(&src, &out)) continue; *out++ = '\\'; } *out++ = *src++; } *out = '\0'; return out - dst; } EXPORT_SYMBOL(string_unescape); static bool escape_passthrough(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = c; *dst = out + 1; return true; } static bool escape_space(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\n': to = 'n'; break; case '\r': to = 'r'; break; case '\t': to = 't'; break; case '\v': to = 'v'; break; case '\f': to = 'f'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_special(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\\': to = '\\'; break; case '\a': to = 'a'; break; case '\e': to = 'e'; break; case '"': to = '"'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_null(unsigned char c, char **dst, char *end) { char *out = *dst; if (c) return false; if (out < end) *out = '\\'; ++out; if (out < end) *out = '0'; ++out; *dst = out; return true; } static bool escape_octal(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = ((c >> 6) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 3) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 0) & 0x07) + '0'; ++out; *dst = out; return true; } static bool escape_hex(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = 'x'; ++out; if (out < end) *out = hex_asc_hi(c); ++out; if (out < end) *out = hex_asc_lo(c); ++out; *dst = out; return true; } /** * string_escape_mem - quote characters in the given memory buffer * @src: source buffer (unescaped) * @isz: source buffer size * @dst: destination buffer (escaped) * @osz: destination buffer size * @flags: combination of the flags * @only: NULL-terminated string containing characters used to limit * the selected escape class. If characters are included in @only * that would not normally be escaped by the classes selected * in @flags, they will be copied to @dst unescaped. * * Description: * The process of escaping byte buffer includes several parts. They are applied * in the following sequence. * * 1. The character is not matched to the one from @only string and thus * must go as-is to the output. * 2. The character is matched to the printable and ASCII classes, if asked, * and in case of match it passes through to the output. * 3. The character is matched to the printable or ASCII class, if asked, * and in case of match it passes through to the output. * 4. The character is checked if it falls into the class given by @flags. * %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any * character. Note that they actually can't go together, otherwise * %ESCAPE_HEX will be ignored. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will not be NULL-terminated, thus caller have to append * it if needs. The supported flags are:: * * %ESCAPE_SPACE: (special white space, not space itself) * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * %ESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * %ESCAPE_NULL: * '\0' - null * %ESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (3 digits) * %ESCAPE_ANY: * all previous together * %ESCAPE_NP: * escape only non-printable characters, checked by isprint() * %ESCAPE_ANY_NP: * all previous together * %ESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (2 digits) * %ESCAPE_NA: * escape only non-ascii characters, checked by isascii() * %ESCAPE_NAP: * escape only non-printable or non-ascii characters * %ESCAPE_APPEND: * append characters from @only to be escaped by the given classes * * %ESCAPE_APPEND would help to pass additional characters to the escaped, when * one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided. * * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the * higher priority than the rest of the flags (%ESCAPE_NAP is the highest). * It doesn't make much sense to use either of them without %ESCAPE_OCTAL * or %ESCAPE_HEX, because they cover most of the other character classes. * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to * the above. * * Return: * The total size of the escaped output that would be generated for * the given input and flags. To check whether the output was * truncated, compare the return value to osz. There is room left in * dst for a '\0' terminator if and only if ret < osz. */ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only) { char *p = dst; char *end = p + osz; bool is_dict = only && *only; bool is_append = flags & ESCAPE_APPEND; while (isz--) { unsigned char c = *src++; bool in_dict = is_dict && strchr(only, c); /* * Apply rules in the following sequence: * - the @only string is supplied and does not contain a * character under question * - the character is printable and ASCII, when @flags has * %ESCAPE_NAP bit set * - the character is printable, when @flags has * %ESCAPE_NP bit set * - the character is ASCII, when @flags has * %ESCAPE_NA bit set * - the character doesn't fall into a class of symbols * defined by given @flags * In these cases we just pass through a character to the * output buffer. * * When %ESCAPE_APPEND is passed, the characters from @only * have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and * %ESCAPE_NA cases. */ if (!(is_append || in_dict) && is_dict && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && isprint(c) && flags & ESCAPE_NAP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isprint(c) && flags & ESCAPE_NP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && flags & ESCAPE_NA && escape_passthrough(c, &p, end)) continue; if (flags & ESCAPE_SPACE && escape_space(c, &p, end)) continue; if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end)) continue; if (flags & ESCAPE_NULL && escape_null(c, &p, end)) continue; /* ESCAPE_OCTAL and ESCAPE_HEX always go last */ if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end)) continue; if (flags & ESCAPE_HEX && escape_hex(c, &p, end)) continue; escape_passthrough(c, &p, end); } return p - dst; } EXPORT_SYMBOL(string_escape_mem); /* * Return an allocated string that has been escaped of special characters * and double quotes, making it safe to log in quotes. */ char *kstrdup_quotable(const char *src, gfp_t gfp) { size_t slen, dlen; char *dst; const int flags = ESCAPE_HEX; const char esc[] = "\f\n\r\t\v\a\e\\\""; if (!src) return NULL; slen = strlen(src); dlen = string_escape_mem(src, slen, NULL, 0, flags, esc); dst = kmalloc(dlen + 1, gfp); if (!dst) return NULL; WARN_ON(string_escape_mem(src, slen, dst, dlen, flags, esc) != dlen); dst[dlen] = '\0'; return dst; } EXPORT_SYMBOL_GPL(kstrdup_quotable); /* * Returns allocated NULL-terminated string containing process * command line, with inter-argument NULLs replaced with spaces, * and other special characters escaped. */ char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp) { char *buffer, *quoted; int i, res; buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buffer) return NULL; res = get_cmdline(task, buffer, PAGE_SIZE - 1); buffer[res] = '\0'; /* Collapse trailing NULLs, leave res pointing to last non-NULL. */ while (--res >= 0 && buffer[res] == '\0') ; /* Replace inter-argument NULLs. */ for (i = 0; i <= res; i++) if (buffer[i] == '\0') buffer[i] = ' '; /* Make sure result is printable. */ quoted = kstrdup_quotable(buffer, gfp); kfree(buffer); return quoted; } EXPORT_SYMBOL_GPL(kstrdup_quotable_cmdline); /* * Returns allocated NULL-terminated string containing pathname, * with special characters escaped, able to be safely logged. If * there is an error, the leading character will be "<". */ char *kstrdup_quotable_file(struct file *file, gfp_t gfp) { char *temp, *pathname; if (!file) return kstrdup("<unknown>", gfp); /* We add 11 spaces for ' (deleted)' to be appended */ temp = kmalloc(PATH_MAX + 11, GFP_KERNEL); if (!temp) return kstrdup("<no_memory>", gfp); pathname = file_path(file, temp, PATH_MAX + 11); if (IS_ERR(pathname)) pathname = kstrdup("<too_long>", gfp); else pathname = kstrdup_quotable(pathname, gfp); kfree(temp); return pathname; } EXPORT_SYMBOL_GPL(kstrdup_quotable_file); /* * Returns duplicate string in which the @old characters are replaced by @new. */ char *kstrdup_and_replace(const char *src, char old, char new, gfp_t gfp) { char *dst; dst = kstrdup(src, gfp); if (!dst) return NULL; return strreplace(dst, old, new); } EXPORT_SYMBOL_GPL(kstrdup_and_replace); /** * kasprintf_strarray - allocate and fill array of sequential strings * @gfp: flags for the slab allocator * @prefix: prefix to be used * @n: amount of lines to be allocated and filled * * Allocates and fills @n strings using pattern "%s-%zu", where prefix * is provided by caller. The caller is responsible to free them with * kfree_strarray() after use. * * Returns array of strings or NULL when memory can't be allocated. */ char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n) { char **names; size_t i; names = kcalloc(n + 1, sizeof(char *), gfp); if (!names) return NULL; for (i = 0; i < n; i++) { names[i] = kasprintf(gfp, "%s-%zu", prefix, i); if (!names[i]) { kfree_strarray(names, i); return NULL; } } return names; } EXPORT_SYMBOL_GPL(kasprintf_strarray); /** * kfree_strarray - free a number of dynamically allocated strings contained * in an array and the array itself * * @array: Dynamically allocated array of strings to free. * @n: Number of strings (starting from the beginning of the array) to free. * * Passing a non-NULL @array and @n == 0 as well as NULL @array are valid * use-cases. If @array is NULL, the function does nothing. */ void kfree_strarray(char **array, size_t n) { unsigned int i; if (!array) return; for (i = 0; i < n; i++) kfree(array[i]); kfree(array); } EXPORT_SYMBOL_GPL(kfree_strarray); struct strarray { char **array; size_t n; }; static void devm_kfree_strarray(struct device *dev, void *res) { struct strarray *array = res; kfree_strarray(array->array, array->n); } char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n) { struct strarray *ptr; ptr = devres_alloc(devm_kfree_strarray, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); ptr->array = kasprintf_strarray(GFP_KERNEL, prefix, n); if (!ptr->array) { devres_free(ptr); return ERR_PTR(-ENOMEM); } ptr->n = n; devres_add(dev, ptr); return ptr->array; } EXPORT_SYMBOL_GPL(devm_kasprintf_strarray); /** * skip_spaces - Removes leading whitespace from @str. * @str: The string to be stripped. * * Returns a pointer to the first non-whitespace character in @str. */ char *skip_spaces(const char *str) { while (isspace(*str)) ++str; return (char *)str; } EXPORT_SYMBOL(skip_spaces); /** * strim - Removes leading and trailing whitespace from @s. * @s: The string to be stripped. * * Note that the first trailing whitespace is replaced with a %NUL-terminator * in the given string @s. Returns a pointer to the first non-whitespace * character in @s. */ char *strim(char *s) { size_t size; char *end; size = strlen(s); if (!size) return s; end = s + size - 1; while (end >= s && isspace(*end)) end--; *(end + 1) = '\0'; return skip_spaces(s); } EXPORT_SYMBOL(strim); /** * sysfs_streq - return true if strings are equal, modulo trailing newline * @s1: one string * @s2: another string * * This routine returns true iff two strings are equal, treating both * NUL and newline-then-NUL as equivalent string terminations. It's * geared for use with sysfs input strings, which generally terminate * with newlines but are compared against values without newlines. */ bool sysfs_streq(const char *s1, const char *s2) { while (*s1 && *s1 == *s2) { s1++; s2++; } if (*s1 == *s2) return true; if (!*s1 && *s2 == '\n' && !s2[1]) return true; if (*s1 == '\n' && !s1[1] && !*s2) return true; return false; } EXPORT_SYMBOL(sysfs_streq); /** * match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @string: string to match with * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. * * Return: * index of a @string in the @array if matches, or %-EINVAL otherwise. */ int match_string(const char * const *array, size_t n, const char *string) { int index; const char *item; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (!strcmp(item, string)) return index; } return -EINVAL; } EXPORT_SYMBOL(match_string); /** * __sysfs_match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @str: string to match with * * Returns index of @str in the @array or -EINVAL, just like match_string(). * Uses sysfs_streq instead of strcmp for matching. * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. */ int __sysfs_match_string(const char * const *array, size_t n, const char *str) { const char *item; int index; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (sysfs_streq(item, str)) return index; } return -EINVAL; } EXPORT_SYMBOL(__sysfs_match_string); /** * strreplace - Replace all occurrences of character in string. * @str: The string to operate on. * @old: The character being replaced. * @new: The character @old is replaced with. * * Replaces the each @old character with a @new one in the given string @str. * * Return: pointer to the string @str itself. */ char *strreplace(char *str, char old, char new) { char *s = str; for (; *s; ++s) if (*s == old) *s = new; return str; } EXPORT_SYMBOL(strreplace); /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else { memcpy(dest, src, dest_len); } } EXPORT_SYMBOL(memcpy_and_pad); #ifdef CONFIG_FORTIFY_SOURCE /* These are placeholders for fortify compile-time warnings. */ void __read_overflow2_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__read_overflow2_field); void __write_overflow_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__write_overflow_field); static const char * const fortify_func_name[] = { #define MAKE_FORTIFY_FUNC_NAME(func) [MAKE_FORTIFY_FUNC(func)] = #func EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC_NAME) #undef MAKE_FORTIFY_FUNC_NAME }; void __fortify_report(const u8 reason, const size_t avail, const size_t size) { const u8 func = FORTIFY_REASON_FUNC(reason); const bool write = FORTIFY_REASON_DIR(reason); const char *name; name = fortify_func_name[umin(func, FORTIFY_FUNC_UNKNOWN)]; WARN(1, "%s: detected buffer overflow: %zu byte %s of buffer size %zu\n", name, size, str_read_write(!write), avail); } EXPORT_SYMBOL(__fortify_report); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) { __fortify_report(reason, avail, size); BUG(); } EXPORT_SYMBOL(__fortify_panic); #endif /* CONFIG_FORTIFY_SOURCE */ |
| 145 145 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 1 1 1 1 1 2 2 2 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM virtual interface * * Copyright (C) 2018 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_link.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/gso.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/dst_metadata.h> #include <net/netns/generic.h> #include <linux/etherdevice.h> static int xfrmi_dev_init(struct net_device *dev); static void xfrmi_dev_setup(struct net_device *dev); static struct rtnl_link_ops xfrmi_link_ops __read_mostly; static unsigned int xfrmi_net_id __read_mostly; static const struct net_device_ops xfrmi_netdev_ops; #define XFRMI_HASH_BITS 8 #define XFRMI_HASH_SIZE BIT(XFRMI_HASH_BITS) struct xfrmi_net { /* lists for storing interfaces in use */ struct xfrm_if __rcu *xfrmi[XFRMI_HASH_SIZE]; struct xfrm_if __rcu *collect_md_xfrmi; }; static const struct nla_policy xfrm_lwt_policy[LWT_XFRM_MAX + 1] = { [LWT_XFRM_IF_ID] = NLA_POLICY_MIN(NLA_U32, 1), [LWT_XFRM_LINK] = NLA_POLICY_MIN(NLA_U32, 1), }; static void xfrmi_destroy_state(struct lwtunnel_state *lwt) { } static int xfrmi_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[LWT_XFRM_MAX + 1]; struct lwtunnel_state *new_state; struct xfrm_md_info *info; int ret; ret = nla_parse_nested(tb, LWT_XFRM_MAX, nla, xfrm_lwt_policy, extack); if (ret < 0) return ret; if (!tb[LWT_XFRM_IF_ID]) { NL_SET_ERR_MSG(extack, "if_id must be set"); return -EINVAL; } new_state = lwtunnel_state_alloc(sizeof(*info)); if (!new_state) { NL_SET_ERR_MSG(extack, "failed to create encap info"); return -ENOMEM; } new_state->type = LWTUNNEL_ENCAP_XFRM; info = lwt_xfrm_info(new_state); info->if_id = nla_get_u32(tb[LWT_XFRM_IF_ID]); if (tb[LWT_XFRM_LINK]) info->link = nla_get_u32(tb[LWT_XFRM_LINK]); *ts = new_state; return 0; } static int xfrmi_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwt) { struct xfrm_md_info *info = lwt_xfrm_info(lwt); if (nla_put_u32(skb, LWT_XFRM_IF_ID, info->if_id) || (info->link && nla_put_u32(skb, LWT_XFRM_LINK, info->link))) return -EMSGSIZE; return 0; } static int xfrmi_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size(sizeof(u32)) + /* LWT_XFRM_IF_ID */ nla_total_size(sizeof(u32)); /* LWT_XFRM_LINK */ } static int xfrmi_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { struct xfrm_md_info *a_info = lwt_xfrm_info(a); struct xfrm_md_info *b_info = lwt_xfrm_info(b); return memcmp(a_info, b_info, sizeof(*a_info)); } static const struct lwtunnel_encap_ops xfrmi_encap_ops = { .build_state = xfrmi_build_state, .destroy_state = xfrmi_destroy_state, .fill_encap = xfrmi_fill_encap_info, .get_encap_size = xfrmi_encap_nlsize, .cmp_encap = xfrmi_encap_cmp, .owner = THIS_MODULE, }; #define for_each_xfrmi_rcu(start, xi) \ for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) static u32 xfrmi_hash(u32 if_id) { return hash_32(if_id, XFRMI_HASH_BITS); } static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if *xi; for_each_xfrmi_rcu(xfrmn->xfrmi[xfrmi_hash(x->if_id)], xi) { if (x->if_id == xi->p.if_id && (xi->dev->flags & IFF_UP)) return xi; } xi = rcu_dereference(xfrmn->collect_md_xfrmi); if (xi && (xi->dev->flags & IFF_UP)) return xi; return NULL; } static bool xfrmi_decode_session(struct sk_buff *skb, unsigned short family, struct xfrm_if_decode_session_result *res) { struct net_device *dev; struct xfrm_if *xi; int ifindex = 0; if (!secpath_exists(skb) || !skb->dev) return false; switch (family) { case AF_INET6: ifindex = inet6_sdif(skb); break; case AF_INET: ifindex = inet_sdif(skb); break; } if (ifindex) { struct net *net = xs_net(xfrm_input_state(skb)); dev = dev_get_by_index_rcu(net, ifindex); } else { dev = skb->dev; } if (!dev || !(dev->flags & IFF_UP)) return false; if (dev->netdev_ops != &xfrmi_netdev_ops) return false; xi = netdev_priv(dev); res->net = xi->net; if (xi->p.collect_md) res->if_id = xfrm_input_state(skb)->if_id; else res->if_id = xi->p.if_id; return true; } static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); rcu_assign_pointer(*xip, xi); } static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip; struct xfrm_if *iter; for (xip = &xfrmn->xfrmi[xfrmi_hash(xi->p.if_id)]; (iter = rtnl_dereference(*xip)) != NULL; xip = &iter->next) { if (xi == iter) { rcu_assign_pointer(*xip, xi->next); break; } } } static void xfrmi_dev_free(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); } static int xfrmi_create(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = dev_net(dev); struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; dev->rtnl_link_ops = &xfrmi_link_ops; err = register_netdevice(dev); if (err < 0) goto out; if (xi->p.collect_md) rcu_assign_pointer(xfrmn->collect_md_xfrmi, xi); else xfrmi_link(xfrmn, xi); return 0; out: return err; } static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p) { struct xfrm_if __rcu **xip; struct xfrm_if *xi; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); for (xip = &xfrmn->xfrmi[xfrmi_hash(p->if_id)]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) if (xi->p.if_id == p->if_id) return xi; return NULL; } static void xfrmi_dev_uninit(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); if (xi->p.collect_md) RCU_INIT_POINTER(xfrmn->collect_md_xfrmi, NULL); else xfrmi_unlink(xfrmn, xi); } static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) { skb_clear_tstamp(skb); skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); nf_reset_ct(skb); nf_reset_trace(skb); if (!xnet) return; ipvs_reset(skb); secpath_reset(skb); skb_orphan(skb); skb->mark = 0; } static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type, unsigned short family) { struct sec_path *sp; sp = skb_sec_path(skb); if (sp && (sp->len || sp->olen) && !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) goto discard; XFRM_SPI_SKB_CB(skb)->family = family; if (family == AF_INET) { XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; } else { XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; } return xfrm_input(skb, nexthdr, spi, encap_type); discard: kfree_skb(skb); return 0; } static int xfrmi4_rcv(struct sk_buff *skb) { return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); } static int xfrmi6_rcv(struct sk_buff *skb) { return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], 0, 0, AF_INET6); } static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); } static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); } static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; struct net_device *dev; struct xfrm_state *x; struct xfrm_if *xi; bool xnet; int link; if (err && !secpath_exists(skb)) return 0; x = xfrm_input_state(skb); xi = xfrmi_lookup(xs_net(x), x); if (!xi) return 1; link = skb->dev->ifindex; dev = xi->dev; skb->dev = dev; if (err) { DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_dropped); return 0; } xnet = !net_eq(xi->net, dev_net(skb->dev)); if (xnet) { inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, inner_mode->family)) return -EPERM; } xfrmi_scrub_packet(skb, xnet); if (xi->p.collect_md) { struct metadata_dst *md_dst; md_dst = metadata_dst_alloc(0, METADATA_XFRM, GFP_ATOMIC); if (!md_dst) return -ENOMEM; md_dst->u.xfrm_info.if_id = x->if_id; md_dst->u.xfrm_info.link = link; skb_dst_set(skb, (struct dst_entry *)md_dst); } dev_sw_netstats_rx_add(dev, skb->len); return 0; } static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; struct xfrm_state *x; int err = -1; u32 if_id; int mtu; if (xi->p.collect_md) { struct xfrm_md_info *md_info = skb_xfrm_md_info(skb); if (unlikely(!md_info)) return -EINVAL; if_id = md_info->if_id; fl->flowi_oif = md_info->link; if (md_info->dst_orig) { struct dst_entry *tmp_dst = dst; dst = md_info->dst_orig; skb_dst_set(skb, dst); md_info->dst_orig = NULL; dst_release(tmp_dst); } } else { if_id = xi->p.if_id; } dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, if_id); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } x = dst->xfrm; if (!x) goto tx_err_link_failure; if (x->if_id != if_id) goto tx_err_link_failure; tdev = dst->dev; if (tdev == dev) { DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb->len > 1280) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); else goto xmit; } else { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } dst_release(dst); return -EMSGSIZE; } xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; err = dst_output(xi->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_aborted_errors); } return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, dst); } break; case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET); if (!dst) { struct rtable *rt; fl.u.ip4.flowi4_oif = dev->ifindex; fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, &rt->dst); } break; default: goto tx_err; } fl.flowi_oif = xi->p.link; ret = xfrmi_xmit2(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } static int xfrmi4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->protocol; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; break; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->nexthdr; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) { if (xi->p.link != p->link) return -EINVAL; xi->p.if_id = p->if_id; return 0; } static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) { struct net *net = xi->net; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; xfrmi_unlink(xfrmn, xi); synchronize_net(); err = xfrmi_change(xi, p); xfrmi_link(xfrmn, xi); netdev_state_change(xi->dev); return err; } static int xfrmi_get_iflink(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return READ_ONCE(xi->p.link); } static const struct net_device_ops xfrmi_netdev_ops = { .ndo_init = xfrmi_dev_init, .ndo_uninit = xfrmi_dev_uninit, .ndo_start_xmit = xfrmi_xmit, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = xfrmi_get_iflink, }; static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); } #define XFRMI_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static int xfrmi_dev_init(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; err = gro_cells_init(&xi->gro_cells, dev); if (err) return err; dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; dev->hw_features |= XFRMI_FEATURES; if (phydev) { dev->needed_headroom = phydev->needed_headroom; dev->needed_tailroom = phydev->needed_tailroom; if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, phydev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); } else { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); } return 0; } static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void xfrmi_netlink_parms(struct nlattr *data[], struct xfrm_if_parms *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_XFRM_LINK]) parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); if (data[IFLA_XFRM_IF_ID]) parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); if (data[IFLA_XFRM_COLLECT_METADATA]) parms->collect_md = true; } static int xfrmi_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct xfrm_if_parms p = {}; struct xfrm_if *xi; int err; xfrmi_netlink_parms(data, &p); if (p.collect_md) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); if (p.link || p.if_id) { NL_SET_ERR_MSG(extack, "link and if_id must be zero"); return -EINVAL; } if (rtnl_dereference(xfrmn->collect_md_xfrmi)) return -EEXIST; } else { if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (xi) return -EEXIST; } xi = netdev_priv(dev); xi->p = p; xi->net = net; xi->dev = dev; err = xfrmi_create(dev); return err; } static void xfrmi_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = xi->net; struct xfrm_if_parms p = {}; xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } if (p.collect_md) { NL_SET_ERR_MSG(extack, "collect_md can't be changed"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); } else { if (xi->dev != dev) return -EEXIST; if (xi->p.collect_md) { NL_SET_ERR_MSG(extack, "device can't be changed to collect_md"); return -EINVAL; } } return xfrmi_update(xi, &p); } static size_t xfrmi_get_size(const struct net_device *dev) { return /* IFLA_XFRM_LINK */ nla_total_size(4) + /* IFLA_XFRM_IF_ID */ nla_total_size(4) + /* IFLA_XFRM_COLLECT_METADATA */ nla_total_size(0) + 0; } static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrm_if_parms *parm = &xi->p; if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id) || (xi->p.collect_md && nla_put_flag(skb, IFLA_XFRM_COLLECT_METADATA))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *xfrmi_get_link_net(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return READ_ONCE(xi->net); } static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { [IFLA_XFRM_UNSPEC] = { .strict_start_type = IFLA_XFRM_COLLECT_METADATA }, [IFLA_XFRM_LINK] = { .type = NLA_U32 }, [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, [IFLA_XFRM_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .kind = "xfrm", .maxtype = IFLA_XFRM_MAX, .policy = xfrmi_policy, .priv_size = sizeof(struct xfrm_if), .setup = xfrmi_dev_setup, .validate = xfrmi_validate, .newlink = xfrmi_newlink, .dellink = xfrmi_dellink, .changelink = xfrmi_changelink, .get_size = xfrmi_get_size, .fill_info = xfrmi_fill_info, .get_link_net = xfrmi_get_link_net, }; static void __net_exit xfrmi_exit_batch_rtnl(struct list_head *net_exit_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_exit_list, exit_list) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; struct xfrm_if *xi; int i; for (i = 0; i < XFRMI_HASH_SIZE; i++) { for (xip = &xfrmn->xfrmi[i]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) unregister_netdevice_queue(xi->dev, dev_to_kill); } xi = rtnl_dereference(xfrmn->collect_md_xfrmi); if (xi) unregister_netdevice_queue(xi->dev, dev_to_kill); } } static struct pernet_operations xfrmi_net_ops = { .exit_batch_rtnl = xfrmi_exit_batch_rtnl, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { .handler = xfrmi6_rcv, .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) static int xfrmi6_rcv_tunnel(struct sk_buff *skb) { const xfrm_address_t *saddr; __be32 spi; saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL); } static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 2, }; static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { .handler = xfrmi6_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 2, }; #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { .handler = xfrmi4_rcv, .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) static int xfrmi4_rcv_tunnel(struct sk_buff *skb) { return xfrm4_rcv_spi(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr); } static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 3, }; static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = { .handler = xfrmi4_rcv_tunnel, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 2, }; #endif static int __init xfrmi4_init(void) { int err; err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) err = xfrm4_tunnel_register(&xfrmi_ipip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ipip_failed; err = xfrm4_tunnel_register(&xfrmi_ipip6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipip6_failed; #endif return 0; #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) xfrm_tunnel_ipip6_failed: xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); #endif xfrm_proto_comp_failed: xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi4_fini(void) { #if IS_REACHABLE(CONFIG_INET_XFRM_TUNNEL) xfrm4_tunnel_deregister(&xfrmi_ipip6_handler, AF_INET6); xfrm4_tunnel_deregister(&xfrmi_ipip_handler, AF_INET); #endif xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); } static int __init xfrmi6_init(void) { int err; err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) err = xfrm6_tunnel_register(&xfrmi_ipv6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipv6_failed; err = xfrm6_tunnel_register(&xfrmi_ip6ip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ip6ip_failed; #endif return 0; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm_tunnel_ip6ip_failed: xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); xfrm_tunnel_ipv6_failed: xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); #endif xfrm_proto_comp_failed: xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi6_fini(void) { #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm6_tunnel_deregister(&xfrmi_ip6ip_handler, AF_INET); xfrm6_tunnel_deregister(&xfrmi_ipv6_handler, AF_INET6); #endif xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); } static const struct xfrm_if_cb xfrm_if_cb = { .decode_session = xfrmi_decode_session, }; static int __init xfrmi_init(void) { const char *msg; int err; pr_info("IPsec XFRM device driver\n"); msg = "tunnel device"; err = register_pernet_device(&xfrmi_net_ops); if (err < 0) goto pernet_dev_failed; msg = "xfrm4 protocols"; err = xfrmi4_init(); if (err < 0) goto xfrmi4_failed; msg = "xfrm6 protocols"; err = xfrmi6_init(); if (err < 0) goto xfrmi6_failed; msg = "netlink interface"; err = rtnl_link_register(&xfrmi_link_ops); if (err < 0) goto rtnl_link_failed; err = register_xfrm_interface_bpf(); if (err < 0) goto kfunc_failed; lwtunnel_encap_add_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM); xfrm_if_register_cb(&xfrm_if_cb); return err; kfunc_failed: rtnl_link_unregister(&xfrmi_link_ops); rtnl_link_failed: xfrmi6_fini(); xfrmi6_failed: xfrmi4_fini(); xfrmi4_failed: unregister_pernet_device(&xfrmi_net_ops); pernet_dev_failed: pr_err("xfrmi init: failed to register %s\n", msg); return err; } static void __exit xfrmi_fini(void) { xfrm_if_unregister_cb(); lwtunnel_encap_del_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM); rtnl_link_unregister(&xfrmi_link_ops); xfrmi4_fini(); xfrmi6_fini(); unregister_pernet_device(&xfrmi_net_ops); } module_init(xfrmi_init); module_exit(xfrmi_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("xfrm"); MODULE_ALIAS_NETDEV("xfrm0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("XFRM virtual interface"); |
| 8 5 5 2 8 39 39 46 49 49 49 39 46 49 49 49 49 1 1 5 1 4 3 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 6 2 2 3 3 3 3 6 3 3 3 2 1 3 3 3 3 3 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 3 3 3 3 1 1 1 2 3 3 3 3 1 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/dir.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) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds * * ext4 directory handling functions * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Hash Tree Directory indexing (c) 2001 Daniel Phillips * */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "ext4.h" #include "xattr.h" static int ext4_dx_readdir(struct file *, struct dir_context *); /** * is_dx_dir() - check if a directory is using htree indexing * @inode: directory inode * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not */ static int is_dx_dir(struct inode *inode) { struct super_block *sb = inode->i_sb; if (ext4_has_feature_dir_index(inode->i_sb) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || ((inode->i_size >> sb->s_blocksize_bits) == 1) || ext4_has_inline_data(inode))) return 1; return 0; } static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de) { /* Check if . or .. , or skip if namelen is 0 */ if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') && (de->name[1] == '.' || de->name[1] == '\0')) return true; /* Check if this is a csum entry */ if (de->file_type == EXT4_FT_DIR_CSUM) return true; return false; } /* * Return 0 if the directory entry is OK, and 1 if there is a problem * * Note: this is the opposite of what ext2 and ext3 historically returned... * * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, struct buffer_head *bh, char *buf, int size, unsigned int offset) { const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); const int next_offset = ((char *) de - buf) + rlen; bool fake = is_fake_dir_entry(de); bool has_csum = ext4_has_metadata_csum(dir->i_sb); if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; else if (unlikely(next_offset > size - ext4_dir_rec_len(1, has_csum ? NULL : dir) && next_offset != size)) error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; else return 0; if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); return 1; } static int ext4_readdir(struct file *file, struct dir_context *ctx) { unsigned int offset; int i; struct ext4_dir_entry_2 *de; int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); err = fscrypt_prepare_readdir(inode); if (err) return err; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) return err; /* Can we just clear INDEX flag to ignore htree information? */ if (!ext4_has_metadata_csum(sb)) { /* * We don't set the inode dirty flag since it's not * critical that it gets flushed back to the disk. */ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } if (ext4_has_inline_data(inode)) { int has_inline_data = 1; err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) return err; } if (IS_ENCRYPTED(inode)) { err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr); if (err < 0) return err; } while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto errout; } cond_resched(); offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); if (err == 0) { /* m_len should never be zero but let's avoid * an infinite loop if it somehow is */ if (map.m_len == 0) map.m_len = 1; ctx->pos += map.m_len * sb->s_blocksize; continue; } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( sb->s_bdev->bd_mapping, &file->f_ra, file, index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; goto errout; } } if (!bh) { /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; ctx->pos += sb->s_blocksize - offset; continue; } /* Check the checksum */ if (!buffer_verified(bh) && !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); bh = NULL; continue; } set_buffer_verified(bh); /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) < ext4_dir_rec_len(1, inode)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; file->f_version = inode_query_iversion(inode); } while (ctx->pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); if (ext4_check_dir_entry(inode, file, de, bh, bh->b_data, bh->b_size, offset)) { /* * On error, skip to the next block */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; break; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { if (!IS_ENCRYPTED(inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } else { int save_len = fstr.len; struct fscrypt_str de_name = FSTR_INIT(de->name, de->name_len); /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, EXT4_DIRENT_HASH(de), EXT4_DIRENT_MINOR_HASH(de), &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) goto errout; if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode)) goto done; brelse(bh); bh = NULL; } done: err = 0; errout: fscrypt_fname_free_buffer(&fstr); brelse(bh); return err; } static inline int is_32bit_api(void) { #ifdef CONFIG_COMPAT return in_compat_syscall(); #else return (BITS_PER_LONG == 32); #endif } /* * These functions convert from the major/minor hash to an f_pos * value for dx directories * * Upper layer (for example NFS) should specify FMODE_32BITHASH or * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted * directly on both 32-bit and 64-bit nodes, under such case, neither * FMODE_32BITHASH nor FMODE_64BITHASH is specified. */ static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return major >> 1; else return ((__u64)(major >> 1) << 32) | (__u64)minor; } static inline __u32 pos2maj_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return (pos << 1) & 0xffffffff; else return ((pos >> 32) << 1) & 0xffffffff; } static inline __u32 pos2min_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return 0; else return pos & 0xffffffff; } /* * Return 32- or 64-bit end-of-file for dx directories */ static inline loff_t ext4_get_htree_eof(struct file *filp) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return EXT4_HTREE_EOF_32BIT; else return EXT4_HTREE_EOF_64BIT; } /* * ext4_dir_llseek() calls generic_file_llseek_size to handle htree * directories, where the "offset" is in terms of the filename hash * value instead of the byte offset. * * Because we may return a 64-bit hash that is well beyond offset limits, * we need to pass the max hash as the maximum allowable offset in * the htree directory case. * * For non-htree, ext4_llseek already chooses the proper max offset. */ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; int dx_dir = is_dx_dir(inode); loff_t ret, htree_max = ext4_get_htree_eof(file); if (likely(dx_dir)) ret = generic_file_llseek_size(file, offset, whence, htree_max, htree_max); else ret = ext4_llseek(file, offset, whence); file->f_version = inode_peek_iversion(inode) - 1; return ret; } /* * This structure holds the nodes of the red-black tree used to store * the directory entry in hash order. */ struct fname { __u32 hash; __u32 minor_hash; struct rb_node rb_hash; struct fname *next; __u32 inode; __u8 name_len; __u8 file_type; char name[]; }; /* * This function implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) { struct fname *fname, *next; rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash) while (fname) { struct fname *old = fname; fname = fname->next; kfree(old); } *root = RB_ROOT; } static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp, loff_t pos) { struct dir_private_info *p; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return NULL; p->curr_hash = pos2maj_hash(filp, pos); p->curr_minor_hash = pos2min_hash(filp, pos); return p; } void ext4_htree_free_dir_info(struct dir_private_info *p) { free_rb_tree_fname(&p->root); kfree(p); } /* * Given a directory entry, enter it into the fname rb tree. * * When filename encryption is enabled, the dirent will hold the * encrypted filename, while the htree will hold decrypted filename. * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; struct dir_private_info *info; int len; info = dir_file->private_data; p = &info->root.rb_node; /* Create and allocate the fname structure */ len = sizeof(struct fname) + ent_name->len + 1; new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; memcpy(new_fn->name, ent_name->name, ent_name->len); while (*p) { parent = *p; fname = rb_entry(parent, struct fname, rb_hash); /* * If the hash and minor hash match up, then we put * them on a linked list. This rarely happens... */ if ((new_fn->hash == fname->hash) && (new_fn->minor_hash == fname->minor_hash)) { new_fn->next = fname->next; fname->next = new_fn; return 0; } if (new_fn->hash < fname->hash) p = &(*p)->rb_left; else if (new_fn->hash > fname->hash) p = &(*p)->rb_right; else if (new_fn->minor_hash < fname->minor_hash) p = &(*p)->rb_left; else /* if (new_fn->minor_hash > fname->minor_hash) */ p = &(*p)->rb_right; } rb_link_node(&new_fn->rb_hash, parent, p); rb_insert_color(&new_fn->rb_hash, &info->root); return 0; } /* * This is a helper function for ext4_dx_readdir. It calls filldir * for all entries on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, struct fname *fname) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; if (!fname) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: " "called with null fname?!?", __func__, __LINE__, inode->i_ino, current->comm); return 0; } ctx->pos = hash2pos(file, fname->hash, fname->minor_hash); while (fname) { if (!dir_emit(ctx, fname->name, fname->name_len, fname->inode, get_dtype(sb, fname->file_type))) { info->extra_fname = fname; return 1; } fname = fname->next; } return 0; } static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); if (!info) return -ENOMEM; file->private_data = info; } if (ctx->pos == ext4_get_htree_eof(file)) return 0; /* EOF */ /* Some one has messed with f_pos; reset the world */ if (info->last_pos != ctx->pos) { free_rb_tree_fname(&info->root); info->curr_node = NULL; info->extra_fname = NULL; info->curr_hash = pos2maj_hash(file, ctx->pos); info->curr_minor_hash = pos2min_hash(file, ctx->pos); } /* * If there are any leftover names on the hash collision * chain, return them first. */ if (info->extra_fname) { if (call_filldir(file, ctx, info->extra_fname)) goto finished; info->extra_fname = NULL; goto next_node; } else if (!info->curr_node) info->curr_node = rb_first(&info->root); while (1) { /* * Fill the rbtree if we have no more entries, * or the inode has changed since we last read in the * cached entries. */ if ((!info->curr_node) || !inode_eq_iversion(inode, file->f_version)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); file->f_version = inode_query_iversion(inode); ret = ext4_htree_fill_tree(file, info->curr_hash, info->curr_minor_hash, &info->next_hash); if (ret < 0) goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_node = rb_first(&info->root); } fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; if (call_filldir(file, ctx, fname)) break; next_node: info->curr_node = rb_next(info->curr_node); if (info->curr_node) { fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; } else { if (info->next_hash == ~0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_hash = info->next_hash; info->curr_minor_hash = 0; } } finished: info->last_pos = ctx->pos; return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) { if (filp->private_data) ext4_htree_free_dir_info(filp->private_data); return 0; } int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size) { struct ext4_dir_entry_2 *de; int rlen; unsigned int offset = 0; char *top; de = buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) return -EFSCORRUPTED; rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } if ((char *) de > top) return -EFSCORRUPTED; return 0; } const struct file_operations ext4_dir_operations = { .llseek = ext4_dir_llseek, .read = generic_read_dir, .iterate_shared = ext4_readdir, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, .release = ext4_release_dir, }; |
| 95 1 5 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the UDP protocol. * * Version: @(#)udp.h 1.0.2 04/28/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_UDP_H #define _LINUX_UDP_H #include <net/inet_sock.h> #include <linux/skbuff.h> #include <net/netns/hash.h> #include <uapi/linux/udp.h> static inline struct udphdr *udp_hdr(const struct sk_buff *skb) { return (struct udphdr *)skb_transport_header(skb); } #define UDP_HTABLE_SIZE_MIN_PERNET 128 #define UDP_HTABLE_SIZE_MIN (IS_ENABLED(CONFIG_BASE_SMALL) ? 128 : 256) #define UDP_HTABLE_SIZE_MAX 65536 static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) { return (num + net_hash_mix(net)) & mask; } enum { UDP_FLAGS_CORK, /* Cork is required */ UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ UDP_FLAGS_ACCEPT_FRAGLIST, UDP_FLAGS_ACCEPT_L4, UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ UDP_FLAGS_UDPLITE_SEND_CC, /* set via udplite setsockopt */ UDP_FLAGS_UDPLITE_RECV_CC, /* set via udplite setsockopt */ }; struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node unsigned long udp_flags; int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ __u16 gso_size; /* * Fields specific to UDP-Lite. */ __u16 pcslen; __u16 pcrlen; /* * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ struct sk_buff * (*gro_receive)(struct sock *sk, struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sock *sk, struct sk_buff *skb, int nhoff); /* udp_recvmsg try to use this before splicing sk_receive_queue */ struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; /* This field is dirtied by udp_recvmsg() */ int forward_deficit; /* This fields follows rcvbuf value, and is touched by udp_recvmsg */ int forward_threshold; /* Cache friendly copy of sk->sk_peek_off >= 0 */ bool peeking_with_offset; }; #define udp_test_bit(nr, sk) \ test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_set_bit(nr, sk) \ set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_test_and_set_bit(nr, sk) \ test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_clear_bit(nr, sk) \ clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) #define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) static inline int udp_set_peek_off(struct sock *sk, int val) { sk_set_peek_off(sk, val); WRITE_ONCE(udp_sk(sk)->peeking_with_offset, val >= 0); return 0; } static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { udp_assign_bit(NO_CHECK6_TX, sk, val); } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { udp_assign_bit(NO_CHECK6_RX, sk, val); } static inline bool udp_get_no_check6_tx(const struct sock *sk) { return udp_test_bit(NO_CHECK6_TX, sk); } static inline bool udp_get_no_check6_rx(const struct sock *sk) { return udp_test_bit(NO_CHECK6_RX, sk); } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int gso_size; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { gso_size = skb_shinfo(skb)->gso_size; put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size); } } DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); #endif static inline bool udp_encap_needed(void) { if (static_branch_unlikely(&udp_encap_needed_key)) return true; #if IS_ENABLED(CONFIG_IPV6) if (static_branch_unlikely(&udpv6_encap_needed_key)) return true; #endif return false; } static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) return false; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_test_bit(ACCEPT_L4, sk)) return true; if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still * land in a tunnel as the socket check in udp_gro_receive cannot be * foolproof. */ if (udp_encap_needed() && READ_ONCE(udp_sk(sk)->encap_rcv) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) return true; return false; } static inline void udp_allow_gso(struct sock *sk) { udp_set_bit(ACCEPT_L4, sk); udp_set_bit(ACCEPT_FRAGLIST, sk); } #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) #define udp_portaddr_for_each_entry_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node) #define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE) #endif /* _LINUX_UDP_H */ |
| 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | #ifndef INTERNAL_IO_SLIST_H #define INTERNAL_IO_SLIST_H #include <linux/io_uring_types.h> #define __wq_list_for_each(pos, head) \ for (pos = (head)->first; pos; pos = (pos)->next) #define wq_list_for_each(pos, prv, head) \ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) #define wq_list_for_each_resume(pos, prv) \ for (; pos; prv = pos, pos = (pos)->next) #define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) #define INIT_WQ_LIST(list) do { \ (list)->first = NULL; \ } while (0) static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) { struct io_wq_work_node *next = pos->next; pos->next = node; node->next = next; if (!next) list->last = node; } static inline void wq_list_add_tail(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = NULL; if (!list->first) { list->last = node; WRITE_ONCE(list->first, node); } else { list->last->next = node; list->last = node; } } static inline void wq_list_add_head(struct io_wq_work_node *node, struct io_wq_work_list *list) { node->next = list->first; if (!node->next) list->last = node; WRITE_ONCE(list->first, node); } static inline void wq_list_cut(struct io_wq_work_list *list, struct io_wq_work_node *last, struct io_wq_work_node *prev) { /* first in the list, if prev==NULL */ if (!prev) WRITE_ONCE(list->first, last->next); else prev->next = last->next; if (last == list->last) list->last = prev; last->next = NULL; } static inline void __wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { list->last->next = to->next; to->next = list->first; INIT_WQ_LIST(list); } static inline bool wq_list_splice(struct io_wq_work_list *list, struct io_wq_work_node *to) { if (!wq_list_empty(list)) { __wq_list_splice(list, to); return true; } return false; } static inline void wq_stack_add_head(struct io_wq_work_node *node, struct io_wq_work_node *stack) { node->next = stack->next; stack->next = node; } static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work_node *node, struct io_wq_work_node *prev) { wq_list_cut(list, node, prev); } static inline struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) { struct io_wq_work_node *node = stack->next; stack->next = node->next; return node; } static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) { if (!work->list.next) return NULL; return container_of(work->list.next, struct io_wq_work, list); } #endif // INTERNAL_IO_SLIST_H |
| 127 125 126 122 126 1 123 1 1 1 1138 1156 1138 1144 1139 1147 1142 1141 | 1 2 3 4 5 6 7 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 #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. * * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted * task and run the task_work, regardless of whether the task is currently * running in the kernel or userspace. * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a * reschedule IPI to force the targeted task to reschedule and run task_work. * This can be advantageous if there's no strict requirement that the * task_work be run as soon as possible, just whenever the task enters the * kernel anyway. * @TWA_RESUME work is run only when the task exits the kernel and returns to * user mode, or before entering guest mode. * * Fails if the @task is exiting/exited and thus it can't process this @work. * Otherwise @work->func() will be called when the @task goes through one of * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); head = READ_ONCE(task->task_works); do { if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (!try_cmpxchg(&task->task_works, &head, work)); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task_work_pending(task))) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); work = READ_ONCE(*pprev); while (work) { if (!match(work, data)) { pprev = &work->next; work = READ_ONCE(*pprev); } else if (try_cmpxchg(pprev, &work, work->next)) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @func: identifies the work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ work = READ_ONCE(task->task_works); do { head = NULL; if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (!try_cmpxchg(&task->task_works, &work, head)); if (!work) break; /* * Synchronize with task_work_cancel(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 466 463 125 125 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 70 57 9 19 | 1 2 3 4 5 6 7 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_BIT_H #define _LINUX_WAIT_BIT_H /* * Linux wait-bit related types and methods: */ #include <linux/wait.h> struct wait_bit_key { void *flags; int bit_nr; unsigned long timeout; }; struct wait_bit_queue_entry { struct wait_bit_key key; struct wait_queue_entry wq_entry; }; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue_entry name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ .wq_entry = { \ .private = current, \ .func = wake_bit_function, \ .entry = \ LIST_HEAD_INIT((name).wq_entry.entry), \ }, \ } extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit. * For instance, if one were to have waiters on a bitflag, one would * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, mode); } /** * wait_on_bit_io - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), but calls * io_schedule() instead of schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, mode); } /** * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), except also takes a * timeout parameter. * * Returned value will be zero if the bit was cleared before the * @timeout elapsed, or non-zero if the @timeout elapsed or process * received a signal and the mode permitted wakeup on that signal. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, mode, timeout); } /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared, and allow the waiting action to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } /** * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit * when one intends to set it, for instance, trying to lock bitflags. * For instance, if one were to have waiters trying to set bitflag * and waiting for it to clear before setting it, one would call * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); } /** * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to atomically set it. This is similar * to wait_on_bit(), but calls io_schedule() instead of schedule() * for the actual waiting. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); } /** * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to set it, and allow the waiting action * to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, action, mode); } extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); #define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_head *__wq_head = __var_waitqueue(var); \ struct wait_bit_queue_entry __wbq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_var_entry(&__wbq_entry, var, \ exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(__wq_head, \ &__wbq_entry.wq_entry, \ state); \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(__wq_head, &__wbq_entry.wq_entry); \ __out: __ret; \ }) #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_killable(var, condition); \ __ret; \ }) #define __wait_var_event_timeout(var, condition, timeout) \ ___wait_var_event(var, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_var_event_timeout(var, condition, timeout); \ __ret; \ }) #define __wait_var_event_interruptible(var, condition) \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * * @bit: the bit of the word being waited on * @word: the word being waited on, a kernel virtual address * * You can use this helper if bitflags are manipulated atomically rather than * non-atomically under a lock. */ static inline void clear_and_wake_up_bit(int bit, void *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ smp_mb__after_atomic(); wake_up_bit(word, bit); } #endif /* _LINUX_WAIT_BIT_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat * * based in parts on udlfb.c: * Copyright (C) 2009 Roberto De Ioris <roberto@unbit.it> * Copyright (C) 2009 Jaya Kumar <jayakumar.lkml@gmail.com> * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com> */ #include <drm/drm.h> #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include "udl_drv.h" /* -BULK_SIZE as per usb-skeleton. Can we get full page and avoid overhead? */ #define BULK_SIZE 512 #define NR_USB_REQUEST_CHANNEL 0x12 #define MAX_TRANSFER (PAGE_SIZE*16 - BULK_SIZE) #define WRITES_IN_FLIGHT (20) #define MAX_VENDOR_DESCRIPTOR_SIZE 256 static struct urb *udl_get_urb_locked(struct udl_device *udl, long timeout); static int udl_parse_vendor_descriptor(struct udl_device *udl) { struct usb_device *udev = udl_to_usb_device(udl); char *desc; char *buf; char *desc_end; u8 total_len = 0; buf = kzalloc(MAX_VENDOR_DESCRIPTOR_SIZE, GFP_KERNEL); if (!buf) return false; desc = buf; total_len = usb_get_descriptor(udev, 0x5f, /* vendor specific */ 0, desc, MAX_VENDOR_DESCRIPTOR_SIZE); if (total_len > 5) { DRM_INFO("vendor descriptor length:%x data:%11ph\n", total_len, desc); if ((desc[0] != total_len) || /* descriptor length */ (desc[1] != 0x5f) || /* vendor descriptor type */ (desc[2] != 0x01) || /* version (2 bytes) */ (desc[3] != 0x00) || (desc[4] != total_len - 2)) /* length after type */ goto unrecognized; desc_end = desc + total_len; desc += 5; /* the fixed header we've already parsed */ while (desc < desc_end) { u8 length; u16 key; key = le16_to_cpu(*((u16 *) desc)); desc += sizeof(u16); length = *desc; desc++; switch (key) { case 0x0200: { /* max_area */ u32 max_area; max_area = le32_to_cpu(*((u32 *)desc)); DRM_DEBUG("DL chip limited to %d pixel modes\n", max_area); udl->sku_pixel_limit = max_area; break; } default: break; } desc += length; } } goto success; unrecognized: /* allow udlfb to load for now even if firmware unrecognized */ DRM_ERROR("Unrecognized vendor firmware descriptor\n"); success: kfree(buf); return true; } /* * Need to ensure a channel is selected before submitting URBs */ int udl_select_std_channel(struct udl_device *udl) { static const u8 set_def_chn[] = {0x57, 0xCD, 0xDC, 0xA7, 0x1C, 0x88, 0x5E, 0x15, 0x60, 0xFE, 0xC6, 0x97, 0x16, 0x3D, 0x47, 0xF2}; void *sendbuf; int ret; struct usb_device *udev = udl_to_usb_device(udl); sendbuf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL); if (!sendbuf) return -ENOMEM; ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), NR_USB_REQUEST_CHANNEL, (USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0, sendbuf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT); kfree(sendbuf); return ret < 0 ? ret : 0; } void udl_urb_completion(struct urb *urb) { struct urb_node *unode = urb->context; struct udl_device *udl = unode->dev; unsigned long flags; /* sync/async unlink faults aren't errors */ if (urb->status) { if (!(urb->status == -ENOENT || urb->status == -ECONNRESET || urb->status == -EPROTO || urb->status == -ESHUTDOWN)) { DRM_ERROR("%s - nonzero write bulk status received: %d\n", __func__, urb->status); } } urb->transfer_buffer_length = udl->urbs.size; /* reset to actual */ spin_lock_irqsave(&udl->urbs.lock, flags); list_add_tail(&unode->entry, &udl->urbs.list); udl->urbs.available++; spin_unlock_irqrestore(&udl->urbs.lock, flags); wake_up(&udl->urbs.sleep); } static void udl_free_urb_list(struct drm_device *dev) { struct udl_device *udl = to_udl(dev); struct urb_node *unode; struct urb *urb; DRM_DEBUG("Waiting for completes and freeing all render urbs\n"); /* keep waiting and freeing, until we've got 'em all */ while (udl->urbs.count) { spin_lock_irq(&udl->urbs.lock); urb = udl_get_urb_locked(udl, MAX_SCHEDULE_TIMEOUT); udl->urbs.count--; spin_unlock_irq(&udl->urbs.lock); if (WARN_ON(!urb)) break; unode = urb->context; /* Free each separately allocated piece */ usb_free_coherent(urb->dev, udl->urbs.size, urb->transfer_buffer, urb->transfer_dma); usb_free_urb(urb); kfree(unode); } wake_up_all(&udl->urbs.sleep); } static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size) { struct udl_device *udl = to_udl(dev); struct urb *urb; struct urb_node *unode; char *buf; size_t wanted_size = count * size; struct usb_device *udev = udl_to_usb_device(udl); spin_lock_init(&udl->urbs.lock); INIT_LIST_HEAD(&udl->urbs.list); init_waitqueue_head(&udl->urbs.sleep); udl->urbs.count = 0; udl->urbs.available = 0; retry: udl->urbs.size = size; while (udl->urbs.count * size < wanted_size) { unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL); if (!unode) break; unode->dev = udl; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) { kfree(unode); break; } unode->urb = urb; buf = usb_alloc_coherent(udev, size, GFP_KERNEL, &urb->transfer_dma); if (!buf) { kfree(unode); usb_free_urb(urb); if (size > PAGE_SIZE) { size /= 2; udl_free_urb_list(dev); goto retry; } break; } /* urb->transfer_buffer_length set to actual before submit */ usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, 1), buf, size, udl_urb_completion, unode); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; list_add_tail(&unode->entry, &udl->urbs.list); udl->urbs.count++; udl->urbs.available++; } DRM_DEBUG("allocated %d %d byte urbs\n", udl->urbs.count, (int) size); return udl->urbs.count; } static struct urb *udl_get_urb_locked(struct udl_device *udl, long timeout) { struct urb_node *unode; assert_spin_locked(&udl->urbs.lock); /* Wait for an in-flight buffer to complete and get re-queued */ if (!wait_event_lock_irq_timeout(udl->urbs.sleep, !udl->urbs.count || !list_empty(&udl->urbs.list), udl->urbs.lock, timeout)) { DRM_INFO("wait for urb interrupted: available: %d\n", udl->urbs.available); return NULL; } if (!udl->urbs.count) return NULL; unode = list_first_entry(&udl->urbs.list, struct urb_node, entry); list_del_init(&unode->entry); udl->urbs.available--; return unode->urb; } #define GET_URB_TIMEOUT HZ struct urb *udl_get_urb(struct drm_device *dev) { struct udl_device *udl = to_udl(dev); struct urb *urb; spin_lock_irq(&udl->urbs.lock); urb = udl_get_urb_locked(udl, GET_URB_TIMEOUT); spin_unlock_irq(&udl->urbs.lock); return urb; } int udl_submit_urb(struct drm_device *dev, struct urb *urb, size_t len) { struct udl_device *udl = to_udl(dev); int ret; if (WARN_ON(len > udl->urbs.size)) { ret = -EINVAL; goto error; } urb->transfer_buffer_length = len; /* set to actual payload len */ ret = usb_submit_urb(urb, GFP_ATOMIC); error: if (ret) { udl_urb_completion(urb); /* because no one else will */ DRM_ERROR("usb_submit_urb error %x\n", ret); } return ret; } /* wait until all pending URBs have been processed */ void udl_sync_pending_urbs(struct drm_device *dev) { struct udl_device *udl = to_udl(dev); spin_lock_irq(&udl->urbs.lock); /* 2 seconds as a sane timeout */ if (!wait_event_lock_irq_timeout(udl->urbs.sleep, udl->urbs.available == udl->urbs.count, udl->urbs.lock, msecs_to_jiffies(2000))) drm_err(dev, "Timeout for syncing pending URBs\n"); spin_unlock_irq(&udl->urbs.lock); } int udl_init(struct udl_device *udl) { struct drm_device *dev = &udl->drm; int ret = -ENOMEM; DRM_DEBUG("\n"); udl->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev)); if (!udl->dmadev) drm_warn(dev, "buffer sharing not supported"); /* not an error */ mutex_init(&udl->gem_lock); if (!udl_parse_vendor_descriptor(udl)) { ret = -ENODEV; DRM_ERROR("firmware not recognized. Assume incompatible device\n"); goto err; } if (udl_select_std_channel(udl)) DRM_ERROR("Selecting channel failed\n"); if (!udl_alloc_urb_list(dev, WRITES_IN_FLIGHT, MAX_TRANSFER)) { DRM_ERROR("udl_alloc_urb_list failed\n"); goto err; } DRM_DEBUG("\n"); ret = udl_modeset_init(dev); if (ret) goto err; drm_kms_helper_poll_init(dev); return 0; err: if (udl->urbs.count) udl_free_urb_list(dev); put_device(udl->dmadev); DRM_ERROR("%d\n", ret); return ret; } int udl_drop_usb(struct drm_device *dev) { struct udl_device *udl = to_udl(dev); udl_free_urb_list(dev); put_device(udl->dmadev); udl->dmadev = NULL; return 0; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Generic RTC interface. * This version contains the part of the user interface to the Real Time Clock * service. It is used with both the legacy mc146818 and also EFI * Struct rtc_time and first 12 ioctl by Paul Gortmaker, 1996 - separated out * from <linux/mc146818rtc.h> to this file for 2.4 kernels. * * Copyright (C) 1999 Hewlett-Packard Co. * Copyright (C) 1999 Stephane Eranian <eranian@hpl.hp.com> */ #ifndef _LINUX_RTC_H_ #define _LINUX_RTC_H_ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/nvmem-provider.h> #include <uapi/linux/rtc.h> extern int rtc_month_days(unsigned int month, unsigned int year); extern int rtc_year_days(unsigned int day, unsigned int month, unsigned int year); extern int rtc_valid_tm(struct rtc_time *tm); extern time64_t rtc_tm_to_time64(struct rtc_time *tm); extern void rtc_time64_to_tm(time64_t time, struct rtc_time *tm); ktime_t rtc_tm_to_ktime(struct rtc_time tm); struct rtc_time rtc_ktime_to_tm(ktime_t kt); /* * rtc_tm_sub - Return the difference in seconds. */ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) { return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); } #include <linux/device.h> #include <linux/seq_file.h> #include <linux/cdev.h> #include <linux/poll.h> #include <linux/mutex.h> #include <linux/timerqueue.h> #include <linux/workqueue.h> extern const struct class rtc_class; /* * For these RTC methods the device parameter is the physical device * on whatever bus holds the hardware (I2C, Platform, SPI, etc), which * was passed to rtc_device_register(). Its driver_data normally holds * device state, including the rtc_device pointer for the RTC. * * Most of these methods are called with rtc_device.ops_lock held, * through the rtc_*(struct rtc_device *, ...) calls. * * The (current) exceptions are mostly filesystem hooks: * - the proc() hook for procfs */ struct rtc_class_ops { int (*ioctl)(struct device *, unsigned int, unsigned long); int (*read_time)(struct device *, struct rtc_time *); int (*set_time)(struct device *, struct rtc_time *); int (*read_alarm)(struct device *, struct rtc_wkalrm *); int (*set_alarm)(struct device *, struct rtc_wkalrm *); int (*proc)(struct device *, struct seq_file *); int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); int (*param_get)(struct device *, struct rtc_param *param); int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; struct rtc_timer { struct timerqueue_node node; ktime_t period; void (*func)(struct rtc_device *rtc); struct rtc_device *rtc; int enabled; }; /* flags */ #define RTC_DEV_BUSY 0 #define RTC_NO_CDEV 1 struct rtc_device { struct device dev; struct module *owner; int id; const struct rtc_class_ops *ops; struct mutex ops_lock; struct cdev char_dev; unsigned long flags; unsigned long irq_data; spinlock_t irq_lock; wait_queue_head_t irq_queue; struct fasync_struct *async_queue; int irq_freq; int max_user_freq; struct timerqueue_head timerqueue; struct rtc_timer aie_timer; struct rtc_timer uie_rtctimer; struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; /* * This offset specifies the update timing of the RTC. * * tsched t1 write(t2.tv_sec - 1sec)) t2 RTC increments seconds * * The offset defines how tsched is computed so that the write to * the RTC (t2.tv_sec - 1sec) is correct versus the time required * for the transport of the write and the time which the RTC needs * to increment seconds the first time after the write (t2). * * For direct accessible RTCs tsched ~= t1 because the write time * is negligible. For RTCs behind slow busses the transport time is * significant and has to be taken into account. * * The time between the write (t1) and the first increment after * the write (t2) is RTC specific. For a MC146818 RTC it's 500ms, * for many others it's exactly 1 second. Consult the datasheet. * * The value of this offset is also used to calculate the to be * written value (t2.tv_sec - 1sec) at tsched. * * The default value for this is NSEC_PER_SEC + 10 msec default * transport time. The offset can be adjusted by drivers so the * calculation for the to be written value at tsched becomes * correct: * * newval = tsched + set_offset_nsec - NSEC_PER_SEC * and (tsched + set_offset_nsec) % NSEC_PER_SEC == 0 */ unsigned long set_offset_nsec; unsigned long features[BITS_TO_LONGS(RTC_FEATURE_CNT)]; time64_t range_min; timeu64_t range_max; timeu64_t alarm_offset_max; time64_t start_secs; time64_t offset_secs; bool set_start_time; #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; /* Those fields are protected by rtc->irq_lock */ unsigned int oldsecs; unsigned int uie_irq_active:1; unsigned int stop_uie_polling:1; unsigned int uie_task_active:1; unsigned int uie_timer_active:1; #endif }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) #define rtc_lock(d) mutex_lock(&d->ops_lock) #define rtc_unlock(d) mutex_unlock(&d->ops_lock) /* useful timestamps */ #define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2079 3471292799LL /* 2079-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2199 7258118399LL /* 2199-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_9999 253402300799LL /* 9999-12-31 23:59:59 */ extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); struct rtc_device *devm_rtc_allocate_device(struct device *dev); int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc); extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern void rtc_update_irq(struct rtc_device *rtc, unsigned long num, unsigned long events); extern struct rtc_device *rtc_class_open(const char *name); extern void rtc_class_close(struct rtc_device *rtc); extern int rtc_irq_set_state(struct rtc_device *rtc, int enabled); extern int rtc_irq_set_freq(struct rtc_device *rtc, int freq); extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled); void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode); void rtc_aie_update_irq(struct rtc_device *rtc); void rtc_uie_update_irq(struct rtc_device *rtc); enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer); void rtc_timer_init(struct rtc_timer *timer, void (*f)(struct rtc_device *r), struct rtc_device *rtc); int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, ktime_t expires, ktime_t period); void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer); int rtc_read_offset(struct rtc_device *rtc, long *offset); int rtc_set_offset(struct rtc_device *rtc, long offset); void rtc_timer_do_work(struct work_struct *work); static inline bool is_leap_year(unsigned int year) { return (!(year % 4) && (year % 100)) || !(year % 400); } /** * rtc_bound_alarmtime() - Return alarm time bound by rtc limit * @rtc: Pointer to rtc device structure * @requested: Requested alarm timeout * * Return: Alarm timeout bound by maximum alarm time supported by rtc. */ static inline ktime_t rtc_bound_alarmtime(struct rtc_device *rtc, ktime_t requested) { if (rtc->alarm_offset_max && rtc->alarm_offset_max * MSEC_PER_SEC < ktime_to_ms(requested)) return ms_to_ktime(rtc->alarm_offset_max * MSEC_PER_SEC); return requested; } #define devm_rtc_register_device(device) \ __devm_rtc_register_device(THIS_MODULE, device) #ifdef CONFIG_RTC_HCTOSYS_DEVICE extern int rtc_hctosys_ret; #else #define rtc_hctosys_ret -ENODEV #endif #ifdef CONFIG_RTC_NVMEM int devm_rtc_nvmem_register(struct rtc_device *rtc, struct nvmem_config *nvmem_config); #else static inline int devm_rtc_nvmem_register(struct rtc_device *rtc, struct nvmem_config *nvmem_config) { return 0; } #endif #ifdef CONFIG_RTC_INTF_SYSFS int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp); int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps); #else static inline int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp) { return 0; } static inline int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) { return 0; } #endif #endif /* _LINUX_RTC_H_ */ |
| 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Regents of the University of California * Copyright (C) 2014 Darius Rad <darius@bluespec.com> * Copyright (C) 2017 SiFive */ #include <linux/syscalls.h> #include <asm/cacheflush.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, off_t offset, unsigned long page_shift_offset) { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } #ifdef CONFIG_64BIT SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) { return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); } #endif #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) { /* * Note that the shift for mmap2 is constant (12), * regardless of PAGE_SIZE */ return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12); } #endif /* * Allows the instruction cache to be flushed from userspace. Despite RISC-V * having a direct 'fence.i' instruction available to userspace (which we * can't trap!), that's not actually viable when running on Linux because the * kernel might schedule a process on another hart. There is no way for * userspace to handle this without invoking the kernel (as it doesn't know the * thread->hart mappings), so we've defined a RISC-V specific system call to * flush the instruction cache. * * sys_riscv_flush_icache() is defined to flush the instruction cache over an * address range, with the flush applying to either all threads or just the * caller. We don't currently do anything with the address range, that's just * in there for forwards compatibility. */ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, uintptr_t, flags) { /* Check the reserved flags. */ if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) return -EINVAL; flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL); return 0; } /* Not defined using SYSCALL_DEFINE0 to avoid error injection */ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused) { return -ENOSYS; } |
| 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | #undef TRACE_SYSTEM #define TRACE_SYSTEM netlink #if !defined(_TRACE_NETLINK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NETLINK_H #include <linux/tracepoint.h> TRACE_EVENT(netlink_extack, TP_PROTO(const char *msg), TP_ARGS(msg), TP_STRUCT__entry( __string( msg, msg ) ), TP_fast_assign( __assign_str(msg); ), TP_printk("msg=%s", __get_str(msg)) ); #endif /* _TRACE_NETLINK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | /* * linux/drivers/video/console/softcursor.c * * Generic software cursor for frame buffer devices * * Created 14 Nov 2002 by James Simmons * * This file is subject to the terms and conditions of the GNU General * Public License. See the file COPYING in the main directory of this * archive for more details. */ #include <linux/module.h> #include <linux/string.h> #include <linux/fb.h> #include <linux/slab.h> #include <asm/io.h> #include "fbcon.h" int soft_cursor(struct fb_info *info, struct fb_cursor *cursor) { struct fbcon_ops *ops = info->fbcon_par; unsigned int scan_align = info->pixmap.scan_align - 1; unsigned int buf_align = info->pixmap.buf_align - 1; unsigned int i, size, dsize, s_pitch, d_pitch; struct fb_image *image; u8 *src, *dst; if (info->state != FBINFO_STATE_RUNNING) return 0; s_pitch = (cursor->image.width + 7) >> 3; dsize = s_pitch * cursor->image.height; if (dsize + sizeof(struct fb_image) != ops->cursor_size) { kfree(ops->cursor_src); ops->cursor_size = dsize + sizeof(struct fb_image); ops->cursor_src = kmalloc(ops->cursor_size, GFP_ATOMIC); if (!ops->cursor_src) { ops->cursor_size = 0; return -ENOMEM; } } src = ops->cursor_src + sizeof(struct fb_image); image = (struct fb_image *)ops->cursor_src; *image = cursor->image; d_pitch = (s_pitch + scan_align) & ~scan_align; size = d_pitch * image->height + buf_align; size &= ~buf_align; dst = fb_get_buffer_offset(info, &info->pixmap, size); if (cursor->enable) { switch (cursor->rop) { case ROP_XOR: for (i = 0; i < dsize; i++) src[i] = image->data[i] ^ cursor->mask[i]; break; case ROP_COPY: default: for (i = 0; i < dsize; i++) src[i] = image->data[i] & cursor->mask[i]; break; } } else memcpy(src, image->data, dsize); fb_pad_aligned_buffer(dst, d_pitch, src, s_pitch, image->height); image->data = dst; info->fbops->fb_imageblit(info, image); return 0; } |
| 49 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (flags & IFF_UP) continue; dev_change_flags(cpriv->dev, flags | IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (!(flags & IFF_UP)) continue; dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } /* Check child interfaces */ down_read_nested(&priv->vlan_rwsem, nesting); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } up_read(&priv->vlan_rwsem); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_update_features(dev); dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); down_write(&ppriv->vlan_rwsem); list_add_tail(&priv->list, &ppriv->child_intfs); up_write(&ppriv->vlan_rwsem); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ASSERT_RTNL(); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); list_del(&priv->list); up_write(&ppriv->vlan_rwsem); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = ipoib_sendq_size * 2; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); up_read(&priv->vlan_rwsem); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 1 1 1 1 1 1 1 2 2 2 2 38 1 1 1 1 1 43 44 44 44 44 44 5 5 5 8 8 3 3 1 1 1 1 1 1 13 13 3 5 5 5 5 5 5 5 3 3 3 3 3 3 3 3 3 3 3 5 5 5 5 5 2 5 5 5 5 4 5 5 7 7 6 1 1 1 1 1 1 7 2 2 2 2 2 2 2 7 6 7 6 2 4 2 6 5 5 6 3 3 3 4 4 2 2 2 2 2 3 3 3 2 1 1 1 1 1 1 1 1 3 7 6 2 1 51 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 2 2 97 97 97 27 90 1 1 1 1 1 1 64 64 11 11 5 5 64 1 4 4 4 4 4 3 4 4 3 4 4 1 4 119 93 32 118 118 117 78 118 136 137 136 6 6 6 6 6 6 6 58 149 96 57 58 58 57 58 4 57 32 27 27 68 97 97 97 266 265 259 262 14 14 14 13 14 14 45 46 42 44 42 27 16 46 46 46 43 43 1 43 43 43 42 48 12 12 12 1 1 1 1 1 1 95 95 163 198 198 198 198 193 168 145 144 142 1 141 3 138 138 137 20 119 1 1 118 116 1 197 51 26 7 49 188 188 119 119 119 104 164 163 21 164 95 94 114 95 162 21 2 2 11 243 48 48 48 2 2 1 48 197 244 246 246 246 48 7 100 99 100 100 22 1 99 97 83 83 84 81 18 38 18 72 64 82 38 64 40 5 38 38 40 40 96 97 96 24 20 16 23 18 18 97 115 117 115 117 116 81 78 72 20 20 66 63 102 24 24 24 20 10 3 14 3 3 1 93 18 15 18 85 35 3 3 1 3 32 66 63 42 43 63 63 15 100 116 86 86 58 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 1 2 2 19 2 2 2 2 2 2 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * ROUTE - implementation of the IP router. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Linus Torvalds, <Linus.Torvalds@helsinki.fi> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Alan Cox : Verify area fixes. * Alan Cox : cli() protects routing changes * Rui Oliveira : ICMP routing table updates * (rco@di.uminho.pt) Routing table insertion and update * Linus Torvalds : Rewrote bits to be sensible * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. * Alan Cox : Removed compatibility cruft. * Alan Cox : RTF_REJECT support. * Alan Cox : TCP irtt support. * Jonathan Naylor : Added Metric support. * Miquel van Smoorenburg : BSD API fixes. * Miquel van Smoorenburg : Metrics. * Alan Cox : Use __u32 properly * Alan Cox : Aligned routing errors more closely with BSD * our system is still very different. * Alan Cox : Faster /proc handling * Alexey Kuznetsov : Massive rework to support tree based routing, * routing caches and better behaviour. * * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. * Andi Kleen : Load-limit warning messages. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Vitaly E. Lavrov : Race condition in ip_route_input_slow. * Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow. * Vladimir V. Ivanov : IP rule info (flowid) is really useful. * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/socket.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/pkt_sched.h> #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> #include "fib_lookup.h" #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) #define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); return NULL; } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, .confirm_neigh = ipv4_confirm_neigh, }; #define ECN_OR_COST(class) TC_PRIO_##class const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos) return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { } static int rt_cache_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); return 0; } static const struct seq_operations rt_cache_seq_ops = { .start = rt_cache_seq_start, .next = rt_cache_seq_next, .stop = rt_cache_seq_stop, .show = rt_cache_seq_show, }; static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } return NULL; } static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } (*pos)++; return NULL; } static void rt_cpu_seq_stop(struct seq_file *seq, void *v) { } static int rt_cpu_seq_show(struct seq_file *seq, void *v) { struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x\n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, st->in_slow_mc, st->in_no_route, st->in_brd, st->in_martian_dst, st->in_martian_src, 0, /* st->out_hit */ st->out_slow_tot, st->out_slow_mc, 0, /* st->gc_total */ 0, /* st->gc_ignored */ 0, /* st->gc_goal_miss */ 0, /* st->gc_dst_overflow */ 0, /* st->in_hlist_search */ 0 /* st->out_hlist_search */ ); return 0; } static const struct seq_operations rt_cpu_seq_ops = { .start = rt_cpu_seq_start, .next = rt_cpu_seq_next, .stop = rt_cpu_seq_stop, .show = rt_cpu_seq_show, }; #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; unsigned int i, j; dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); if (!dst) return -ENOMEM; for_each_possible_cpu(i) { src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); for (j = 0; j < 256; j++) { dst[j].o_bytes += src[j].o_bytes; dst[j].o_packets += src[j].o_packets; dst[j].i_bytes += src[j].i_bytes; dst[j].i_packets += src[j].i_packets; } } seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); kfree(dst); return 0; } #endif static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; pde = proc_create_seq("rt_cache", 0444, net->proc_net, &rt_cache_seq_ops); if (!pde) goto err1; pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_ops); if (!pde) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create_single("rt_acct", 0, net->proc_net, rt_acct_proc_show); if (!pde) goto err3; #endif return 0; #ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif err2: remove_proc_entry("rt_cache", net->proc_net); err1: return -ENOMEM; } static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); #ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, }; static int __init ip_rt_proc_init(void) { return register_pernet_subsys(&ip_rt_proc_ops); } #else static inline int ip_rt_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ static inline bool rt_is_expired(const struct rtable *rth) { return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; struct neighbour *n; rcu_read_lock(); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { n = ip_neigh_gw6(dev, &rt->rt_gw6); } else { __be32 pkey; pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr); n = ip_neigh_gw4(dev, pkey); } if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { pkey = (const __be32 *)&rt->rt_gw4; } else if (rt->rt_gw_family == AF_INET6) { return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6); } else if (!daddr || (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) { return; } __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } /* Hash tables of size 2048..262144 depending on RAM size. * Each bucket uses 8 bytes. */ static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; u32 *p_tstamp; u32 delta = 0; bucket = hash & ip_idents_mask; p_tstamp = ip_tstamps + bucket; p_id = ip_idents + bucket; old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = get_random_u32_below(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug * in UBSAN, and it has been fixed in GCC-8. */ return atomic_add_return(segs + delta, p_id) - segs; } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { u32 hash, id; /* Note the following code is not safe, but this is okay. */ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) get_random_bytes(&net->ipv4.ip_id_key, sizeof(net->ipv4.ip_id_key)); hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, int flow_flags) { __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, const struct sock *sk) { const struct net *net = dev_net(skb->dev); const struct iphdr *iph = ip_hdr(skb); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0); } static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); } static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, const struct sk_buff *skb) { if (skb) build_skb_flow_key(fl4, skb, sk); else build_sk_flow_key(fl4, sk); } static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) { struct rtable *rt; rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } } static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception __rcu **fnhe_p, **oldest_p; struct fib_nh_exception *fnhe, *oldest = NULL; for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); if (!fnhe) break; if (!oldest || time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; oldest_p = fnhe_p; } } fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); } static u32 fnhe_hashfun(__be32 daddr) { static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } } static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, __be32 gw, u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; u32 genid, hval; unsigned int i; int depth; genid = fnhe_genid(dev_net(nhc->nhc_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference(nhc->nhc_exceptions); if (!hash) { hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC); if (!hash) goto out_unlock; rcu_assign_pointer(nhc->nhc_exceptions, hash); } hash += hval; depth = 0; for (fnhe = rcu_dereference(hash->chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) break; depth++; } if (fnhe) { if (fnhe->fnhe_genid != genid) fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) fill_route_from_fnhe(rt, fnhe); rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) fill_route_from_fnhe(rt, fnhe); } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + get_random_u32_below(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); depth--; } fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); if (!fnhe) goto out_unlock; fnhe->fnhe_next = hash->chain; fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); rcu_assign_pointer(hash->chain, fnhe); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; for_each_possible_cpu(i) { struct rtable __rcu **prt; prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; } } fnhe->fnhe_stamp = jiffies; out_unlock: spin_unlock_bh(&fnhe_lock); } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct neighbour *n; struct net *net; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: break; default: return; } if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev)) goto reject_redirect; } else { if (inet_addr_type(net, new_gw) != RTN_UNICAST) goto reject_redirect; } n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, skb); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) { const struct iphdr *iph = (const struct iphdr *) skb->data; __be32 daddr = iph->daddr; __be32 saddr = iph->saddr; net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); } #endif ; } static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; rt = dst_rtable(dst); __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); struct dst_entry *ret = dst; if (rt) { if (dst->obsolete > 0) { ip_rt_put(rt); ret = NULL; } else if ((rt->rt_flags & RTCF_REDIRECTED) || rt->dst.expires) { ip_rt_put(rt); ret = NULL; } } return ret; } /* * Algorithm: * 1. The first ip_rt_redirect_number redirects are sent * with exponential backoff, then we stop sending them at all, * assuming that the host ignores our redirects. * 2. If we did not see packets requiring redirects * during ip_rt_redirect_silence, we assume that the host * forgot redirected route and start to send redirects again. * * This algorithm is much cheaper and more intelligent than dumb load limiting * in icmp.c. * * NOTE. Do not forget to inhibit load limiting for redirects (redundant) * and "frag. need" (breaks PMTU discovery) in icmp.c. */ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; struct net *net; int log_martians; int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; peer->n_redirects = 0; } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent * redirect. */ if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } out_put_peer: inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; SKB_DR(reason); bool send; int code; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) goto out; } in_dev = __in_dev_get_rcu(dev); /* IP on this device is disabled. */ if (!in_dev) goto out; net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: SKB_DR_SET(reason, IP_INADDRERRORS); __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } goto out; } switch (rt->dst.error) { case EINVAL: default: goto out; case EHOSTUNREACH: code = ICMP_HOST_UNREACH; break; case ENETUNREACH: code = ICMP_NET_UNREACH; SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { now = jiffies; peer->rate_tokens += now - peer->rate_last; if (peer->rate_tokens > ip_rt_error_burst) peer->rate_tokens = ip_rt_error_burst; peer->rate_last = now; if (peer->rate_tokens >= ip_rt_error_cost) peer->rate_tokens -= ip_rt_error_cost; else send = false; inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb_reason(skb, reason); return 0; } static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct net *net = dev_net(dst->dev); struct fib_result res; bool lock = false; u32 old_mtu; if (ip_mtu_locked(dst)) return; old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) return; rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } rcu_read_unlock(); } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct rtable *rt = dst_rtable(dst); struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); /* Don't make lookup fail for bridged encapsulations */ if (skb && netif_is_any_bridge_port(skb->dev)) fl4.flowi4_oif = 0; __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0); if (!fl4.flowi4_mark) fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; bool new = false; struct net *net = sock_net(sk); bh_lock_sock(sk); if (!ip_sk_accept_pmtu(sk)) goto out; odst = sk_dst_get(sk); if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = dst_rtable(odst); if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } __ip_rt_update_pmtu(dst_rtable(xfrm_dst_path(&rt->dst)), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } if (new) sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = dst_rtable(dst); /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct net_device *dev; struct ip_options opt; int res; /* Recompile ip options since IPCB may not be valid anymore. * Also check we have a reasonable ipv4 header. */ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; memset(&opt, 0, sizeof(opt)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) return; } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); } static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; } /* * We do not cache source address of outgoing interface, * because it is used only by IP RR, TS and SRR options, * so that it out of fast path. * * BTW remember: "addr" is allowed to be not aligned * in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; if (rt_is_output_route(rt)) src = ip_hdr(skb)->saddr; else { struct fib_result res; struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = RT_TOS(iph->tos), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, }; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); } #ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) rt->dst.tclassid |= tag & 0xFFFF; if (!(rt->dst.tclassid & 0xFFFF0000)) rt->dst.tclassid |= tag & 0xFFFF0000; } #endif static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, net->ipv4.ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { return ip_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ipv4_mtu); static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe, __rcu **fnhe_p; u32 hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference_protected(nhc->nhc_exceptions, lockdep_is_held(&fnhe_lock)); hash += hval; fnhe_p = &hash->chain; fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); while (fnhe) { if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); /* set fnhe_daddr to 0 to ensure it won't bind with * new dsts in rt_bind_exception(). */ fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; } fnhe_p = &fnhe->fnhe_next; fnhe = rcu_dereference_protected(fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)); } spin_unlock_bh(&fnhe_lock); } static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions); struct fib_nh_exception *fnhe; u32 hval; if (!hash) return NULL; hval = fnhe_hashfun(daddr); for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) { if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) { ip_del_fnhe(nhc, daddr); break; } return fnhe; } } return NULL; } /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device */ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { struct fib_nh_common *nhc = res->nhc; struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; u32 mtu = 0; if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; if (likely(!mtu)) { struct fib_nh_exception *fnhe; fnhe = find_exception(nhc, daddr); if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) mtu = fnhe->fnhe_pmtu; } if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { bool ret = false; spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { struct rtable __rcu **porig; struct rtable *orig; int genid = fnhe_genid(dev_net(rt->dst.dev)); if (rt_is_input_route(rt)) porig = &fnhe->fnhe_rth_input; else porig = &fnhe->fnhe_rth_output; orig = rcu_dereference(*porig); if (fnhe->fnhe_genid != genid) { fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } fill_route_from_fnhe(rt, fnhe); if (!rt->rt_gw4) { rt->rt_gw4 = daddr; rt->rt_gw_family = AF_INET; } if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { dst_dev_put(&orig->dst); dst_release(&orig->dst); } ret = true; } fnhe->fnhe_stamp = jiffies; } spin_unlock_bh(&fnhe_lock); return ret; } static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) { struct rtable *orig, *prev, **p; bool ret = true; if (rt_is_input_route(rt)) { p = (struct rtable **)&nhc->nhc_rth_input; } else { p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } orig = *p; /* hold dst before doing cmpxchg() to avoid race condition * on this dst */ dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { dst_release(&rt->dst); ret = false; } return ret; } struct uncached_list { spinlock_t lock; struct list_head head; struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void ipv4_dst_destroy(struct dst_entry *dst) { ip_dst_metrics_put(dst); rt_del_uncached_list(dst_rtable(dst)); } void rt_flush_dev(struct net_device *dev) { struct rtable *rt, *safe; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); list_move(&rt->dst.rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); } } static bool rt_cache_valid(const struct rtable *rt) { return rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag, const bool do_cache) { bool cached = false; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) rt->rt_gw4 = nhc->nhc_gw.ipv4; else rt->rt_gw6 = nhc->nhc_gw.ipv6; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); rt->dst.tclassid = nh->nh_tclassid; } #endif rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) cached = rt_cache_route(nhc, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or * FIB nexthop have the DST_NOCACHE bit clear. * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ if (!rt->rt_gw4) { rt->rt_gw_family = AF_INET; rt->rt_gw4 = daddr; } rt_add_uncached_list(rt); } } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool noxfrm) { struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); rt->rt_flags = flags; rt->rt_type = type; rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; rt->dst.output = ip_output; if (flags & RTCF_LOCAL) rt->dst.input = ip_local_deliver; } return rt; } EXPORT_SYMBOL(rt_dst_alloc); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) { struct rtable *new_rt; new_rt = dst_alloc(&ipv4_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, rt->dst.flags); if (new_rt) { new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); new_rt->rt_flags = rt->rt_flags; new_rt->rt_type = rt->rt_type; new_rt->rt_is_input = rt->rt_is_input; new_rt->rt_iif = rt->rt_iif; new_rt->rt_pmtu = rt->rt_pmtu; new_rt->rt_mtu_locked = rt->rt_mtu_locked; new_rt->rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; new_rt->dst.input = rt->dst.input; new_rt->dst.output = rt->dst.output; new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); } return new_rt; } EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag) { int err; /* Primary sanity checks. */ if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, itag); if (err < 0) return err; } return 0; } /* called in rcu_read_lock() section */ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; u32 itag = 0; int err; err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); if (err) return err; if (our) flags |= RTCF_LOCAL; if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, false); if (!rth) return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; rth->rt_is_input= 1; #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, __be32 daddr, __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) { /* * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ pr_warn("martian source %pI4 from %pI4, on dev %s\n", &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { print_hex_dump(KERN_WARNING, "ll header: ", DUMP_PREFIX_OFFSET, 16, 1, skb_mac_header(skb), dev->hard_header_len, false); } } #endif } /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); goto cleanup; } do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && skb->protocol == htons(ETH_P_IP)) { __be32 gw; gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; if (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, gw)) IPCB(skb)->flags |= IPSKB_DOREDIRECT; } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. * * Proxy arp feature have been extended to allow, ARP * replies back to the same interface, to support * Private VLAN switch technologies. See arp.c. */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } } if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; goto cleanup; } rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; cleanup: return err; } #ifdef CONFIG_IP_ROUTE_MULTIPATH /* To make ICMP packets follow the right flow, the multipath hash is * calculated from the inner IP addresses. */ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; if (likely(outer_iph->protocol != IPPROTO_ICMP)) goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmp_is_err(icmph->type)) goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; out: hash_keys->addrs.v4addrs.src = key_iph->saddr; hash_keys->addrs.v4addrs.dst = key_iph->daddr; } static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return flow_hash_from_keys(&hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return flow_hash_from_keys(&hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = fl4->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = fl4->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl4->flowi4_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl4->fl4_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; return flow_hash_from_keys(&hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash = 0; switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (skb) { ip_multipath_l3_keys(skb, &hash_keys); } else { hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = flow_hash_from_keys(&hash_keys); break; case 1: /* skb is currently provided only when forwarding */ if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); /* skb is currently provided only when forwarding */ if (skb) { struct flow_keys keys; skb_flow_dissect_flow_keys(skb, &keys, 0); /* Inner can be v4 or v6 */ if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; hash_keys.tags.flow_label = keys.tags.flow_label; hash_keys.basic.ip_proto = keys.basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; ip_multipath_l3_keys(skb, &hash_keys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = flow_hash_from_keys(&hash_keys); break; case 3: if (skb) mhash = fib_multipath_custom_hash_skb(net, skb); else mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif /* create a routing cache entry */ return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* Implements all the saddr-related checks as ip_route_input_slow(), * assuming daddr is valid and the destination is not a local broadcast one. * Uses the provided hint instead of performing a route lookup. */ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, const struct sk_buff *hint) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); int err = -EINVAL; u32 tag = 0; if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; if (ipv4_is_zeronet(saddr)) goto martian_source; if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; tos &= IPTOS_RT_MASK; err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); if (err < 0) goto martian_source; skip_validate_source: skb_dst_copy(skb, hint); return 0; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); return err; } /* get device for dst_alloc with local routes */ static struct net_device *ip_rt_get_dev(struct net *net, const struct fib_result *res) { struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; struct net_device *dev = NULL; if (nhc) dev = l3mdev_master_dev_rcu(nhc->nhc_dev); return dev ? : net->loopback_dev; } /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. * Changes in the enforced policies must be applied also to * ip_route_use_hint(). * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. * called with rcu_read_lock() */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; struct flowi4 fl4; bool do_cache = true; /* IP on this device is disabled. */ if (!in_dev) goto out; /* Check for the most weird martians, which can be not detected * by fib_lookup. */ tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; else fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; res->fi = NULL; res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ if (ipv4_is_zeronet(saddr)) goto martian_source; if (ipv4_is_zeronet(daddr)) goto martian_destination; /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_destination; } else if (ipv4_is_loopback(saddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; } /* * Now we are ready to route packet. */ fl4.flowi4_l3mdev = 0; fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; } else { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) { err = -EHOSTUNREACH; goto no_route; } if (res->type != RTN_UNICAST) goto martian_destination; make_route: err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: if (skb->protocol != htons(ETH_P_IP)) goto e_inval; if (!ipv4_is_zeronet(saddr)) { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; } flags |= RTCF_BROADCAST; res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; goto out; } } rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, false); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } if (unlikely(!rt_cache_route(nhc, rth))) rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); err = 0; goto out; no_route: RT_CACHE_STAT_INC(in_no_route); res->type = RTN_UNREACHABLE; res->fi = NULL; res->table = NULL; goto local_input; /* * Do not cache martian addresses: they should be logged (RFC1812) */ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif e_inval: err = -EINVAL; goto out; e_nobufs: err = -ENOBUFS; goto out; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } /* called with rcu_read_lock held */ static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. * The problem was that too many Ethernet cards have broken/missing * hardware multicast filters :-( As result the host on multicasting * network acquires a lot of useless route cache entries, sort of * SDR messages from all the world. Now we try to get rid of them. * Really, provided software IP multicast filter is organized * reasonably (at least, hashed), it does not result in a slowdown * comparing with route cache reject entries. * Note, that multicast routers are not affected, because * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; int err = -EINVAL; if (!in_dev) return err; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); /* check l3 master if no match yet */ if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); if (l3_in_dev) our = ip_check_mc_rcu(l3_in_dev, daddr, saddr, ip_hdr(skb)->protocol); } if (our #ifdef CONFIG_IP_MROUTE || (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) #endif ) { err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } return err; } return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { struct fib_result res; int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); return err; } EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) type = RTN_MULTICAST; else if (ipv4_is_zeronet(fl4->daddr)) return ERR_PTR(-EINVAL); if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; else do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. */ if (fi && res->prefixlen < 4) fi = NULL; } else if ((type == RTN_LOCAL) && (orig_oif != 0) && (orig_oif != dev_out->ifindex)) { /* For local routes that require a particular output interface * we do not want to cache the result. Caching the result * causes incorrect behaviour when there are multiple source * addresses on the interface, the end result being that if the * intended recipient is waiting on that interface for the * packet he won't receive it because it will be delivered on * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct rtable __rcu **prth; fnhe = find_exception(nhc, fl4->daddr); if (!do_cache) goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && !(nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } rth = rcu_dereference(*prth); if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } add: rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_ORCONF(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; RT_CACHE_STAT_INC(out_slow_tot); if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mc_output; } } #endif } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); lwtunnel_set_redirect(&rth->dst); return rth; } /* * Major route resolver routine. */ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, .table = NULL, .tclassid = 0, }; struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos &= IPTOS_RT_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); rcu_read_unlock(); return rth; } EXPORT_SYMBOL_GPL(ip_route_output_key_hash); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, struct fib_result *res, const struct sk_buff *skb) { struct net_device *dev_out = NULL; int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; int err; if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || ipv4_is_zeronet(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. * It was wrong for two reasons: * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr * is assigned to multiple interfaces. * 2. Moreover, we are allowed to send packets with saddr * of another iface. --ANK */ if (fl4->flowi4_oif == 0 && (ipv4_is_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); if (!dev_out) goto out; /* Special hack: user can direct multicasts * and limited broadcast via necessary interface * without fiddling with IP_MULTICAST_IF or IP_PKTINFO. * This hack is not just for fun, it allows * vic,vat and friends to work. * They bind socket to loopback, set ttl to zero * and expect that it will work. * From the viewpoint of routing cache they are broken, * because we are not allowed to build multicast path * with loopback source addr (look, routing cache * cannot know, that ttl is zero, so that packet * will not leave this host and route is valid). * Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; goto make_route; } if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { rth = ERR_PTR(-ENETUNREACH); goto out; } if (ipv4_is_local_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr) || fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); goto make_route; } if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); else if (!fl4->daddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } } if (!fl4->daddr) { fl4->daddr = fl4->saddr; if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } err = fib_lookup(net, fl4, res, 0); if (err) { res->fi = NULL; res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) { /* Apparently, routing tables are wrong. Assume, * that the destination is on link. * * WHY? DW. * Because we are allowed to send to iface * even if it has NO routes and NO assigned * addresses. When oif is specified, routing * tables are looked up with only one purpose: * to catch if destination is gatewayed, rather than * direct. Moreover, if MSG_DONTROUTE is set, * we send packet, ignoring both routing tables * and ifaddr state. --ANK * * * We could make it even if oif is unknown, * likely IPv6, but we do not. */ if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } if (res->type == RTN_LOCAL) { if (!fl4->saddr) { if (res->fi->fib_prefsrc) fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; /* make sure orig_oif points to fib result device even * though packet rx/tx happens over loopback or l3mdev */ orig_oif = FIB_RES_OIF(*res); fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: return rth; } static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .default_advmss = ipv4_default_advmss, .neigh_lookup = ipv4_neigh_lookup, .check = dst_blackhole_check, .cow_metrics = dst_blackhole_cow_metrics, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rtable *ort = dst_rtable(dst_orig); struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; new->dev = net->loopback_dev; netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; } dst_release(dst_orig); return rt ? &rt->dst : ERR_PTR(-ENOMEM); } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); if (IS_ERR(rt)) return rt; if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; rt = dst_rtable(xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0)); } return rt; } EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; u32 error; u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; if (rt->dst.lwtstate && lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway) { if (rt->rt_gw_family == AF_INET && nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; } else if (rt->rt_gw_family == AF_INET6) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &rt->rt_gw6, alen); } } expires = rt->dst.expires; if (expires) { unsigned long now = jiffies; if (time_before(now, expires)) expires -= now; else expires = 0; } memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rt->rt_mtu_locked && expires) metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (fl4) { if (fl4->flowi4_mark && nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && nla_put_u32(skb, RTA_UID, from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) goto nla_put_failure; if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); if (err <= 0) { if (err == 0) return 0; goto nla_put_failure; } } else #endif if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } } error = rt->dst.error; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, int *fa_index, int fa_start, unsigned int flags) { int i; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference(bucket[i].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { struct rtable *rt; int err; if (*fa_index < fa_start) goto next; if (fnhe->fnhe_genid != genid) goto next; if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) goto next; rt = rcu_dereference(fnhe->fnhe_rth_input); if (!rt) rt = rcu_dereference(fnhe->fnhe_rth_output); if (!rt) goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) return err; next: (*fa_index)++; } } return 0; } int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); struct fnhe_hash_bucket *bucket; int err; if (nhc->nhc_flags & RTNH_F_DEAD) continue; rcu_read_lock(); bucket = rcu_dereference(nhc->nhc_exceptions); err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, genid, fa_index, fa_start, flags); rcu_read_unlock(); if (err) return err; } return 0; } static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) { struct sk_buff *skb; struct iphdr *iph; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return NULL; /* Reserve room for dummy headers, this skb can pass * through good chunk of routing engine. */ skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); iph = skb_put(skb, sizeof(struct iphdr)); iph->protocol = ip_proto; iph->saddr = src; iph->daddr = dst; iph->version = 0x4; iph->frag_off = 0; iph->ihl = 0x5; skb_set_transport_header(skb, skb->len); switch (iph->protocol) { case IPPROTO_UDP: { struct udphdr *udph; udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } case IPPROTO_TCP: { struct tcphdr *tcph; tcph = skb_put_zero(skb, sizeof(struct tcphdr)); tcph->source = sport; tcph->dest = dport; tcph->doff = sizeof(struct tcphdr) / 4; tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), src, dst, 0); break; } case IPPROTO_ICMP: { struct icmphdr *icmph; icmph = skb_put_zero(skb, sizeof(struct icmphdr)); icmph->type = ICMP_ECHO; icmph->code = 0; } } return skb; } static int inet_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_NOTIFY | RTM_F_LOOKUP_TABLE | RTM_F_FIB_MATCH)) { NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_IIF: case RTA_OIF: case RTA_SRC: case RTA_DST: case RTA_IP_PROTO: case RTA_SPORT: case RTA_DPORT: case RTA_MARK: case RTA_UID: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); return -EINVAL; } } return 0; } static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; u32 table_id = RT_TABLE_MAIN; __be16 sport = 0, dport = 0; struct fib_result res = {}; u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; struct sk_buff *skb; struct rtmsg *rtm; struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; kuid_t uid; u32 iif; int err; int mark; err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else uid = (iif ? INVALID_UID : current_uid()); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &ip_proto, AF_INET, extack); if (err) return err; } if (tb[RTA_SPORT]) sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) dport = nla_get_be16(tb[RTA_DPORT]); skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); if (!skb) return -ENOBUFS; fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) fl4.fl4_sport = sport; if (dport) fl4.fl4_dport = dport; fl4.flowi4_proto = ip_proto; rcu_read_lock(); if (iif) { struct net_device *dev; dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_rcu; } fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos & IPTOS_RT_MASK, dev, &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { fl4.flowi4_iif = LOOPBACK_IFINDEX; skb->dev = net->loopback_dev; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); else skb_dst_set(skb, &rt->dst); } if (err) goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; /* reset skb for netlink reply msg */ skb_trim(skb, 0); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { struct fib_rt_info fri; if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } fri.fi = res.fi; fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos); fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; fri.offload_failed = 0; if (res.fa_head) { struct fib_alias *fa; hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { u8 slen = 32 - fri.dst_len; if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && fa->fa_dscp == fri.dscp && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); break; } } } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: return err; errout_rcu: rcu_read_unlock(); kfree_skb(skb); goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; if (write) { rt_cache_flush(net); fnhe_genid_bump(net); return 0; } return -EINVAL; } static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static const char ipv4_route_flush_procname[] = "flush"; static struct ctl_table ipv4_route_netns_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, { .procname = "min_pmtu", .data = &init_net.ipv4.ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &ip_min_valid_pmtu, }, { .procname = "mtu_expires", .data = &init_net.ipv4.ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv4.ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; size_t table_size = ARRAY_SIZE(ipv4_route_netns_table); tbl = ipv4_route_netns_table; if (!net_eq(net, &init_net)) { int i; tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL); if (!tbl) goto err_dup; /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { if (tbl[0].procname != ipv4_route_flush_procname) table_size = 0; } /* Update the variables to point into the current struct net * except for the first element flush */ for (i = 1; i < table_size; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl_sz(net, "net/ipv4/route", tbl, table_size); if (!net->ipv4.route_hdr) goto err_reg; return 0; err_reg: if (tbl != ipv4_route_netns_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_route_net_exit(struct net *net) { const struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); BUG_ON(tbl == ipv4_route_netns_table); kfree(tbl); } static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, }; #endif static __net_init int netns_ip_rt_init(struct net *net) { /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } static struct pernet_operations __net_initdata ip_rt_ops = { .init = netns_ip_rt_init, }; static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; static int __net_init ipv4_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv4.peers = bp; return 0; } static void __net_exit ipv4_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv4.peers; net->ipv4.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, }; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_IP_ROUTE_CLASSID */ int __init ip_rt_init(void) { void *idents_hash; int cpu; /* For modern hosts, this will use 2 MB of memory */ idents_hash = alloc_large_system_hash("IP idents", sizeof(*ip_idents) + sizeof(*ip_tstamps), 0, 16, /* one bucket per 64 KB */ HASH_ZERO, NULL, &ip_idents_mask, 2048, 256*1024); ip_idents = idents_hash; get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif ipv4_dst_ops.kmem_cachep = KMEM_CACHE(rtable, SLAB_HWCACHE_ALIGN | SLAB_PANIC); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; if (dst_entries_init(&ipv4_dst_ops) < 0) panic("IP: failed to allocate ipv4_dst_ops counter\n"); if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); ipv4_dst_ops.gc_thresh = ~0; ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, RTNL_FLAG_DOIT_UNLOCKED); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&ip_rt_ops); register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; } #ifdef CONFIG_SYSCTL /* * We really need to sanitize the damn ipv4 init order, then all * this nonsense will go away. */ void __init ip_static_sysctl_init(void) { register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif |
| 1 4 4 4 6 16 21 20 2 4 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/ipc/util.h * Copyright (C) 1999 Christoph Rohland * * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com> * namespaces support. 2006 OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> */ #ifndef _IPC_UTIL_H #define _IPC_UTIL_H #include <linux/unistd.h> #include <linux/err.h> #include <linux/ipc_namespace.h> #include <linux/pid.h> /* * The IPC ID contains 2 separate numbers - index and sequence number. * By default, * bits 0-14: index (32k, 15 bits) * bits 15-30: sequence number (64k, 16 bits) * * When IPCMNI extension mode is turned on, the composition changes: * bits 0-23: index (16M, 24 bits) * bits 24-30: sequence number (128, 7 bits) */ #define IPCMNI_SHIFT 15 #define IPCMNI_EXTEND_SHIFT 24 #define IPCMNI_EXTEND_MIN_CYCLE (RADIX_TREE_MAP_SIZE * RADIX_TREE_MAP_SIZE) #define IPCMNI (1 << IPCMNI_SHIFT) #define IPCMNI_EXTEND (1 << IPCMNI_EXTEND_SHIFT) #ifdef CONFIG_SYSVIPC_SYSCTL extern int ipc_mni; extern int ipc_mni_shift; extern int ipc_min_cycle; #define ipcmni_seq_shift() ipc_mni_shift #define IPCMNI_IDX_MASK ((1 << ipc_mni_shift) - 1) #else /* CONFIG_SYSVIPC_SYSCTL */ #define ipc_mni IPCMNI #define ipc_min_cycle ((int)RADIX_TREE_MAP_SIZE) #define ipcmni_seq_shift() IPCMNI_SHIFT #define IPCMNI_IDX_MASK ((1 << IPCMNI_SHIFT) - 1) #endif /* CONFIG_SYSVIPC_SYSCTL */ void sem_init(void); void msg_init(void); void shm_init(void); struct ipc_namespace; struct pid_namespace; #ifdef CONFIG_POSIX_MQUEUE extern void mq_clear_sbinfo(struct ipc_namespace *ns); #else static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { } #endif #ifdef CONFIG_SYSVIPC void sem_init_ns(struct ipc_namespace *ns); int msg_init_ns(struct ipc_namespace *ns); void shm_init_ns(struct ipc_namespace *ns); void sem_exit_ns(struct ipc_namespace *ns); void msg_exit_ns(struct ipc_namespace *ns); void shm_exit_ns(struct ipc_namespace *ns); #else static inline void sem_init_ns(struct ipc_namespace *ns) { } static inline int msg_init_ns(struct ipc_namespace *ns) { return 0; } static inline void shm_init_ns(struct ipc_namespace *ns) { } static inline void sem_exit_ns(struct ipc_namespace *ns) { } static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif /* * Structure that holds the parameters needed by the ipc operations * (see after) */ struct ipc_params { key_t key; int flg; union { size_t size; /* for shared memories */ int nsems; /* for semaphores */ } u; /* holds the getnew() specific param */ }; /* * Structure that holds some ipc operations. This structure is used to unify * the calls to sys_msgget(), sys_semget(), sys_shmget() * . routine to call to create a new ipc object. Can be one of newque, * newary, newseg * . routine to call to check permissions for a new ipc object. * Can be one of security_msg_associate, security_sem_associate, * security_shm_associate * . routine to call for an extra check if needed */ struct ipc_ops { int (*getnew)(struct ipc_namespace *, struct ipc_params *); int (*associate)(struct kern_ipc_perm *, int); int (*more_checks)(struct kern_ipc_perm *, struct ipc_params *); }; struct seq_file; struct ipc_ids; void ipc_init_ids(struct ipc_ids *ids); #ifdef CONFIG_PROC_FS void __init ipc_init_proc_interface(const char *path, const char *header, int ids, int (*show)(struct seq_file *, void *)); struct pid_namespace *ipc_seq_pid_ns(struct seq_file *); #else #define ipc_init_proc_interface(path, header, ids, show) do {} while (0) #endif #define IPC_SEM_IDS 0 #define IPC_MSG_IDS 1 #define IPC_SHM_IDS 2 #define ipcid_to_idx(id) ((id) & IPCMNI_IDX_MASK) #define ipcid_to_seqx(id) ((id) >> ipcmni_seq_shift()) #define ipcid_seq_max() (INT_MAX >> ipcmni_seq_shift()) /* must be called with ids->rwsem acquired for writing */ int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int); /* must be called with both locks acquired. */ void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with both locks acquired. */ void ipc_set_key_private(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with ipcp locked */ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); /** * ipc_get_maxidx - get the highest assigned index * @ids: ipc identifier set * * The function returns the highest assigned index for @ids. The function * doesn't scan the idr tree, it uses a cached value. * * Called with ipc_ids.rwsem held for reading. */ static inline int ipc_get_maxidx(struct ipc_ids *ids) { if (ids->in_use == 0) return -1; if (ids->in_use == ipc_mni) return ipc_mni - 1; return ids->max_idx; } /* * For allocation that need to be freed by RCU. * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. * * refcount is initialized by ipc_addid(), before that point call_rcu() * must be used. */ bool ipc_rcu_getref(struct kern_ipc_perm *ptr); void ipc_rcu_putref(struct kern_ipc_perm *ptr, void (*func)(struct rcu_head *head)); struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out); void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out); int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out); struct kern_ipc_perm *ipcctl_obtain_check(struct ipc_namespace *ns, struct ipc_ids *ids, int id, int cmd, struct ipc64_perm *perm, int extra_perm); static inline void ipc_update_pid(struct pid **pos, struct pid *pid) { struct pid *old = *pos; if (old != pid) { *pos = get_pid(pid); put_pid(old); } } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION int ipc_parse_version(int *cmd); #endif extern void free_msg(struct msg_msg *msg); extern struct msg_msg *load_msg(const void __user *src, size_t len); extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst); extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len); static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int id) { return ipcid_to_seqx(id) != ipcp->seq; } static inline void ipc_lock_object(struct kern_ipc_perm *perm) { spin_lock(&perm->lock); } static inline void ipc_unlock_object(struct kern_ipc_perm *perm) { spin_unlock(&perm->lock); } static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm) { assert_spin_locked(&perm->lock); } static inline void ipc_unlock(struct kern_ipc_perm *perm) { ipc_unlock_object(perm); rcu_read_unlock(); } /* * ipc_valid_object() - helper to sort out IPC_RMID races for codepaths * where the respective ipc_ids.rwsem is not being held down. * Checks whether the ipc object is still around or if it's gone already, as * ipc_rmid() may have already freed the ID while the ipc lock was spinning. * Needs to be called with kern_ipc_perm.lock held -- exception made for one * checkpoint case at sys_semtimedop() as noted in code commentary. */ static inline bool ipc_valid_object(struct kern_ipc_perm *perm) { return !perm->deleted; } struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id); int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, const struct ipc_ops *ops, struct ipc_params *params); void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)); static inline int sem_check_semmni(struct ipc_namespace *ns) { /* * Check semmni range [0, ipc_mni] * semmni is the last element of sem_ctls[4] array */ return ((ns->sem_ctls[3] < 0) || (ns->sem_ctls[3] > ipc_mni)) ? -ERANGE : 0; } #ifdef CONFIG_COMPAT #include <linux/compat.h> struct compat_ipc_perm { key_t key; __compat_uid_t uid; __compat_gid_t gid; __compat_uid_t cuid; __compat_gid_t cgid; compat_mode_t mode; unsigned short seq; }; void to_compat_ipc_perm(struct compat_ipc_perm *, struct ipc64_perm *); void to_compat_ipc64_perm(struct compat_ipc64_perm *, struct ipc64_perm *); int get_compat_ipc_perm(struct ipc64_perm *, struct compat_ipc_perm __user *); int get_compat_ipc64_perm(struct ipc64_perm *, struct compat_ipc64_perm __user *); static inline int compat_ipc_parse_version(int *cmd) { int version = *cmd & IPC_64; *cmd &= ~IPC_64; return version; } long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg); long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr); long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr); #endif #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_TSTAMP_H #define _NF_CONNTRACK_TSTAMP_H #include <net/net_namespace.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> struct nf_conn_tstamp { u_int64_t start; u_int64_t stop; }; static inline struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); #else return NULL; #endif } static inline struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP struct net *net = nf_ct_net(ct); if (!net->ct.sysctl_tstamp) return NULL; return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); #else return NULL; #endif }; #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP void nf_conntrack_tstamp_pernet_init(struct net *net); #else static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {} #endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ #endif /* _NF_CONNTRACK_TSTAMP_H */ |
| 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 2 2 2 2 2 5 1 1 1 4 2 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * Added support for a Unix98-style ptmx device. * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998 * */ #include <linux/module.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/fcntl.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/major.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/device.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/devpts_fs.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/ioctl.h> #include <linux/compat.h> #include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP # define tty_debug_hangup(tty, f, args...) tty_debug(tty, f, ##args) #else # define tty_debug_hangup(tty, f, args...) do {} while (0) #endif #ifdef CONFIG_UNIX98_PTYS static struct tty_driver *ptm_driver; static struct tty_driver *pts_driver; static DEFINE_MUTEX(devpts_mutex); #endif static void pty_close(struct tty_struct *tty, struct file *filp) { if (tty->driver->subtype == PTY_TYPE_MASTER) WARN_ON(tty->count > 1); else { if (tty_io_error(tty)) return; if (tty->count > 2) return; } set_bit(TTY_IO_ERROR, &tty->flags); wake_up_interruptible(&tty->read_wait); wake_up_interruptible(&tty->write_wait); spin_lock_irq(&tty->ctrl.lock); tty->ctrl.packet = false; spin_unlock_irq(&tty->ctrl.lock); /* Review - krefs on tty_link ?? */ if (!tty->link) return; set_bit(TTY_OTHER_CLOSED, &tty->link->flags); wake_up_interruptible(&tty->link->read_wait); wake_up_interruptible(&tty->link->write_wait); if (tty->driver->subtype == PTY_TYPE_MASTER) { set_bit(TTY_OTHER_CLOSED, &tty->flags); #ifdef CONFIG_UNIX98_PTYS if (tty->driver == ptm_driver) { mutex_lock(&devpts_mutex); if (tty->link->driver_data) devpts_pty_kill(tty->link->driver_data); mutex_unlock(&devpts_mutex); } #endif tty_vhangup(tty->link); } } /* * The unthrottle routine is called by the line discipline to signal * that it can receive more characters. For PTY's, the TTY_THROTTLED * flag is always set, to force the line discipline to always call the * unthrottle routine when there are fewer than TTY_THRESHOLD_UNTHROTTLE * characters in the queue. This is necessary since each time this * happens, we need to wake up any sleeping processes that could be * (1) trying to send data to the pty, or (2) waiting in wait_until_sent() * for the pty buffer to be drained. */ static void pty_unthrottle(struct tty_struct *tty) { tty_wakeup(tty->link); set_bit(TTY_THROTTLED, &tty->flags); } /** * pty_write - write to a pty * @tty: the tty we write from * @buf: kernel buffer of data * @c: bytes to write * * Our "hardware" write method. Data is coming from the ldisc which * may be in a non sleeping state. We simply throw this at the other * end of the link as if we were an IRQ handler receiving stuff for * the other side of the pty/tty pair. */ static ssize_t pty_write(struct tty_struct *tty, const u8 *buf, size_t c) { struct tty_struct *to = tty->link; if (tty->flow.stopped || !c) return 0; return tty_insert_flip_string_and_push_buffer(to->port, buf, c); } /** * pty_write_room - write space * @tty: tty we are writing from * * Report how many bytes the ldisc can send into the queue for * the other device. */ static unsigned int pty_write_room(struct tty_struct *tty) { if (tty->flow.stopped) return 0; return tty_buffer_space_avail(tty->link->port); } /* Set the lock flag on a pty */ static int pty_set_lock(struct tty_struct *tty, int __user *arg) { int val; if (get_user(val, arg)) return -EFAULT; if (val) set_bit(TTY_PTY_LOCK, &tty->flags); else clear_bit(TTY_PTY_LOCK, &tty->flags); return 0; } static int pty_get_lock(struct tty_struct *tty, int __user *arg) { int locked = test_bit(TTY_PTY_LOCK, &tty->flags); return put_user(locked, arg); } /* Set the packet mode on a pty */ static int pty_set_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode; if (get_user(pktmode, arg)) return -EFAULT; spin_lock_irq(&tty->ctrl.lock); if (pktmode) { if (!tty->ctrl.packet) { tty->link->ctrl.pktstatus = 0; smp_mb(); tty->ctrl.packet = true; } } else tty->ctrl.packet = false; spin_unlock_irq(&tty->ctrl.lock); return 0; } /* Get the packet mode of a pty */ static int pty_get_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode = tty->ctrl.packet; return put_user(pktmode, arg); } /* Send a signal to the slave */ static int pty_signal(struct tty_struct *tty, int sig) { struct pid *pgrp; if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP) return -EINVAL; if (tty->link) { pgrp = tty_get_pgrp(tty->link); if (pgrp) kill_pgrp(pgrp, sig, 1); put_pid(pgrp); } return 0; } static void pty_flush_buffer(struct tty_struct *tty) { struct tty_struct *to = tty->link; if (!to) return; tty_buffer_flush(to, NULL); if (to->ctrl.packet) { spin_lock_irq(&tty->ctrl.lock); tty->ctrl.pktstatus |= TIOCPKT_FLUSHWRITE; wake_up_interruptible(&to->read_wait); spin_unlock_irq(&tty->ctrl.lock); } } static int pty_open(struct tty_struct *tty, struct file *filp) { if (!tty || !tty->link) return -ENODEV; if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) goto out; if (test_bit(TTY_PTY_LOCK, &tty->link->flags)) goto out; if (tty->driver->subtype == PTY_TYPE_SLAVE && tty->link->count != 1) goto out; clear_bit(TTY_IO_ERROR, &tty->flags); clear_bit(TTY_OTHER_CLOSED, &tty->link->flags); set_bit(TTY_THROTTLED, &tty->flags); return 0; out: set_bit(TTY_IO_ERROR, &tty->flags); return -EIO; } static void pty_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { /* See if packet mode change of state. */ if (tty->link && tty->link->ctrl.packet) { int extproc = (old_termios->c_lflag & EXTPROC) | L_EXTPROC(tty); int old_flow = ((old_termios->c_iflag & IXON) && (old_termios->c_cc[VSTOP] == '\023') && (old_termios->c_cc[VSTART] == '\021')); int new_flow = (I_IXON(tty) && STOP_CHAR(tty) == '\023' && START_CHAR(tty) == '\021'); if ((old_flow != new_flow) || extproc) { spin_lock_irq(&tty->ctrl.lock); if (old_flow != new_flow) { tty->ctrl.pktstatus &= ~(TIOCPKT_DOSTOP | TIOCPKT_NOSTOP); if (new_flow) tty->ctrl.pktstatus |= TIOCPKT_DOSTOP; else tty->ctrl.pktstatus |= TIOCPKT_NOSTOP; } if (extproc) tty->ctrl.pktstatus |= TIOCPKT_IOCTL; spin_unlock_irq(&tty->ctrl.lock); wake_up_interruptible(&tty->link->read_wait); } } tty->termios.c_cflag &= ~(CSIZE | PARENB); tty->termios.c_cflag |= (CS8 | CREAD); } /** * pty_resize - resize event * @tty: tty being resized * @ws: window size being set. * * Update the termios variables and send the necessary signals to * peform a terminal resize correctly */ static int pty_resize(struct tty_struct *tty, struct winsize *ws) { struct pid *pgrp, *rpgrp; struct tty_struct *pty = tty->link; /* For a PTY we need to lock the tty side */ mutex_lock(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; /* Signal the foreground process group of both ptys */ pgrp = tty_get_pgrp(tty); rpgrp = tty_get_pgrp(pty); if (pgrp) kill_pgrp(pgrp, SIGWINCH, 1); if (rpgrp != pgrp && rpgrp) kill_pgrp(rpgrp, SIGWINCH, 1); put_pid(pgrp); put_pid(rpgrp); tty->winsize = *ws; pty->winsize = *ws; /* Never used so will go away soon */ done: mutex_unlock(&tty->winsize_mutex); return 0; } /** * pty_start - start() handler * pty_stop - stop() handler * @tty: tty being flow-controlled * * Propagates the TIOCPKT status to the master pty. * * NB: only the master pty can be in packet mode so only the slave * needs start()/stop() handlers */ static void pty_start(struct tty_struct *tty) { unsigned long flags; if (tty->link && tty->link->ctrl.packet) { spin_lock_irqsave(&tty->ctrl.lock, flags); tty->ctrl.pktstatus &= ~TIOCPKT_STOP; tty->ctrl.pktstatus |= TIOCPKT_START; spin_unlock_irqrestore(&tty->ctrl.lock, flags); wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } static void pty_stop(struct tty_struct *tty) { unsigned long flags; if (tty->link && tty->link->ctrl.packet) { spin_lock_irqsave(&tty->ctrl.lock, flags); tty->ctrl.pktstatus &= ~TIOCPKT_START; tty->ctrl.pktstatus |= TIOCPKT_STOP; spin_unlock_irqrestore(&tty->ctrl.lock, flags); wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } /** * pty_common_install - set up the pty pair * @driver: the pty driver * @tty: the tty being instantiated * @legacy: true if this is BSD style * * Perform the initial set up for the tty/pty pair. Called from the * tty layer when the port is first opened. * * Locking: the caller must hold the tty_mutex */ static int pty_common_install(struct tty_driver *driver, struct tty_struct *tty, bool legacy) { struct tty_struct *o_tty; struct tty_port *ports[2]; int idx = tty->index; int retval = -ENOMEM; /* Opening the slave first has always returned -EIO */ if (driver->subtype != PTY_TYPE_MASTER) return -EIO; ports[0] = kmalloc(sizeof **ports, GFP_KERNEL); ports[1] = kmalloc(sizeof **ports, GFP_KERNEL); if (!ports[0] || !ports[1]) goto err; if (!try_module_get(driver->other->owner)) { /* This cannot in fact currently happen */ goto err; } o_tty = alloc_tty_struct(driver->other, idx); if (!o_tty) goto err_put_module; tty_set_lock_subclass(o_tty); lockdep_set_subclass(&o_tty->termios_rwsem, TTY_LOCK_SLAVE); if (legacy) { /* We always use new tty termios data so we can do this the easy way .. */ tty_init_termios(tty); tty_init_termios(o_tty); driver->other->ttys[idx] = o_tty; driver->ttys[idx] = tty; } else { memset(&tty->termios_locked, 0, sizeof(tty->termios_locked)); tty->termios = driver->init_termios; memset(&o_tty->termios_locked, 0, sizeof(tty->termios_locked)); o_tty->termios = driver->other->init_termios; } /* * Everything allocated ... set up the o_tty structure. */ tty_driver_kref_get(driver->other); /* Establish the links in both directions */ tty->link = o_tty; o_tty->link = tty; tty_port_init(ports[0]); tty_port_init(ports[1]); tty_buffer_set_limit(ports[0], 8192); tty_buffer_set_limit(ports[1], 8192); o_tty->port = ports[0]; tty->port = ports[1]; o_tty->port->itty = o_tty; tty_buffer_set_lock_subclass(o_tty->port); tty_driver_kref_get(driver); tty->count++; o_tty->count++; return 0; err_put_module: module_put(driver->other->owner); err: kfree(ports[0]); kfree(ports[1]); return retval; } static void pty_cleanup(struct tty_struct *tty) { tty_port_put(tty->port); } /* Traditional BSD devices */ #ifdef CONFIG_LEGACY_PTYS static int pty_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, true); } static void pty_remove(struct tty_driver *driver, struct tty_struct *tty) { struct tty_struct *pair = tty->link; driver->ttys[tty->index] = NULL; if (pair) pair->driver->ttys[pair->index] = NULL; } static int pty_bsd_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *) arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); case TIOCGPTN: /* TTY returns ENOTTY, but glibc expects EINVAL here */ return -EINVAL; } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_bsd_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_bsd_ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); } #else #define pty_bsd_compat_ioctl NULL #endif static int legacy_count = CONFIG_LEGACY_PTY_COUNT; /* * not really modular, but the easiest way to keep compat with existing * bootargs behaviour is to continue using module_param here. */ module_param(legacy_count, int, 0); /* * The master side of a pty can do TIOCSPTLCK and thus * has pty_bsd_ioctl. */ static const struct tty_operations master_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_bsd_ioctl, .compat_ioctl = pty_bsd_compat_ioctl, .cleanup = pty_cleanup, .resize = pty_resize, .remove = pty_remove }; static const struct tty_operations slave_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .cleanup = pty_cleanup, .resize = pty_resize, .start = pty_start, .stop = pty_stop, .remove = pty_remove }; static void __init legacy_pty_init(void) { struct tty_driver *pty_driver, *pty_slave_driver; if (legacy_count <= 0) return; pty_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pty_driver)) panic("Couldn't allocate pty driver"); pty_slave_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pty_slave_driver)) panic("Couldn't allocate pty slave driver"); pty_driver->driver_name = "pty_master"; pty_driver->name = "pty"; pty_driver->major = PTY_MASTER_MAJOR; pty_driver->minor_start = 0; pty_driver->type = TTY_DRIVER_TYPE_PTY; pty_driver->subtype = PTY_TYPE_MASTER; pty_driver->init_termios = tty_std_termios; pty_driver->init_termios.c_iflag = 0; pty_driver->init_termios.c_oflag = 0; pty_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_driver->init_termios.c_lflag = 0; pty_driver->init_termios.c_ispeed = 38400; pty_driver->init_termios.c_ospeed = 38400; pty_driver->other = pty_slave_driver; tty_set_operations(pty_driver, &master_pty_ops_bsd); pty_slave_driver->driver_name = "pty_slave"; pty_slave_driver->name = "ttyp"; pty_slave_driver->major = PTY_SLAVE_MAJOR; pty_slave_driver->minor_start = 0; pty_slave_driver->type = TTY_DRIVER_TYPE_PTY; pty_slave_driver->subtype = PTY_TYPE_SLAVE; pty_slave_driver->init_termios = tty_std_termios; pty_slave_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_slave_driver->init_termios.c_ispeed = 38400; pty_slave_driver->init_termios.c_ospeed = 38400; pty_slave_driver->other = pty_driver; tty_set_operations(pty_slave_driver, &slave_pty_ops_bsd); if (tty_register_driver(pty_driver)) panic("Couldn't register pty driver"); if (tty_register_driver(pty_slave_driver)) panic("Couldn't register pty slave driver"); } #else static inline void legacy_pty_init(void) { } #endif /* Unix98 devices */ #ifdef CONFIG_UNIX98_PTYS static struct cdev ptmx_cdev; /** * ptm_open_peer - open the peer of a pty * @master: the open struct file of the ptmx device node * @tty: the master of the pty being opened * @flags: the flags for open * * Provide a race free way for userspace to open the slave end of a pty * (where they have the master fd and cannot access or trust the mount * namespace /dev/pts was mounted inside). */ int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) { int fd; struct file *filp; int retval = -EINVAL; struct path path; if (tty->driver != ptm_driver) return -EIO; fd = get_unused_fd_flags(flags); if (fd < 0) { retval = fd; goto err; } /* Compute the slave's path */ path.mnt = devpts_mntget(master, tty->driver_data); if (IS_ERR(path.mnt)) { retval = PTR_ERR(path.mnt); goto err_put; } path.dentry = tty->link->driver_data; filp = dentry_open(&path, flags, current_cred()); mntput(path.mnt); if (IS_ERR(filp)) { retval = PTR_ERR(filp); goto err_put; } fd_install(fd, filp); return fd; err_put: put_unused_fd(fd); err: return retval; } static int pty_unix98_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *)arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCGPTN: /* Get PT Number */ return put_user(tty->index, (unsigned int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_unix98_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_unix98_ioctl(tty, cmd, cmd == TIOCSIG ? arg : (unsigned long)compat_ptr(arg)); } #else #define pty_unix98_compat_ioctl NULL #endif /** * ptm_unix98_lookup - find a pty master * @driver: ptm driver * @file: unused * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking. */ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { /* Master must be open via /dev/ptmx */ return ERR_PTR(-EIO); } /** * pts_unix98_lookup - find a pty slave * @driver: pts driver * @file: file pointer to tty * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking for the tty pointer. */ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { struct tty_struct *tty; mutex_lock(&devpts_mutex); tty = devpts_get_priv(file->f_path.dentry); mutex_unlock(&devpts_mutex); /* Master must be open before slave */ if (!tty) return ERR_PTR(-EIO); return tty; } static int pty_unix98_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, false); } /* this is called once with whichever end is closed last */ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) { struct pts_fs_info *fsi; if (tty->driver->subtype == PTY_TYPE_MASTER) fsi = tty->driver_data; else fsi = tty->link->driver_data; if (fsi) { devpts_kill_index(fsi, tty->index); devpts_release(fsi); } } static void pty_show_fdinfo(struct tty_struct *tty, struct seq_file *m) { seq_printf(m, "tty-index:\t%d\n", tty->index); } static const struct tty_operations ptm_unix98_ops = { .lookup = ptm_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_unix98_ioctl, .compat_ioctl = pty_unix98_compat_ioctl, .resize = pty_resize, .cleanup = pty_cleanup, .show_fdinfo = pty_show_fdinfo, }; static const struct tty_operations pty_unix98_ops = { .lookup = pts_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .start = pty_start, .stop = pty_stop, .cleanup = pty_cleanup, }; /** * ptmx_open - open a unix 98 pty master * @inode: inode of device file * @filp: file pointer to tty * * Allocate a unix98 pty master device from the ptmx driver. * * Locking: tty_mutex protects the init_dev work. tty->count should * protect the rest. * allocated_ptys_lock handles the list of free pty numbers */ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; struct dentry *dentry; int retval; int index; nonseekable_open(inode, filp); /* We refuse fsnotify events on ptmx, since it's a shared resource */ filp->f_mode |= FMODE_NONOTIFY; retval = tty_alloc_file(filp); if (retval) return retval; fsi = devpts_acquire(filp); if (IS_ERR(fsi)) { retval = PTR_ERR(fsi); goto out_free_file; } /* find a device that is not in use. */ mutex_lock(&devpts_mutex); index = devpts_new_index(fsi); mutex_unlock(&devpts_mutex); retval = index; if (index < 0) goto out_put_fsi; mutex_lock(&tty_mutex); tty = tty_init_dev(ptm_driver, index); /* The tty returned here is locked so we can safely drop the mutex */ mutex_unlock(&tty_mutex); retval = PTR_ERR(tty); if (IS_ERR(tty)) goto out; /* * From here on out, the tty is "live", and the index and * fsi will be killed/put by the tty_release() */ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = fsi; tty_add_file(tty, filp); dentry = devpts_pty_new(fsi, index, tty->link); if (IS_ERR(dentry)) { retval = PTR_ERR(dentry); goto err_release; } tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) goto err_release; tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); tty_unlock(tty); return 0; err_release: tty_unlock(tty); // This will also put-ref the fsi tty_release(inode, filp); return retval; out: devpts_kill_index(fsi, index); out_put_fsi: devpts_release(fsi); out_free_file: tty_free_file(filp); return retval; } static struct file_operations ptmx_fops __ro_after_init; static void __init unix98_pty_init(void) { ptm_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(ptm_driver)) panic("Couldn't allocate Unix98 ptm driver"); pts_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC); if (IS_ERR(pts_driver)) panic("Couldn't allocate Unix98 pts driver"); ptm_driver->driver_name = "pty_master"; ptm_driver->name = "ptm"; ptm_driver->major = UNIX98_PTY_MASTER_MAJOR; ptm_driver->minor_start = 0; ptm_driver->type = TTY_DRIVER_TYPE_PTY; ptm_driver->subtype = PTY_TYPE_MASTER; ptm_driver->init_termios = tty_std_termios; ptm_driver->init_termios.c_iflag = 0; ptm_driver->init_termios.c_oflag = 0; ptm_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; ptm_driver->init_termios.c_lflag = 0; ptm_driver->init_termios.c_ispeed = 38400; ptm_driver->init_termios.c_ospeed = 38400; ptm_driver->other = pts_driver; tty_set_operations(ptm_driver, &ptm_unix98_ops); pts_driver->driver_name = "pty_slave"; pts_driver->name = "pts"; pts_driver->major = UNIX98_PTY_SLAVE_MAJOR; pts_driver->minor_start = 0; pts_driver->type = TTY_DRIVER_TYPE_PTY; pts_driver->subtype = PTY_TYPE_SLAVE; pts_driver->init_termios = tty_std_termios; pts_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pts_driver->init_termios.c_ispeed = 38400; pts_driver->init_termios.c_ospeed = 38400; pts_driver->other = ptm_driver; tty_set_operations(pts_driver, &pty_unix98_ops); if (tty_register_driver(ptm_driver)) panic("Couldn't register Unix98 ptm driver"); if (tty_register_driver(pts_driver)) panic("Couldn't register Unix98 pts driver"); /* Now create the /dev/ptmx special device */ tty_default_fops(&ptmx_fops); ptmx_fops.open = ptmx_open; cdev_init(&ptmx_cdev, &ptmx_fops); if (cdev_add(&ptmx_cdev, MKDEV(TTYAUX_MAJOR, 2), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0) panic("Couldn't register /dev/ptmx driver"); device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx"); } #else static inline void unix98_pty_init(void) { } #endif static int __init pty_init(void) { legacy_pty_init(); unix98_pty_init(); return 0; } device_initcall(pty_init); |
| 5 15 5 16 14 5 12 2 2 2 5 5 4 4 1 3 4 4 4 4 4 4 1 4 3 3 2 1 2 2 2 2 2 2 2 2 2 2 3 2 3 3 2 2 2 4 4 4 4 4 4 4 4 3 3 9 9 9 8 8 9 9 9 9 9 3 1 1 1 2 19 18 19 19 19 18 19 18 19 19 19 18 3 2 3 3 3 3 2 3 3 6 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 5 4 4 3 1 5 4 5 5 20 19 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_version = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_version = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 48 49 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 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/workqueue.h> #include <net/udp_tunnel.h> #include <net/vxlan.h> enum udp_tunnel_nic_table_entry_flags { UDP_TUNNEL_NIC_ENTRY_ADD = BIT(0), UDP_TUNNEL_NIC_ENTRY_DEL = BIT(1), UDP_TUNNEL_NIC_ENTRY_OP_FAIL = BIT(2), UDP_TUNNEL_NIC_ENTRY_FROZEN = BIT(3), }; struct udp_tunnel_nic_table_entry { __be16 port; u8 type; u8 flags; u16 use_cnt; #define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; /** * struct udp_tunnel_nic - UDP tunnel port offload state * @work: async work for talking to hardware from process context * @dev: netdev pointer * @need_sync: at least one port start changed * @need_replay: space was freed, we need a replay of all ports * @work_pending: @work is currently scheduled * @n_tables: number of tables under @entries * @missed: bitmap of tables which overflown * @entries: table of tables of ports currently offloaded */ struct udp_tunnel_nic { struct work_struct work; struct net_device *dev; u8 need_sync:1; u8 need_replay:1; u8 work_pending:1; unsigned int n_tables; unsigned long missed; struct udp_tunnel_nic_table_entry *entries[] __counted_by(n_tables); }; /* We ensure all work structs are done using driver state, but not the code. * We need a workqueue we can flush before module gets removed. */ static struct workqueue_struct *udp_tunnel_nic_workqueue; static const char *udp_tunnel_nic_tunnel_type_name(unsigned int type) { switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: return "geneve"; case UDP_TUNNEL_TYPE_VXLAN_GPE: return "vxlan-gpe"; default: return "unknown"; } } static bool udp_tunnel_nic_entry_is_free(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt == 0 && !entry->flags; } static bool udp_tunnel_nic_entry_is_present(struct udp_tunnel_nic_table_entry *entry) { return entry->use_cnt && !(entry->flags & ~UDP_TUNNEL_NIC_ENTRY_FROZEN); } static bool udp_tunnel_nic_entry_is_frozen(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_freeze_used(struct udp_tunnel_nic_table_entry *entry) { if (!udp_tunnel_nic_entry_is_free(entry)) entry->flags |= UDP_TUNNEL_NIC_ENTRY_FROZEN; } static void udp_tunnel_nic_entry_unfreeze(struct udp_tunnel_nic_table_entry *entry) { entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_FROZEN; } static bool udp_tunnel_nic_entry_is_queued(struct udp_tunnel_nic_table_entry *entry) { return entry->flags & (UDP_TUNNEL_NIC_ENTRY_ADD | UDP_TUNNEL_NIC_ENTRY_DEL); } static void udp_tunnel_nic_entry_queue(struct udp_tunnel_nic *utn, struct udp_tunnel_nic_table_entry *entry, unsigned int flag) { entry->flags |= flag; utn->need_sync = 1; } static void udp_tunnel_nic_ti_from_entry(struct udp_tunnel_nic_table_entry *entry, struct udp_tunnel_info *ti) { memset(ti, 0, sizeof(*ti)); ti->port = entry->port; ti->type = entry->type; ti->hw_priv = entry->hw_priv; } static bool udp_tunnel_nic_is_empty(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) if (!udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return false; return true; } static bool udp_tunnel_nic_should_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; if (!utn->missed) return false; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!test_bit(i, &utn->missed)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_is_free(&utn->entries[i][j])) return true; } return false; } static void __udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; entry = &utn->entries[table][idx]; if (entry->use_cnt) udp_tunnel_nic_ti_from_entry(entry, ti); } static void __udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { dev->udp_tunnel_nic->entries[table][idx].hw_priv = priv; } static void udp_tunnel_nic_entry_update_done(struct udp_tunnel_nic_table_entry *entry, int err) { bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; WARN_ON_ONCE(entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD && (!err || (err == -EEXIST && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_ADD; if (entry->flags & UDP_TUNNEL_NIC_ENTRY_DEL && (!err || (err == -ENOENT && dodgy))) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_DEL; if (!err) entry->flags &= ~UDP_TUNNEL_NIC_ENTRY_OP_FAIL; else entry->flags |= UDP_TUNNEL_NIC_ENTRY_OP_FAIL; } static void udp_tunnel_nic_device_sync_one(struct net_device *dev, struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx) { struct udp_tunnel_nic_table_entry *entry; struct udp_tunnel_info ti; int err; entry = &utn->entries[table][idx]; if (!udp_tunnel_nic_entry_is_queued(entry)) return; udp_tunnel_nic_ti_from_entry(entry, &ti); if (entry->flags & UDP_TUNNEL_NIC_ENTRY_ADD) err = dev->udp_tunnel_nic_info->set_port(dev, table, idx, &ti); else err = dev->udp_tunnel_nic_info->unset_port(dev, table, idx, &ti); udp_tunnel_nic_entry_update_done(entry, err); if (err) netdev_warn(dev, "UDP tunnel port sync failed port %d type %s: %d\n", be16_to_cpu(entry->port), udp_tunnel_nic_tunnel_type_name(entry->type), err); } static void udp_tunnel_nic_device_sync_by_port(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_device_sync_one(dev, utn, i, j); } static void udp_tunnel_nic_device_sync_by_table(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; int err; for (i = 0; i < utn->n_tables; i++) { /* Find something that needs sync in this table */ for (j = 0; j < info->tables[i].n_entries; j++) if (udp_tunnel_nic_entry_is_queued(&utn->entries[i][j])) break; if (j == info->tables[i].n_entries) continue; err = info->sync_table(dev, i); if (err) netdev_warn(dev, "UDP tunnel port sync failed for table %d: %d\n", i, err); for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (udp_tunnel_nic_entry_is_queued(entry)) udp_tunnel_nic_entry_update_done(entry, err); } } } static void __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { if (!utn->need_sync) return; if (dev->udp_tunnel_nic_info->sync_table) udp_tunnel_nic_device_sync_by_table(dev, utn); else udp_tunnel_nic_device_sync_by_port(dev, utn); utn->need_sync = 0; /* Can't replay directly here, in case we come from the tunnel driver's * notification - trying to replay may deadlock inside tunnel driver. */ utn->need_replay = udp_tunnel_nic_should_replay(dev, utn); } static void udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; bool may_sleep; if (!utn->need_sync) return; /* Drivers which sleep in the callback need to update from * the workqueue, if we come from the tunnel driver's notification. */ may_sleep = info->flags & UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (!may_sleep) __udp_tunnel_nic_device_sync(dev, utn); if (may_sleep || utn->need_replay) { queue_work(udp_tunnel_nic_workqueue, &utn->work); utn->work_pending = 1; } } static bool udp_tunnel_nic_table_is_capable(const struct udp_tunnel_nic_table_info *table, struct udp_tunnel_info *ti) { return table->tunnel_types & ti->type; } static bool udp_tunnel_nic_is_capable(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i; /* Special case IPv4-only NICs */ if (info->flags & UDP_TUNNEL_NIC_INFO_IPV4_ONLY && ti->sa_family != AF_INET) return false; for (i = 0; i < utn->n_tables; i++) if (udp_tunnel_nic_table_is_capable(&info->tables[i], ti)) return true; return false; } static int udp_tunnel_nic_has_collision(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_table_entry *entry; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry) && entry->port == ti->port && entry->type != ti->type) { __set_bit(i, &utn->missed); return true; } } return false; } static void udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ entry->use_cnt += use_cnt_adj; if (!dodgy && !entry->use_cnt == !(entry->use_cnt - use_cnt_adj)) return; /* Cancel the op before it was sent to the device, if possible, * otherwise we'd need to take special care to issue commands * in the same order the ports arrived. */ if (use_cnt_adj < 0) { from = UDP_TUNNEL_NIC_ENTRY_ADD; to = UDP_TUNNEL_NIC_ENTRY_DEL; } else { from = UDP_TUNNEL_NIC_ENTRY_DEL; to = UDP_TUNNEL_NIC_ENTRY_ADD; } if (entry->flags & from) { entry->flags &= ~from; if (!dodgy) return; } udp_tunnel_nic_entry_queue(utn, entry, to); } static bool udp_tunnel_nic_entry_try_adj(struct udp_tunnel_nic *utn, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti, int use_cnt_adj) { struct udp_tunnel_nic_table_entry *entry = &utn->entries[table][idx]; if (udp_tunnel_nic_entry_is_free(entry) || entry->port != ti->port || entry->type != ti->type) return false; if (udp_tunnel_nic_entry_is_frozen(entry)) return true; udp_tunnel_nic_entry_adj(utn, table, idx, use_cnt_adj); return true; } /* Try to find existing matching entry and adjust its use count, instead of * adding a new one. Returns true if entry was found. In case of delete the * entry may have gotten removed in the process, in which case it will be * queued for removal. */ static bool udp_tunnel_nic_try_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti, int use_cnt_adj) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) if (udp_tunnel_nic_entry_try_adj(utn, i, j, ti, use_cnt_adj)) return true; } return false; } static bool udp_tunnel_nic_add_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, +1); } static bool udp_tunnel_nic_del_existing(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { return udp_tunnel_nic_try_existing(dev, utn, ti, -1); } static bool udp_tunnel_nic_add_new(struct net_device *dev, struct udp_tunnel_nic *utn, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_table_info *table; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) { table = &dev->udp_tunnel_nic_info->tables[i]; if (!udp_tunnel_nic_table_is_capable(table, ti)) continue; for (j = 0; j < table->n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; if (!udp_tunnel_nic_entry_is_free(entry)) continue; entry->port = ti->port; entry->type = ti->type; entry->use_cnt = 1; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); return true; } /* The different table may still fit this port in, but there * are no devices currently which have multiple tables accepting * the same tunnel type, and false positives are okay. */ __set_bit(i, &utn->missed); } return false; } static void __udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!netif_running(dev) && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY) return; if (info->flags & UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN && ti->port == htons(IANA_VXLAN_UDP_PORT)) { if (ti->type != UDP_TUNNEL_TYPE_VXLAN) netdev_warn(dev, "device assumes port 4789 will be used by vxlan tunnels\n"); return; } if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; /* It may happen that a tunnel of one type is removed and different * tunnel type tries to reuse its port before the device was informed. * Rely on utn->missed to re-add this port later. */ if (udp_tunnel_nic_has_collision(dev, utn, ti)) return; if (!udp_tunnel_nic_add_existing(dev, utn, ti)) udp_tunnel_nic_add_new(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { struct udp_tunnel_nic *utn; utn = dev->udp_tunnel_nic; if (!utn) return; if (!udp_tunnel_nic_is_capable(dev, utn, ti)) return; udp_tunnel_nic_del_existing(dev, utn, ti); udp_tunnel_nic_device_sync(dev, utn); } static void __udp_tunnel_nic_reset_ntf(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int i, j; ASSERT_RTNL(); utn = dev->udp_tunnel_nic; if (!utn) return; utn->need_sync = false; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { struct udp_tunnel_nic_table_entry *entry; entry = &utn->entries[i][j]; entry->flags &= ~(UDP_TUNNEL_NIC_ENTRY_DEL | UDP_TUNNEL_NIC_ENTRY_OP_FAIL); /* We don't release rtnl across ops */ WARN_ON(entry->flags & UDP_TUNNEL_NIC_ENTRY_FROZEN); if (!entry->use_cnt) continue; udp_tunnel_nic_entry_queue(utn, entry, UDP_TUNNEL_NIC_ENTRY_ADD); } __udp_tunnel_nic_device_sync(dev, utn); } static size_t __udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; unsigned int j; size_t size; utn = dev->udp_tunnel_nic; if (!utn) return 0; size = 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; size += nla_total_size(0) + /* _TABLE_ENTRY */ nla_total_size(sizeof(__be16)) + /* _ENTRY_PORT */ nla_total_size(sizeof(u32)); /* _ENTRY_TYPE */ } return size; } static int __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic *utn; struct nlattr *nest; unsigned int j; utn = dev->udp_tunnel_nic; if (!utn) return 0; for (j = 0; j < info->tables[table].n_entries; j++) { if (!udp_tunnel_nic_entry_is_present(&utn->entries[table][j])) continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_TYPE, ilog2(utn->entries[table][j].type))) goto err_cancel; nla_nest_end(skb, nest); } return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static const struct udp_tunnel_nic_ops __udp_tunnel_nic_ops = { .get_port = __udp_tunnel_nic_get_port, .set_port_priv = __udp_tunnel_nic_set_port_priv, .add_port = __udp_tunnel_nic_add_port, .del_port = __udp_tunnel_nic_del_port, .reset_ntf = __udp_tunnel_nic_reset_ntf, .dump_size = __udp_tunnel_nic_dump_size, .dump_write = __udp_tunnel_nic_dump_write, }; static void udp_tunnel_nic_flush(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; unsigned int i, j; for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) { int adj_cnt = -utn->entries[i][j].use_cnt; if (adj_cnt) udp_tunnel_nic_entry_adj(utn, i, j, adj_cnt); } __udp_tunnel_nic_device_sync(dev, utn); for (i = 0; i < utn->n_tables; i++) memset(utn->entries[i], 0, array_size(info->tables[i].n_entries, sizeof(**utn->entries))); WARN_ON(utn->need_sync); utn->need_replay = 0; } static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay * does not double up the refcount. */ for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_freeze_used(&utn->entries[i][j]); utn->missed = 0; utn->need_replay = 0; if (!info->shared) { udp_tunnel_get_rx_info(dev); } else { list_for_each_entry(node, &info->shared->devices, list) udp_tunnel_get_rx_info(node->dev); } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) udp_tunnel_nic_entry_unfreeze(&utn->entries[i][j]); } static void udp_tunnel_nic_device_sync_work(struct work_struct *work) { struct udp_tunnel_nic *utn = container_of(work, struct udp_tunnel_nic, work); rtnl_lock(); utn->work_pending = 0; __udp_tunnel_nic_device_sync(utn->dev, utn); if (utn->need_replay) udp_tunnel_nic_replay(utn->dev, utn); rtnl_unlock(); } static struct udp_tunnel_nic * udp_tunnel_nic_alloc(const struct udp_tunnel_nic_info *info, unsigned int n_tables) { struct udp_tunnel_nic *utn; unsigned int i; utn = kzalloc(struct_size(utn, entries, n_tables), GFP_KERNEL); if (!utn) return NULL; utn->n_tables = n_tables; INIT_WORK(&utn->work, udp_tunnel_nic_device_sync_work); for (i = 0; i < n_tables; i++) { utn->entries[i] = kcalloc(info->tables[i].n_entries, sizeof(*utn->entries[i]), GFP_KERNEL); if (!utn->entries[i]) goto err_free_prev_entries; } return utn; err_free_prev_entries: while (i--) kfree(utn->entries[i]); kfree(utn); return NULL; } static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) { unsigned int i; for (i = 0; i < utn->n_tables; i++) kfree(utn->entries[i]); kfree(utn); } static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); /* Expect use count of at most 2 (IPv4, IPv6) per device */ BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; if (WARN_ON(info->shared && info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return -EINVAL; n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) continue; n_tables++; if (WARN_ON(!info->tables[i - 1].n_entries)) return -EINVAL; } /* Create UDP tunnel state structures */ if (info->shared) { node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->dev = dev; } if (info->shared && info->shared->udp_tunnel_nic_info) { utn = info->shared->udp_tunnel_nic_info; } else { utn = udp_tunnel_nic_alloc(info, n_tables); if (!utn) { kfree(node); return -ENOMEM; } } if (info->shared) { if (!info->shared->udp_tunnel_nic_info) { INIT_LIST_HEAD(&info->shared->devices); info->shared->udp_tunnel_nic_info = utn; } list_add_tail(&node->list, &info->shared->devices); } utn->dev = dev; dev_hold(dev); dev->udp_tunnel_nic = utn; if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) udp_tunnel_get_rx_info(dev); return 0; } static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; /* For a shared table remove this dev from the list of sharing devices * and if there are other devices just detach. */ if (info->shared) { struct udp_tunnel_nic_shared_node *node, *first; list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; if (list_entry_is_head(node, &info->shared->devices, list)) return; list_del(&node->list); kfree(node); first = list_first_entry_or_null(&info->shared->devices, typeof(*first), list); if (first) { udp_tunnel_drop_rx_info(dev); utn->dev = first->dev; goto release_dev; } info->shared->udp_tunnel_nic_info = NULL; } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. */ udp_tunnel_nic_flush(dev, utn); /* Wait for the work to be done using the state, netdev core will * retry unregister until we give up our reference on this device. */ if (utn->work_pending) return; udp_tunnel_nic_free(utn); release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } static int udp_tunnel_nic_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); const struct udp_tunnel_nic_info *info; struct udp_tunnel_nic *utn; info = dev->udp_tunnel_nic_info; if (!info) return NOTIFY_DONE; if (event == NETDEV_REGISTER) { int err; err = udp_tunnel_nic_register(dev); if (err) netdev_WARN(dev, "failed to register for UDP tunnel offloads: %d", err); return notifier_from_errno(err); } /* All other events will need the udp_tunnel_nic state */ utn = dev->udp_tunnel_nic; if (!utn) return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { udp_tunnel_nic_unregister(dev, utn); return NOTIFY_OK; } /* All other events only matter if NIC has to be programmed open */ if (!(info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) return NOTIFY_DONE; if (event == NETDEV_UP) { WARN_ON(!udp_tunnel_nic_is_empty(dev, utn)); udp_tunnel_get_rx_info(dev); return NOTIFY_OK; } if (event == NETDEV_GOING_DOWN) { udp_tunnel_nic_flush(dev, utn); return NOTIFY_OK; } return NOTIFY_DONE; } static struct notifier_block udp_tunnel_nic_notifier_block __read_mostly = { .notifier_call = udp_tunnel_nic_netdevice_event, }; static int __init udp_tunnel_nic_init_module(void) { int err; udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; rtnl_lock(); udp_tunnel_nic_ops = &__udp_tunnel_nic_ops; rtnl_unlock(); err = register_netdevice_notifier(&udp_tunnel_nic_notifier_block); if (err) goto err_unset_ops; return 0; err_unset_ops: rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); return err; } late_initcall(udp_tunnel_nic_init_module); static void __exit udp_tunnel_nic_cleanup_module(void) { unregister_netdevice_notifier(&udp_tunnel_nic_notifier_block); rtnl_lock(); udp_tunnel_nic_ops = NULL; rtnl_unlock(); destroy_workqueue(udp_tunnel_nic_workqueue); } module_exit(udp_tunnel_nic_cleanup_module); MODULE_LICENSE("GPL"); |
| 2 3 3 3 3 5 6 6 5 5 2 5 1 5 5 4 5 2 2 2 2 2 2 2 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * Basic idea behind the notification queue: An fsnotify group (like inotify) * sends the userspace notification about events asynchronously some time after * the event happened. When inotify gets an event it will need to add that * event to the group notify queue. Since a single event might need to be on * multiple group's notification queues we can't add the event directly to each * queue and instead add a small "event_holder" to each queue. This event_holder * has a pointer back to the original event. Since the majority of events are * going to end up on one, and only one, notification queue we embed one * event_holder into each event. This means we have a single allocation instead * of always needing two. If the embedded event_holder is already in use by * another group a new event_holder (from fsnotify_event_holder_cachep) will be * allocated and used. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0); /** * fsnotify_get_cookie - return a unique cookie for use in synchronizing events. * Called from fsnotify_move, which is inlined into filesystem modules. */ u32 fsnotify_get_cookie(void) { return atomic_inc_return(&fsnotify_sync_cookie); } EXPORT_SYMBOL_GPL(fsnotify_get_cookie); void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event) { /* Overflow events are per-group and we don't want to free them */ if (!event || event == group->overflow_event) return; /* * If the event is still queued, we have a problem... Do an unreliable * lockless check first to avoid locking in the common case. The * locking may be necessary for permission events which got removed * from the list by a different CPU than the one freeing the event. */ if (!list_empty(&event->list)) { spin_lock(&group->notification_lock); WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } group->ops->free_event(group, event); } /* * Try to add an event to the notification queue. * The group can later pull this event off the queue to deal with. * The group can use the @merge hook to merge the event with a queued event. * The group can use the @insert hook to insert the event into hash table. * The function returns: * 0 if the event was added to a queue * 1 if the event was merged with some other queued event * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; pr_debug("%s: group=%p event=%p\n", __func__, group, event); spin_lock(&group->notification_lock); if (group->shutdown) { spin_unlock(&group->notification_lock); return 2; } if (event == group->overflow_event || group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ if (!list_empty(&group->overflow_event->list)) { spin_unlock(&group->notification_lock); return ret; } event = group->overflow_event; goto queue; } if (!list_empty(list) && merge) { ret = merge(group, event); if (ret) { spin_unlock(&group->notification_lock); return ret; } } queue: group->q_len++; list_add_tail(&event->list, list); if (insert) insert(group, event); spin_unlock(&group->notification_lock); wake_up(&group->notification_waitq); kill_fasync(&group->fsn_fa, SIGIO, POLL_IN); return ret; } void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event) { assert_spin_locked(&group->notification_lock); /* * We need to init list head for the case of overflow event so that * check in fsnotify_add_event() works */ list_del_init(&event->list); group->q_len--; } /* * Return the first event on the notification list without removing it. * Returns NULL if the list is empty. */ struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); if (fsnotify_notify_queue_is_empty(group)) return NULL; return list_first_entry(&group->notification_list, struct fsnotify_event, list); } /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) { struct fsnotify_event *event = fsnotify_peek_first_event(group); if (!event) return NULL; pr_debug("%s: group=%p event=%p\n", __func__, group, event); fsnotify_remove_queued_event(group, event); return event; } /* * Called when a group is being torn down to clean up any outstanding * event notifications. */ void fsnotify_flush_notify(struct fsnotify_group *group) { struct fsnotify_event *event; spin_lock(&group->notification_lock); while (!fsnotify_notify_queue_is_empty(group)) { event = fsnotify_remove_first_event(group); spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, event); spin_lock(&group->notification_lock); } spin_unlock(&group->notification_lock); } |
| 10 10 8 10 2 26 28 26 6 2 6 6 6 2 5 4 5 1 5 4 5 6 6 5 5 5 6 5 19 19 19 1 20 19 21 19 18 18 16 21 21 7 6 6 7 7 3 7 5 5 5 4 4 5 5 5 3 5 8 8 8 8 8 8 5 3 4 2 7 7 7 5 2 7 7 6 1 7 7 5 7 3 8 8 4 4 4 4 5 4 5 49 50 50 50 50 2 2 2 2 2 2 2 2 1 1 2 2 32 32 32 31 2 32 32 32 98 103 102 101 101 102 102 2 103 100 | 1 2 3 4 5 6 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file 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/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/uio.h> #include "kernfs-internal.h" struct kernfs_open_node { struct rcu_head rcu_head; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ unsigned int nr_mmapped; unsigned int nr_to_release; }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for %NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn) { int idx = hash_ptr(kn, NR_KERNFS_LOCK_BITS); return &kernfs_locks->open_file_mutex[idx]; } static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn) { struct mutex *lock; lock = kernfs_open_file_mutex_ptr(kn); mutex_lock(lock); return lock; } /** * of_on - Get the kernfs_open_node of the specified kernfs_open_file * @of: target kernfs_open_file * * Return: the kernfs_open_node of the kernfs_open_file */ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) { return rcu_dereference_protected(of->kn->attr.open, !list_empty(&of->list)); } /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * * @kn: target kernfs_node. * * Fetch and return ->attr.open of @kn when caller holds the * kernfs_open_file_mutex_ptr(kn). * * Update of ->attr.open happens under kernfs_open_file_mutex_ptr(kn). So when * the caller guarantees that this mutex is being held, other updaters can't * change ->attr.open and this means that we can safely deref ->attr.open * outside RCU read-side critical section. * * The caller needs to make sure that kernfs_open_file_mutex is held. * * Return: @kn->attr.open when kernfs_open_file_mutex is held. */ static struct kernfs_open_node * kernfs_deref_open_node_locked(struct kernfs_node *kn) { return rcu_dereference_protected(kn->attr.open, lockdep_is_held(kernfs_open_file_mutex_ptr(kn))); } static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active(of->kn); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } return single_start(sf, ppos); } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of_on(of)->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of_on(of)->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read_iter(iocb, iter); return kernfs_file_read_iter(iocb, iter); } /* * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; char *buf; if (of->atomic_write_len) { if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len > 0) iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active(of->kn)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active(of->kn); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active(of->kn); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active(of->kn); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active(of->kn); return ret; } static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_fop_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active(of->kn)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; if (!of->mmapped) { of->mmapped = true; of_on(of)->nr_mmapped++; of->vm_ops = vma->vm_ops; } vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active(of->kn); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * Locking: * Kernel thread context (may sleep). * * Return: * %0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { /* not there, initialize a new one */ on = kzalloc(sizeof(*on), GFP_KERNEL); if (!on) { mutex_unlock(mutex); return -ENOMEM; } atomic_set(&on->event, 1); init_waitqueue_head(&on->poll); INIT_LIST_HEAD(&on->files); rcu_assign_pointer(kn->attr.open, on); } list_add_tail(&of->list, &on->files); if (kn->flags & KERNFS_HAS_RELEASE) on->nr_to_release++; mutex_unlock(mutex); return 0; } /** * kernfs_unlink_open_file - Unlink @of from @kn. * * @kn: target kernfs_node * @of: associated kernfs_open_file * @open_failed: ->open() failed, cancel ->release() * * Unlink @of from list of @kn's associated open files. If list of * associated open files becomes empty, disassociate and free * kernfs_open_node. * * LOCKING: * None. */ static void kernfs_unlink_open_file(struct kernfs_node *kn, struct kernfs_open_file *of, bool open_failed) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } if (of) { if (kn->flags & KERNFS_HAS_RELEASE) { WARN_ON_ONCE(of->released == open_failed); if (open_failed) on->nr_to_release--; } if (of->mmapped) on->nr_mmapped--; list_del(&of->list); } if (list_empty(&on->files)) { rcu_assign_pointer(kn->attr.open, NULL); kfree_rcu(on, rcu_head); } mutex_unlock(mutex); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_lock nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * For similar reasons, writable and readonly files are given different * lockdep key, because the writable file /sys/power/resume may call vfs * lookup helpers for arbitrary paths and readonly files can be read by * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. * * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else if (file->f_mode & FMODE_WRITE) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_unlink_open_file(kn, of, true); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex_ptr(kn) is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(kernfs_open_file_mutex_ptr(kn)); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; of_on(of)->nr_to_release--; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); kernfs_release_file(kn, of); mutex_unlock(mutex); } kernfs_unlink_open_file(kn, of, false); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } bool kernfs_should_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; bool ret; /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. */ WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); rcu_read_lock(); on = rcu_dereference(kn->attr.open); ret = on && (on->nr_mmapped || on->nr_to_release); rcu_read_unlock(); return ret; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (of->mmapped) { unmap_mapping_range(inode->i_mapping, 0, 0, 1); of->mmapped = false; on->nr_mmapped--; } if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } WARN_ON_ONCE(on->nr_mmapped || on->nr_to_release); mutex_unlock(mutex); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_open_node *on = of_on(of); poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active(kn)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); return ret; } static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; loff_t ret; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); return -ENODEV; } ops = kernfs_ops(of->kn); if (ops->llseek) ret = ops->llseek(of, offset, whence); else ret = generic_file_llseek(file, offset, whence); kernfs_put_active(of->kn); mutex_unlock(&of->mutex); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; struct kernfs_root *root; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); root = kernfs_root(kn); /* kick fsnotify */ down_read(&root->kernfs_supers_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, p_inode, &name, inode, 0); iput(p_inode); } kernfs_put(parent); } if (!p_inode) fsnotify_inode(inode, FS_MODIFY); iput(inode); } up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } rcu_read_unlock(); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Return: the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accessible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 258 6 84 16 11 11 20 48 29 50 29 4 3 3 102 196 8 66 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; }; enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_PER_VMA_LOCK_STATS #define count_vm_vma_lock_event(x) count_vm_event(x) #else #define count_vm_vma_lock_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { __mod_zone_page_state(folio_zone(folio), item, nr); } static inline void __zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void __zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { mod_zone_page_state(folio_zone(folio), item, nr); } static inline void zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void __node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { __mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void __node_stat_add_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void __node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } static inline void node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void node_stat_add_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #ifdef CONFIG_MEMCG void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val); static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __lruvec_stat_mod_folio(folio, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { lruvec_stat_mod_folio(page_folio(page), idx, val); } #else static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { __mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void __lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void __lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } static inline void lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } #endif /* _LINUX_VMSTAT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | // SPDX-License-Identifier: GPL-2.0 /* * lib/smp_processor_id.c * * DEBUG_PREEMPT variant of smp_processor_id(). */ #include <linux/export.h> #include <linux/kprobes.h> #include <linux/sched.h> noinstr static unsigned int check_preemption_disabled(const char *what1, const char *what2) { int this_cpu = raw_smp_processor_id(); if (likely(preempt_count())) goto out; if (irqs_disabled()) goto out; if (is_percpu_thread()) goto out; #ifdef CONFIG_SMP if (current->migration_disabled) goto out; #endif /* * It is valid to assume CPU-locality during early bootup: */ if (system_state < SYSTEM_SCHEDULING) goto out; /* * Avoid recursion: */ preempt_disable_notrace(); instrumentation_begin(); if (!printk_ratelimit()) goto out_enable; printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", what1, what2, preempt_count() - 1, current->comm, current->pid); printk("caller is %pS\n", __builtin_return_address(0)); dump_stack(); out_enable: instrumentation_end(); preempt_enable_no_resched_notrace(); out: return this_cpu; } noinstr unsigned int debug_smp_processor_id(void) { return check_preemption_disabled("smp_processor_id", ""); } EXPORT_SYMBOL(debug_smp_processor_id); noinstr void __this_cpu_preempt_check(const char *op) { check_preemption_disabled("__this_cpu_", op); } EXPORT_SYMBOL(__this_cpu_preempt_check); |
| 183 182 1277 1267 317 15 15 41 41 21 22 22 314 1178 1198 16 16 208 15 208 208 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_FIND_H_ #define __LINUX_FIND_H_ #ifndef __LINUX_BITMAP_H #error only <linux/bitmap.h> can be included directly #endif #include <linux/bitops.h> unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits, unsigned long start); unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); #ifdef __BIG_ENDIAN unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size); unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset); #endif #ifndef find_next_bit /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit(addr, size, offset); } #endif #ifndef find_next_and_bit /** * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & *addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_and_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_andnot_bit /** * find_next_andnot_bit - find the next set bit in *addr1 excluding all the bits * in *addr2 * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr1 & ~*addr2 & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_andnot_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_or_bit /** * find_next_or_bit - find the next set bit in either memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = (*addr1 | *addr2) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_or_bit(addr1, addr2, size, offset); } #endif #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val; if (unlikely(offset >= size)) return size; val = *addr | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit(addr, size, offset); } #endif #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_bit(addr, size); } #endif /** * find_nth_bit - find N'th set bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * The following is semantically equivalent: * idx = find_nth_bit(addr, size, 0); * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ static inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_bit(addr, size, n); } /** * find_nth_and_bit - find N'th set bit in 2 memory regions * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_bit(addr1, addr2, size, n); } /** * find_nth_andnot_bit - find N'th set bit in 2 memory regions, * flipping bits in 2nd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_andnot_bit(addr1, addr2, size, n); } /** * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, * excluding those set in 3rd region * @addr1: The 1st address to start the search at * @addr2: The 2nd address to start the search at * @addr3: The 3rd address to start the search at * @size: The maximum number of bits to search * @n: The number of set bit, which position is needed, counting from 0 * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ static __always_inline unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { if (n >= size) return size; if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); return val ? fns(val, n) : size; } return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); } #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the next set bit * If no bits are set, returns @size. */ static inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_bit(addr1, addr2, size); } #endif /** * find_first_and_and_bit - find the first set bit in 3 memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @addr3: The third address to base the search on * @size: The bitmap size in bits * * Returns the bit number for the first set bit * If no bits are set, returns @size. */ static inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); return val ? __ffs(val) : size; } return _find_first_and_and_bit(addr1, addr2, addr3, size); } #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region * @addr: The address to start the search at * @size: The maximum number of bits to search * * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ static inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit(addr, size); } #endif #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region * @addr: The address to start the search at * @size: The number of bits to search * * Returns the bit number of the last set bit, or size. */ static inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = *addr & GENMASK(size - 1, 0); return val ? __fls(val) : size; } return _find_last_bit(addr, size); } #endif /** * find_next_and_bit_wrap - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { unsigned long bit = find_next_and_bit(addr1, addr2, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_and_bit(addr1, addr2, offset); return bit < offset ? bit : size; } /** * find_next_bit_wrap - find the next set bit in a memory region * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ static inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { unsigned long bit = find_next_bit(addr, size, offset); if (bit < size || offset == 0) return bit; bit = find_first_bit(addr, offset); return bit < offset ? bit : size; } /* * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ static inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { unsigned long bit; /* If not wrapped around */ if (n > start) { /* and have a bit, just return it. */ bit = find_next_bit(bitmap, size, n); if (bit < size) return bit; /* Otherwise, wrap around and ... */ n = 0; } /* Search the other part. */ bit = find_next_bit(bitmap, start, n); return bit < start ? bit : size; } /** * find_next_clump8 - find next 8-bit clump with set bits in a memory region * @clump: location to store copy of found clump * @addr: address to base the search on * @size: bitmap size in number of bits * @offset: bit offset at which to start searching * * Returns the bit offset for the next set clump; the found clump value is * copied to the location pointed by @clump. If no bits are set, returns @size. */ extern unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset); #define find_first_clump8(clump, bits, size) \ find_next_clump8((clump), (bits), (size), 0) #if defined(__LITTLE_ENDIAN) static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } static inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } static inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) | ~GENMASK(size - 1, offset); return val == ~0UL ? size : ffz(val); } return _find_next_zero_bit_le(addr, size, offset); } #endif #ifndef find_first_zero_bit_le static inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { unsigned long val = swab(*(const unsigned long *)addr) | ~GENMASK(size - 1, 0); return val == ~0UL ? size : ffz(val); } return _find_first_zero_bit_le(addr, size); } #endif #ifndef find_next_bit_le static inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { if (small_const_nbits(size)) { unsigned long val = *(const unsigned long *)addr; if (unlikely(offset >= size)) return size; val = swab(val) & GENMASK(size - 1, offset); return val ? __ffs(val) : size; } return _find_next_bit_le(addr, size, offset); } #endif #else #error "Please fix <asm/byteorder.h>" #endif #define for_each_set_bit(bit, addr, size) \ for ((bit) = 0; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_and_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_andnot_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) #define for_each_or_bit(bit, addr1, addr2, size) \ for ((bit) = 0; \ (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) #define for_each_clear_bit(bit, addr, size) \ for ((bit) = 0; \ (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); \ (bit)++) /* same as for_each_clear_bit() but use bit as value to start with */ #define for_each_clear_bit_from(bit, addr, size) \ for (; (bit) = find_next_zero_bit((addr), (size), (bit)), (bit) < (size); (bit)++) /** * for_each_set_bitrange - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit) * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_bit((addr), (size), b), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_bit((addr), (size), (b)), \ (e) = find_next_zero_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first unset bit) * @e: bit offset of end of current bitrange (first set bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange(b, e, addr, size) \ for ((b) = 0; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) * @b: bit offset of start of current bitrange (first set bit); must be initialized * @e: bit offset of end of current bitrange (first unset bit) * @addr: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_clear_bitrange_from(b, e, addr, size) \ for (; \ (b) = find_next_zero_bit((addr), (size), (b)), \ (e) = find_next_bit((addr), (size), (b) + 1), \ (b) < (size); \ (b) = (e) + 1) /** * for_each_set_bit_wrap - iterate over all set bits starting from @start, and * wrapping around the end of bitmap. * @bit: offset for current iteration * @addr: bitmap address to base the search on * @size: bitmap size in number of bits * @start: Starting bit for bitmap traversing, wrapping around the bitmap end */ #define for_each_set_bit_wrap(bit, addr, size, start) \ for ((bit) = find_next_bit_wrap((addr), (size), (start)); \ (bit) < (size); \ (bit) = __for_each_wrap((addr), (size), (start), (bit) + 1)) /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset * @clump: location to store copy of current 8-bit clump * @bits: bitmap address to base the search on * @size: bitmap size in number of bits */ #define for_each_set_clump8(start, clump, bits, size) \ for ((start) = find_first_clump8(&(clump), (bits), (size)); \ (start) < (size); \ (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) #endif /*__LINUX_FIND_H_ */ |
| 66 36 36 36 66 66 66 66 66 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 38 | 1 2 3 4 5 6 7 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/quotaops.h> #include <linux/uuid.h> #include "ext4.h" #include "xattr.h" #include "ext4_jbd2.h" static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, const struct fscrypt_name *src) { memset(dst, 0, sizeof(*dst)); dst->usr_fname = src->usr_fname; dst->disk_name = src->disk_name; dst->hinfo.hash = src->hash; dst->hinfo.minor_hash = src->minor_hash; dst->crypto_buf = src->crypto_buf; } int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct ext4_filename *fname) { struct fscrypt_name name; int err; err = fscrypt_setup_filename(dir, iname, lookup, &name); if (err) return err; ext4_fname_from_fscrypt_name(fname, &name); #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); if (err) ext4_fname_free_filename(fname); #endif return err; } int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, struct ext4_filename *fname) { struct fscrypt_name name; int err; err = fscrypt_prepare_lookup(dir, dentry, &name); if (err) return err; ext4_fname_from_fscrypt_name(fname, &name); #if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); if (err) ext4_fname_free_filename(fname); #endif return err; } void ext4_fname_free_filename(struct ext4_filename *fname) { struct fscrypt_name name; name.crypto_buf = fname->crypto_buf; fscrypt_free_filename(&name); fname->crypto_buf.name = NULL; fname->usr_fname = NULL; fname->disk_name.name = NULL; #if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif } static bool uuid_is_zero(__u8 u[16]) { int i; for (i = 0; i < 16; i++) if (u[i]) return false; return true; } int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) { struct super_block *sb = file_inode(filp)->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); int err, err2; handle_t *handle; if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { err = mnt_want_write_file(filp); if (err) return err; handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto pwsalt_err_exit; } err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, EXT4_JTR_NONE); if (err) goto pwsalt_err_journal; lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); ext4_superblock_csum_set(sb); unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; pwsalt_err_exit: mnt_drop_write_file(filp); if (err) return err; } if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16)) return -EFAULT; return 0; } static int ext4_get_context(struct inode *inode, void *ctx, size_t len) { return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); } static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; int res, res2, credits, retries = 0; /* * Encrypting the root directory is not allowed because e2fsck expects * lost+found to exist and be unencrypted, and encrypting the root * directory would imply encrypting the lost+found directory as well as * the filename "lost+found" itself. */ if (inode->i_ino == EXT4_ROOT_INO) return -EPERM; if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) return -EINVAL; if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) return -EOPNOTSUPP; res = ext4_convert_inline_data(inode); if (res) return res; /* * If a journal handle was specified, then the encryption context is * being set on a new inode via inheritance and is part of a larger * transaction to create the inode. Otherwise the encryption context is * being set on an existing inode in its own transaction. Only in the * latter case should the "retry on ENOSPC" logic be used. */ if (handle) { res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, 0); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); /* * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ ext4_set_inode_flags(inode, false); } return res; } res = dquot_initialize(inode); if (res) return res; retry: res = ext4_xattr_set_credits(inode, len, false /* is_create */, &credits); if (res) return res; handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) return PTR_ERR(handle); res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, 0); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); /* * Update inode->i_flags - S_ENCRYPTED will be enabled, * S_DAX may be disabled */ ext4_set_inode_flags(inode, false); res = ext4_mark_inode_dirty(handle, inode); if (res) EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); } res2 = ext4_journal_stop(handle); if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; if (!res) res = res2; return res; } static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) { return EXT4_SB(sb)->s_dummy_enc_policy.policy; } static bool ext4_has_stable_inodes(struct super_block *sb) { return ext4_has_feature_stable_inodes(sb); } const struct fscrypt_operations ext4_cryptops = { .needs_bounce_pages = 1, .has_32bit_inodes = 1, .supports_subblock_data_units = 1, .legacy_key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, .get_dummy_policy = ext4_get_dummy_policy, .empty_dir = ext4_empty_dir, .has_stable_inodes = ext4_has_stable_inodes, }; |
| 11 852 63 29 29 26 27 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H #include <linux/bug.h> #include <linux/kernel.h> #include <linux/list.h> #include <uapi/linux/random.h> struct notifier_block; void add_device_randomness(const void *buf, size_t len); void __init add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); static inline void add_latent_entropy(void) { #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); #else add_device_randomness(NULL, 0); #endif } #if IS_ENABLED(CONFIG_VMGENID) void add_vmfork_randomness(const void *unique_vm_id, size_t len); int register_random_vmfork_notifier(struct notifier_block *nb); int unregister_random_vmfork_notifier(struct notifier_block *nb); #else static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif void get_random_bytes(void *buf, size_t len); u8 get_random_u8(void); u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 return get_random_u64(); #else return get_random_u32(); #endif } u32 __get_random_u32_below(u32 ceil); /* * Returns a random integer in the interval [0, ceil), with uniform * distribution, suitable for all uses. Fastest when ceil is a constant, but * still fast for variable ceil as well. */ static inline u32 get_random_u32_below(u32 ceil) { if (!__builtin_constant_p(ceil)) return __get_random_u32_below(ceil); /* * For the fast path, below, all operations on ceil are precomputed by * the compiler, so this incurs no overhead for checking pow2, doing * divisions, or branching based on integer size. The resultant * algorithm does traditional reciprocal multiplication (typically * optimized by the compiler into shifts and adds), rejecting samples * whose lower half would indicate a range indivisible by ceil. */ BUILD_BUG_ON_MSG(!ceil, "get_random_u32_below() must take ceil > 0"); if (ceil <= 1) return 0; for (;;) { if (ceil <= 1U << 8) { u32 mult = ceil * get_random_u8(); if (likely(is_power_of_2(ceil) || (u8)mult >= (1U << 8) % ceil)) return mult >> 8; } else if (ceil <= 1U << 16) { u32 mult = ceil * get_random_u16(); if (likely(is_power_of_2(ceil) || (u16)mult >= (1U << 16) % ceil)) return mult >> 16; } else { u64 mult = (u64)ceil * get_random_u32(); if (likely(is_power_of_2(ceil) || (u32)mult >= -ceil % ceil)) return mult >> 32; } } } /* * Returns a random integer in the interval (floor, U32_MAX], with uniform * distribution, suitable for all uses. Fastest when floor is a constant, but * still fast for variable floor as well. */ static inline u32 get_random_u32_above(u32 floor) { BUILD_BUG_ON_MSG(__builtin_constant_p(floor) && floor == U32_MAX, "get_random_u32_above() must take floor < U32_MAX"); return floor + 1 + get_random_u32_below(U32_MAX - floor); } /* * Returns a random integer in the interval [floor, ceil], with uniform * distribution, suitable for all uses. Fastest when floor and ceil are * constant, but still fast for variable floor and ceil as well. */ static inline u32 get_random_u32_inclusive(u32 floor, u32 ceil) { BUILD_BUG_ON_MSG(__builtin_constant_p(floor) && __builtin_constant_p(ceil) && (floor > ceil || ceil - floor == U32_MAX), "get_random_u32_inclusive() must take floor <= ceil"); return floor + get_random_u32_below(ceil - floor + 1); } void __init random_init_early(const char *command_line); void __init random_init(void); bool rng_is_initialized(void); int wait_for_random_bytes(void); int execute_with_initialized_rng(struct notifier_block *nb); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); return ret; } #define declare_get_random_var_wait(name, ret_type) \ static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ *out = get_random_ ## name(); \ return 0; \ } declare_get_random_var_wait(u8, u8) declare_get_random_var_wait(u16, u16) declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var /* * This is designed to be standalone for just prandom * users, but for now we include it from <linux/random.h> * for legacy reasons. */ #include <linux/prandom.h> #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); #endif #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif #endif /* _LINUX_RANDOM_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page, 1 << order); } #else static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return false; } #endif static unsigned long hugetlb_cma_size __initdata; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return; vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. * * Folios in this VMA will be aligned to, and at least the size of the * number of bytes returned by this function. * * Return: The default size of the folios allocated when backing a VMA. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else vma->vm_private_data = NULL; } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } mpol_cond_put(mpol); return folio; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(int *next_node, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(*next_node, nodes_allowed); *next_node = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) /* used to demote non-gigantic_huge pages as well */ static void __destroy_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i; int nr_pages = 1 << order; struct page *p; atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_pincount, 0); for (i = 1; i < nr_pages; i++) { p = folio_page(folio, i); p->flags &= ~PAGE_FLAGS_CHECK_AT_FREE; p->mapping = NULL; clear_compound_head(p); if (!demote) set_page_refcounted(p); } __folio_clear_head(folio); } static void destroy_compound_hugetlb_folio_for_demote(struct folio *folio, unsigned int order) { __destroy_compound_gigantic_folio(folio, order, true); } #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { __destroy_compound_gigantic_folio(folio, order, false); } static void free_gigantic_folio(struct folio *folio, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA int nid = folio_nid(folio); if (cma_release(hugetlb_cma[nid], &folio->page, 1 << order)) return; #endif free_contig_range(folio_pfn(folio), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct page *page; unsigned long nr_pages = pages_per_huge_page(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) return page_folio(page); } if (!(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) return page_folio(page); } } } #endif page = alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); return page ? page_folio(page) : NULL; } #else /* !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } static inline void free_gigantic_folio(struct folio *folio, unsigned int order) { } static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * A reference is held on the folio, except in the case of demote. * * Must be called with hugetlb lock held. */ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus, bool demote) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); /* * In the case of demote we do not ref count the page as it will soon * be turned into a page of smaller size. */ if (!demote) folio_ref_unfreeze(folio, 1); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { __remove_hugetlb_folio(h, folio, adjust_surplus, false); } static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, bool adjust_surplus) { __remove_hugetlb_folio(h, folio, adjust_surplus, true); } static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int zeroed; int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); /* * This folio is about to be managed by the hugetlb allocator and * should have no users. Drop our reference, and check for others * just in case. */ zeroed = folio_put_testzero(folio); if (unlikely(!zeroed)) /* * It is VERY unlikely soneone else has taken a ref * on the folio. In this case, we simply return as * free_huge_folio() will be called when this other ref * is dropped. */ return; arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Non-gigantic pages demoted from CMA allocated gigantic pages * need to be given back to CMA in free_gigantic_folio. */ if (hstate_is_gigantic(h) || hugetlb_cma_folio(folio, huge_page_order(h))) { destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_folio(folio, huge_page_order(h)); } else { INIT_LIST_HEAD(&folio->_deferred_list); folio_put(folio); } } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void __prep_account_new_huge_page(struct hstate *h, int nid) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; } static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { init_new_hugetlb_folio(h, folio); hugetlb_vmemmap_optimize_folio(h, folio); } static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } static bool __prep_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i, j; int nr_pages = 1 << order; struct page *p; __folio_clear_reserved(folio); for (i = 0; i < nr_pages; i++) { p = folio_page(folio, i); /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic * hugepages and clear the PG_reserved bit from all tail pages * too. Otherwise drivers using get_user_pages() to access tail * pages may get the reference counting wrong if they see * PG_reserved set on a tail page (despite the head page not * having PG_reserved set). Enforcing this consistency between * head and tail pages allows drivers to optimize away a check * on the head page when they need know if put_page() is needed * after get_user_pages(). */ if (i != 0) /* head page cleared above */ __ClearPageReserved(p); /* * Subtle and very unlikely * * Gigantic 'page allocators' such as memblock or cma will * return a set of pages with each page ref counted. We need * to turn this set of pages into a compound page with tail * page ref counts set to zero. Code such as speculative page * cache adding could take a ref on a 'to be' tail page. * We need to respect any increased ref count, and only set * the ref count to zero if count is currently 1. If count * is not 1, we return an error. An error return indicates * the set of pages can not be converted to a gigantic page. * The caller who allocated the pages should then discard the * pages using the appropriate free interface. * * In the case of demote, the ref count will be zero. */ if (!demote) { if (!page_ref_freeze(p, 1)) { pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); goto out_error; } } else { VM_BUG_ON_PAGE(page_count(p), p); } if (i != 0) set_compound_head(p, &folio->page); } __folio_set_head(folio); /* we rely on prep_new_hugetlb_folio to set the hugetlb flag */ folio_set_order(folio, order); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_pincount, 0); return true; out_error: /* undo page modifications made above */ for (j = 0; j < i; j++) { p = folio_page(folio, j); if (j != 0) clear_compound_head(p); set_page_refcounted(p); } /* need to clear PG_reserved on remaining tail pages */ for (; j < nr_pages; j++) { p = folio_page(folio, j); __ClearPageReserved(p); } return false; } static bool prep_compound_gigantic_folio(struct folio *folio, unsigned int order) { return __prep_compound_gigantic_folio(folio, order, false); } static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, unsigned int order) { return __prep_compound_gigantic_folio(folio, order, true); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct folio *folio; bool alloc_try_hard = true; bool retry = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; gfp_mask |= __GFP_COMP|__GFP_NOWARN; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = __folio_alloc(gfp_mask, order, nid, nmask); if (folio && !folio_ref_freeze(folio, 1)) { folio_put(folio); if (retry) { /* retry once */ retry = false; goto retry; } /* WOW! twice in a row. */ pr_warn("HugeTLB unexpected inflated folio ref count\n"); folio = NULL; } /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; bool retry = false; retry: if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!folio) return NULL; if (hstate_is_gigantic(h)) { if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* * Rare failure to convert pages to compound page. * Free pages and try again - ONCE! */ free_gigantic_folio(folio, huge_page_order(h)); if (!retry) { retry = true; goto retry; } return NULL; } } return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(h, folio); return folio; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages * * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; folio = __alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!folio) return NULL; prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return folio; } static void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, false); h->max_huge_pages++; goto out; } } else rc = 0; update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask | __GFP_NOWARN; gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { if (!new_folio) { spin_unlock_irq(&hugetlb_lock); new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) return -ENOMEM; __prep_new_hugetlb_folio(h, new_folio); goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) { /* Folio has a zero ref count, but needs a ref to be freed */ folio_ref_unfreeze(new_folio, 1); update_and_free_hugetlb_folio(h, new_folio, false); } return ret; } int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { struct hstate *h; struct folio *folio = page_folio(page); int ret = -EBUSY; /* * The page might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. * Return success when racing as if we dissolved the page ourselves. */ spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { spin_unlock_irq(&hugetlb_lock); return 0; } spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (hstate_is_gigantic(h)) return -ENOMEM; if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long map_chg, map_commit, nr_pages = pages_per_huge_page(h); long gbl_chg; int memcg_charge_ret, ret, idx; struct hugetlb_cgroup *h_cg = NULL; struct mem_cgroup *memcg; bool deferred_reserve; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; memcg = get_mem_cgroup_from_current(); memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); if (memcg_charge_ret == -ENOMEM) { mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) { if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve; if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) { spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } if (!memcg_charge_ret) mem_cgroup_commit_charge(folio, memcg); mem_cgroup_put(memcg); return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); out_end_reservation: vma_end_reservation(h, vma, addr); if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) { m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[node]); m->hstate = h; return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = zone_idx(folio_zone(folio)); int nid = folio_nid(folio); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; int ret; for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); ret = page_ref_freeze(page, 1); VM_BUG_ON(!ret); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* Prepare folio head */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); /* Initialize the necessary tail struct pages */ hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); prep_compound_head((struct page *)folio, huge_page_order(h)); } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry(m, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(h, folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = num_node_state(N_MEMORY), .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); if (!folio) break; free_huge_folio(folio); /* free it into the hugepage allocator */ } cond_resched(); } if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; job.thread_fn = hugetlb_pages_alloc_boot_node; job.start = 0; job.size = h->max_huge_pages; /* * job.max_threads is twice the num_node_state(N_MEMORY), * * Tests below indicate that a multiplier of 2 significantly improves * performance, and although larger values also provide improvements, * the gains are marginal. * * Therefore, choosing 2 as the multiplier strikes a good balance between * enhancing parallel processing capabilities and maintaining efficient * resource management. * * +------------+-------+-------+-------+-------+-------+ * | multiplier | 1 | 2 | 3 | 4 | 5 | * +------------+-------+-------+-------+-------+-------+ * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms | * | 2T 4node | 979ms | 679ms | 543ms | 489ms | 481ms | * | 50G 2node | 71ms | 44ms | 37ms | 30ms | 31ms | * +------------+-------+-------+-------+-------+-------+ */ job.max_threads = num_node_state(N_MEMORY) * 2; job.min_chunk = h->max_huge_pages / num_node_state(N_MEMORY) / 2; padata_do_multithreaded(&job); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; static bool initialized __initdata; /* skip gigantic hugepages allocation if hugetlb_cma enabled */ if (hstate_is_gigantic(h) && hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } /* hugetlb_hstate_alloc_pages will be called many times, initialize huge_boot_pages once */ if (!initialized) { int i = 0; for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); initialized = true; } /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) { int i, nid = folio_nid(folio); struct hstate *target_hstate; struct page *subpage; struct folio *inner_folio; int rc = 0; target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); /* * If vmemmap already existed for folio, the remove routine above would * have cleared the hugetlb folio flag. Hence the folio is technically * no longer a hugetlb folio. hugetlb_vmemmap_restore_folio can only be * passed hugetlb folios and will BUG otherwise. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { /* Allocation of vmemmmap failed, we can not demote folio */ spin_lock_irq(&hugetlb_lock); folio_ref_unfreeze(folio, 1); add_hugetlb_folio(h, folio, false); return rc; } } /* * Use destroy_compound_hugetlb_folio_for_demote for all huge page * sizes as it will not ref count folios. */ destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h)); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold h->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&target_hstate->resize_lock); for (i = 0; i < pages_per_huge_page(h); i += pages_per_huge_page(target_hstate)) { subpage = folio_page(folio, i); inner_folio = page_folio(subpage); if (hstate_is_gigantic(target_hstate)) prep_compound_gigantic_folio_for_demote(inner_folio, target_hstate->order); else prep_compound_page(subpage, target_hstate->order); folio_change_private(inner_folio, NULL); prep_new_hugetlb_folio(target_hstate, inner_folio, nid); free_huge_folio(inner_folio); } mutex_unlock(&target_hstate->resize_lock); spin_lock_irq(&hugetlb_lock); /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ h->max_huge_pages--; target_hstate->max_huge_pages += pages_per_huge_page(h) / pages_per_huge_page(target_hstate); return rc; } static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct folio *folio; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!h->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { list_for_each_entry(folio, &h->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; return demote_free_hugetlb_folio(h, folio); } } /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR_WO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_WO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock_irq(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static ssize_t demote_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned long nr_demote; unsigned long nr_available; nodemask_t nodes_allowed, *n_mask; struct hstate *h; int err; int nid; err = kstrtoul(buf, 10, &nr_demote); if (err) return err; h = kobj_to_hstate(kobj, &nid); if (nid != NUMA_NO_NODE) { init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } else { n_mask = &node_states[N_MEMORY]; } /* Synchronize with other sysfs operations modifying huge pages */ mutex_lock(&h->resize_lock); spin_lock_irq(&hugetlb_lock); while (nr_demote) { /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; else nr_available = h->free_huge_pages; nr_available -= h->resv_huge_pages; if (!nr_available) break; err = demote_pool_huge_page(h, n_mask); if (err) break; nr_demote--; } spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); if (err) return err; return len; } HSTATE_ATTR_WO(demote); static ssize_t demote_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; return sysfs_emit(buf, "%lukB\n", demote_size); } static ssize_t demote_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct hstate *h, *demote_hstate; unsigned long demote_size; unsigned int demote_order; demote_size = (unsigned long)memparse(buf, NULL); demote_hstate = size_to_hstate(demote_size); if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; if (demote_order < HUGETLB_PAGE_ORDER) return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, NULL); if (demote_order >= h->order) return -EINVAL; /* resize_lock synchronizes access to demote size and writes */ mutex_lock(&h->resize_lock); h->demote_order = demote_order; mutex_unlock(&h->resize_lock); return count; } HSTATE_ATTR(demote_size); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static struct attribute *hstate_demote_attrs[] = { &demote_size_attr.attr, &demote_attr.attr, NULL, }; static const struct attribute_group hstate_demote_attr_group = { .attrs = hstate_demote_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } if (h->demote_order) { retval = sysfs_create_group(hstate_kobjs[hi], &hstate_demote_attr_group); if (retval) { pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } } return 0; } #ifdef CONFIG_NUMA static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; if (!hstate_kobj) continue; if (h->demote_order) sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); kobject_put(hstate_kobj); nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (!hugetlb_sysfs_initialized) return; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_online_node(nid) hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif #ifdef CONFIG_CMA static void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_check(void) { } #endif static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } #ifdef CONFIG_NUMA hugetlb_sysfs_initialized = true; #endif hugetlb_register_all_nodes(); } #ifdef CONFIG_SYSCTL static void hugetlb_sysctl_init(void); #else static inline void hugetlb_sysctl_init(void) { } #endif static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); h = &hstates[hugetlb_max_hstate++]; mutex_init(&h->resize_lock); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 1; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } /* * Global state is always initialized later in hugetlb_init. * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 1; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 1; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } static int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ static int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock_irq(&hugetlb_lock); } out: return ret; } static struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, }, #ifdef CONFIG_NUMA { .procname = "nr_hugepages_mempolicy", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, #endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, }; static void hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } else hugetlb_vma_lock_alloc(vma); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. */ if (addr & ~PUD_MASK) { /* * hugetlb_vm_op_split is called right before we attempt to * split the VMA. We will need to unshare PMDs in the old and * new VMAs, so let's unshare before we split. */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) hugetlb_unshare_pmds(vma, floor, ceil); } return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } /* * If the pagetables are shared don't copy or take references. * * dst_pte == src_pte is the common case of src/dest sharing. * However, src could have 'unshared' and dst shares with * another vma. So page_count of ptep page is checked instead * to reliably determine whether pte is shared. */ if (page_count(virt_to_page(dst_pte)) > 1) { addr |= last_addr_mask; continue; } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); again: if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(src_pte))) continue; if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation = false; unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(page_folio(page)); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(page_folio(page))) { folio_set_hugetlb_restore_reserve(page_folio(page)); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock(ptl); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation && vma_needs_reservation(h, vma, address)) vma_add_reservation(h, vma, address); tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. */ if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) return VM_FAULT_SIGSEGV; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_folio != pagecache_folio) outside_reserve = 1; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, &old_folio->page, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct folio *folio; pte_t new_pte; bool new_folio, new_pagecache_folio = false; u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, 0); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } clear_huge_page(&folio->page, vmf->real_address, pages_per_huge_page(h)); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(vmf->pte), vmf->orig_pte)) goto backout; if (anon_rmap) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(folio, vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct folio *pagecache_folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(vmf.pte); if (huge_pte_none_mostly(vmf.orig_pte)) { if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } } /* * Other PTE markers should be handled the same way as none PTE. * * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); } ret = 0; /* * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this * point, so this check prevents the kernel from going below assuming * that we have an active hugepage in pagecache. This goto expects * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned) * check will properly handle it. */ if (!pte_present(vmf.orig_pte)) { if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.pte); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte))) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. Also lookup the pagecache page now as it is used to * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, vmf.pgoff); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } /* * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and * pagecache_folio, so here we need take the former one * when folio != pagecache_folio or !pagecache_folio. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) { need_wait_lock = 1; goto out_ptl; } folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { ret = hugetlb_wp(pagecache_folio, &vmf); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_put_page: if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio); out_ptl: spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } out_mutex: hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; int writable; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ if (wp_enabled || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { /* Nothing to do. */ } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte = pte; if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissons do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } else { /* None pte */ if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); } spin_unlock(ptl); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages > 0 ? (pages << h->order) : pages; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg = -1, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ hugetlb_vma_lock_alloc(vma); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) goto out_err; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL); } return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /* * unmap huge page backed by shared pte. * * Hugetlb pte page is ref counted at the time of mapping. If pte is shared * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); return 1; } #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* * These functions are overwritable if your architecture needs its own * behavior. */ bool isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } void folio_putback_active_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); set_page_owner_migrate_reason(&new_folio->page, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } } static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { int nid, count = 0; unsigned long tmp; char *s = p; while (*s) { if (sscanf(s, "%lu%n", &tmp, &count) != 1) break; if (s[count] == ':') { if (tmp >= MAX_NUMNODES) break; nid = array_index_nospec(tmp, MAX_NUMNODES); s += count + 1; tmp = memparse(s, &s); hugetlb_cma_size_in_node[nid] = tmp; hugetlb_cma_size += tmp; /* * Skip the separator if have one, otherwise * break the parsing. */ if (*s == ',') s++; else break; } else { hugetlb_cma_size = memparse(p, &p); break; } } return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; bool node_specific_cma_alloc = false; int nid; /* * HugeTLB CMA reservation is required for gigantic * huge pages which could not be allocated via the * page allocator. Just warn if there is any change * breaking this assumption. */ VM_WARN_ON(order <= MAX_PAGE_ORDER); cma_reserve_called = true; if (!hugetlb_cma_size) return; for (nid = 0; nid < MAX_NUMNODES; nid++) { if (hugetlb_cma_size_in_node[nid] == 0) continue; if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; continue; } if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", nid, (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; } else { node_specific_cma_alloc = true; } } /* Validate the CMA size again in case some invalid nodes specified. */ if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size = 0; return; } if (!node_specific_cma_alloc) { /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } reserved = 0; for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; if (node_specific_cma_alloc) { if (hugetlb_cma_size_in_node[nid] == 0) continue; size = hugetlb_cma_size_in_node[nid]; } else { size = min(per_node, hugetlb_cma_size - reserved); } size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); /* * Note that 'order per bit' is based on smallest size that * may be returned to CMA allocator in the case of * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, HUGETLB_PAGE_ORDER, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } if (!reserved) /* * hugetlb_cma_size is used to determine if allocations from * cma are possible. Set to zero if no cma regions are set up. */ hugetlb_cma_size = 0; } static void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 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 | // 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 (! vel) /* set volume to zero -- note off */ // type = SNDRV_SEQ_EVENT_NOTEOFF; //else 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; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Checksum updating actions * * Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org> */ #include <linux/types.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/netlink.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/icmp.h> #include <linux/icmpv6.h> #include <linux/igmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include <net/sctp/checksum.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_csum.h> #include <net/tc_act/tc_csum.h> #include <net/tc_wrapper.h> static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy, NULL); if (err < 0) return err; if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_csum_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) /* dont override defaults */ return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; p = to_tcf_csum(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { err = -ENOMEM; goto put_chain; } params_new->update_flags = parm->update_flags; spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(p->params, params_new, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params_new) kfree_rcu(params_new, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } /** * tcf_csum_skb_nextlayer - Get next layer pointer * @skb: sk_buff to use * @ihl: previous summed headers length * @ipl: complete packet length * @jhl: next header length * * Check the expected next layer availability in the specified sk_buff. * Return the next layer pointer if pass, NULL otherwise. */ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, unsigned int jhl) { int ntkoff = skb_network_offset(skb); int hl = ihl + jhl; if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || skb_try_make_writable(skb, hl + ntkoff)) return NULL; else return (void *)(skb_network_header(skb) + ihl); } static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmphdr *icmph; icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph)); if (icmph == NULL) return 0; icmph->checksum = 0; skb->csum = csum_partial(icmph, ipl - ihl, 0); icmph->checksum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_igmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct igmphdr *igmph; igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph)); if (igmph == NULL) return 0; igmph->csum = 0; skb->csum = csum_partial(igmph, ipl - ihl, 0); igmph->csum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmp6hdr *icmp6h; const struct ipv6hdr *ip6h; icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h)); if (icmp6h == NULL) return 0; ip6h = ipv6_hdr(skb); icmp6h->icmp6_cksum = 0; skb->csum = csum_partial(icmp6h, ipl - ihl, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_ICMPV6, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct iphdr *iph; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; iph = ip_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = tcp_v4_check(ipl - ihl, iph->saddr, iph->daddr, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct ipv6hdr *ip6h; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; ip6h = ipv6_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_TCP, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct iphdr *iph; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use iph->tot_len, or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; iph = ip_hdr(skb); ul = ntohs(udph->len); if (udplite || udph->check) { udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, ul, iph->protocol, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; } skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct ipv6hdr *ip6h; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; ip6h = ipv6_hdr(skb); ul = ntohs(udph->len); udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul, udplite ? IPPROTO_UDPLITE : IPPROTO_UDP, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct sctphdr *sctph; if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); if (!sctph) return 0; sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); skb_reset_csum_not_inet(skb); return 1; } static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) { const struct iphdr *iph; int ntkoff; ntkoff = skb_network_offset(skb); if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff)) goto fail; iph = ip_hdr(skb); switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { case IPPROTO_ICMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_IGMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP) if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 0)) goto fail; break; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 1)) goto fail; break; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff)) goto fail; ip_send_check(ip_hdr(skb)); } return 1; fail: return 0; } static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl, unsigned int *pl) { int off, len, optlen; unsigned char *xh = (void *)ip6xh; off = sizeof(*ip6xh); len = ixhl - off; while (len > 1) { switch (xh[off]) { case IPV6_TLV_PAD1: optlen = 1; break; case IPV6_TLV_JUMBO: optlen = xh[off + 1] + 2; if (optlen != 6 || len < 6 || (off & 3) != 2) /* wrong jumbo option length/alignment */ return 0; *pl = ntohl(*(__be32 *)(xh + off + 2)); goto done; default: optlen = xh[off + 1] + 2; if (optlen > len) /* ignore obscure options */ goto done; break; } off += optlen; len -= optlen; } done: return 1; } static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) { struct ipv6hdr *ip6h; struct ipv6_opt_hdr *ip6xh; unsigned int hl, ixhl; unsigned int pl; int ntkoff; u8 nexthdr; ntkoff = skb_network_offset(skb); hl = sizeof(*ip6h); if (!pskb_may_pull(skb, hl + ntkoff)) goto fail; ip6h = ipv6_hdr(skb); pl = ntohs(ip6h->payload_len); nexthdr = ip6h->nexthdr; do { switch (nexthdr) { case NEXTHDR_FRAGMENT: goto ignore_skb; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); ixhl = ipv6_optlen(ip6xh); if (!pskb_may_pull(skb, hl + ixhl + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); if ((nexthdr == NEXTHDR_HOP) && !(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl))) goto fail; nexthdr = ip6xh->nexthdr; hl += ixhl; break; case IPPROTO_ICMPV6: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv6_icmp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv6_tcp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 0)) goto fail; goto done; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 1)) goto fail; goto done; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; default: goto ignore_skb; } } while (pskb_may_pull(skb, hl + 1 + ntkoff)); done: ignore_skb: return 1; fail: return 0; } TC_INDIRECT_SCOPE int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); bool orig_vlan_tag_present = false; unsigned int vlan_hdr_count = 0; struct tcf_csum_params *params; u32 update_flags; __be16 protocol; int action; params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); tcf_action_update_bstats(&p->common, skb); action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) goto drop; update_flags = params->update_flags; protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_IPV6): if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_8021AD): fallthrough; case cpu_to_be16(ETH_P_8021Q): if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { protocol = skb->protocol; orig_vlan_tag_present = true; } else { struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data; protocol = vlan->h_vlan_encapsulated_proto; skb_pull(skb, VLAN_HLEN); skb_reset_network_header(skb); vlan_hdr_count++; } goto again; } out: /* Restore the skb for the pulled VLAN tags */ while (vlan_hdr_count--) { skb_push(skb, VLAN_HLEN); skb_reset_network_header(skb); } return action; drop: tcf_action_inc_drop_qstats(&p->common); action = TC_ACT_SHOT; goto out; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_csum *p = to_tcf_csum(a); struct tcf_csum_params *params; struct tc_csum opt = { .index = p->tcf_index, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&p->tcf_lock); params = rcu_dereference_protected(p->params, lockdep_is_held(&p->tcf_lock)); opt.action = p->tcf_action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_csum_cleanup(struct tc_action *a) { struct tcf_csum *p = to_tcf_csum(a); struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); if (params) kfree_rcu(params, rcu); } static size_t tcf_csum_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_csum)); } static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; entry->id = FLOW_ACTION_CSUM; entry->csum_flags = tcf_csum_update_flags(act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_CSUM; } return 0; } static struct tc_action_ops act_csum_ops = { .kind = "csum", .id = TCA_ID_CSUM, .owner = THIS_MODULE, .act = tcf_csum_act, .dump = tcf_csum_dump, .init = tcf_csum_init, .cleanup = tcf_csum_cleanup, .get_fill_size = tcf_csum_get_fill_size, .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; MODULE_ALIAS_NET_ACT("csum"); static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_csum_ops.net_id); } static struct pernet_operations csum_net_ops = { .init = csum_init_net, .exit_batch = csum_exit_net, .id = &act_csum_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Checksum updating actions"); MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { return tcf_register_action(&act_csum_ops, &csum_net_ops); } static void __exit csum_cleanup_module(void) { tcf_unregister_action(&act_csum_ops, &csum_net_ops); } module_init(csum_init_module); module_exit(csum_cleanup_module); |
| 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 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BYTEORDER_GENERIC_H #define _LINUX_BYTEORDER_GENERIC_H /* * linux/byteorder/generic.h * Generic Byte-reordering support * * The "... p" macros, like le64_to_cpup, can be used with pointers * to unaligned data, but there will be a performance penalty on * some architectures. Use get_unaligned for unaligned data. * * Francois-Rene Rideau <fare@tunes.org> 19970707 * gathered all the good ideas from all asm-foo/byteorder.h into one file, * cleaned them up. * I hope it is compliant with non-GCC compilers. * I decided to put __BYTEORDER_HAS_U64__ in byteorder.h, * because I wasn't sure it would be ok to put it in types.h * Upgraded it to 2.1.43 * Francois-Rene Rideau <fare@tunes.org> 19971012 * Upgraded it to 2.1.57 * to please Linus T., replaced huge #ifdef's between little/big endian * by nestedly #include'd files. * Francois-Rene Rideau <fare@tunes.org> 19971205 * Made it to 2.1.71; now a facelift: * Put files under include/linux/byteorder/ * Split swab from generic support. * * TODO: * = Regular kernel maintainers could also replace all these manual * byteswap macros that remain, disseminated among drivers, * after some grep or the sources... * = Linus might want to rename all these macros and files to fit his taste, * to fit his personal naming scheme. * = it seems that a few drivers would also appreciate * nybble swapping support... * = every architecture could add their byteswap macro in asm/byteorder.h * see how some architectures already do (i386, alpha, ppc, etc) * = cpu_to_beXX and beXX_to_cpu might some day need to be well * distinguished throughout the kernel. This is not the case currently, * since little endian, big endian, and pdp endian machines needn't it. * But this might be the case for, say, a port of Linux to 20/21 bit * architectures (and F21 Linux addict around?). */ /* * The following macros are to be defined by <asm/byteorder.h>: * * Conversion of long and short int between network and host format * ntohl(__u32 x) * ntohs(__u16 x) * htonl(__u32 x) * htons(__u16 x) * It seems that some programs (which? where? or perhaps a standard? POSIX?) * might like the above to be functions, not macros (why?). * if that's true, then detect them, and take measures. * Anyway, the measure is: define only ___ntohl as a macro instead, * and in a separate file, have * unsigned long inline ntohl(x){return ___ntohl(x);} * * The same for constant arguments * __constant_ntohl(__u32 x) * __constant_ntohs(__u16 x) * __constant_htonl(__u32 x) * __constant_htons(__u16 x) * * Conversion of XX-bit integers (16- 32- or 64-) * between native CPU format and little/big endian format * 64-bit stuff only defined for proper architectures * cpu_to_[bl]eXX(__uXX x) * [bl]eXX_to_cpu(__uXX x) * * The same, but takes a pointer to the value to convert * cpu_to_[bl]eXXp(__uXX x) * [bl]eXX_to_cpup(__uXX x) * * The same, but change in situ * cpu_to_[bl]eXXs(__uXX x) * [bl]eXX_to_cpus(__uXX x) * * See asm-foo/byteorder.h for examples of how to provide * architecture-optimized versions * */ #define cpu_to_le64 __cpu_to_le64 #define le64_to_cpu __le64_to_cpu #define cpu_to_le32 __cpu_to_le32 #define le32_to_cpu __le32_to_cpu #define cpu_to_le16 __cpu_to_le16 #define le16_to_cpu __le16_to_cpu #define cpu_to_be64 __cpu_to_be64 #define be64_to_cpu __be64_to_cpu #define cpu_to_be32 __cpu_to_be32 #define be32_to_cpu __be32_to_cpu #define cpu_to_be16 __cpu_to_be16 #define be16_to_cpu __be16_to_cpu #define cpu_to_le64p __cpu_to_le64p #define le64_to_cpup __le64_to_cpup #define cpu_to_le32p __cpu_to_le32p #define le32_to_cpup __le32_to_cpup #define cpu_to_le16p __cpu_to_le16p #define le16_to_cpup __le16_to_cpup #define cpu_to_be64p __cpu_to_be64p #define be64_to_cpup __be64_to_cpup #define cpu_to_be32p __cpu_to_be32p #define be32_to_cpup __be32_to_cpup #define cpu_to_be16p __cpu_to_be16p #define be16_to_cpup __be16_to_cpup #define cpu_to_le64s __cpu_to_le64s #define le64_to_cpus __le64_to_cpus #define cpu_to_le32s __cpu_to_le32s #define le32_to_cpus __le32_to_cpus #define cpu_to_le16s __cpu_to_le16s #define le16_to_cpus __le16_to_cpus #define cpu_to_be64s __cpu_to_be64s #define be64_to_cpus __be64_to_cpus #define cpu_to_be32s __cpu_to_be32s #define be32_to_cpus __be32_to_cpus #define cpu_to_be16s __cpu_to_be16s #define be16_to_cpus __be16_to_cpus /* * They have to be macros in order to do the constant folding * correctly - if the argument passed into a inline function * it is no longer constant according to gcc.. */ #undef ntohl #undef ntohs #undef htonl #undef htons #define ___htonl(x) __cpu_to_be32(x) #define ___htons(x) __cpu_to_be16(x) #define ___ntohl(x) __be32_to_cpu(x) #define ___ntohs(x) __be16_to_cpu(x) #define htonl(x) ___htonl(x) #define ntohl(x) ___ntohl(x) #define htons(x) ___htons(x) #define ntohs(x) ___ntohs(x) static inline void le16_add_cpu(__le16 *var, u16 val) { *var = cpu_to_le16(le16_to_cpu(*var) + val); } static inline void le32_add_cpu(__le32 *var, u32 val) { *var = cpu_to_le32(le32_to_cpu(*var) + val); } static inline void le64_add_cpu(__le64 *var, u64 val) { *var = cpu_to_le64(le64_to_cpu(*var) + val); } /* XXX: this stuff can be optimized */ static inline void le32_to_cpu_array(u32 *buf, unsigned int words) { while (words--) { __le32_to_cpus(buf); buf++; } } static inline void cpu_to_le32_array(u32 *buf, unsigned int words) { while (words--) { __cpu_to_le32s(buf); buf++; } } static inline void be16_add_cpu(__be16 *var, u16 val) { *var = cpu_to_be16(be16_to_cpu(*var) + val); } static inline void be32_add_cpu(__be32 *var, u32 val) { *var = cpu_to_be32(be32_to_cpu(*var) + val); } static inline void be64_add_cpu(__be64 *var, u64 val) { *var = cpu_to_be64(be64_to_cpu(*var) + val); } static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); } static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); } #endif /* _LINUX_BYTEORDER_GENERIC_H */ |
| 152 151 152 151 97 99 | 1 2 3 4 5 6 7 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 | #include <linux/bpf.h> #include <linux/vmalloc.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/namei.h> #include <linux/user_namespace.h> #include <linux/security.h> static bool bpf_ns_capable(struct user_namespace *ns, int cap) { return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); } bool bpf_token_capable(const struct bpf_token *token, int cap) { struct user_namespace *userns; /* BPF token allows ns_capable() level of capabilities */ userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; if (token && security_bpf_token_capable(token, cap) < 0) return false; return true; } void bpf_token_inc(struct bpf_token *token) { atomic64_inc(&token->refcnt); } static void bpf_token_free(struct bpf_token *token) { security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } static void bpf_token_put_deferred(struct work_struct *work) { struct bpf_token *token = container_of(work, struct bpf_token, work); bpf_token_free(token); } void bpf_token_put(struct bpf_token *token) { if (!token) return; if (!atomic64_dec_and_test(&token->refcnt)) return; INIT_WORK(&token->work, bpf_token_put_deferred); schedule_work(&token->work); } static int bpf_token_release(struct inode *inode, struct file *filp) { struct bpf_token *token = filp->private_data; bpf_token_put(token); return 0; } static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_token *token = filp->private_data; u64 mask; BUILD_BUG_ON(__MAX_BPF_CMD >= 64); mask = BIT_ULL(__MAX_BPF_CMD) - 1; if ((token->allowed_cmds & mask) == mask) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; if ((token->allowed_maps & mask) == mask) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; if ((token->allowed_progs & mask) == mask) seq_printf(m, "allowed_progs:\tany\n"); else seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; if ((token->allowed_attachs & mask) == mask) seq_printf(m, "allowed_attachs:\tany\n"); else seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" static const struct inode_operations bpf_token_iops = { }; static const struct file_operations bpf_token_fops = { .release = bpf_token_release, .show_fdinfo = bpf_token_show_fdinfo, }; int bpf_token_create(union bpf_attr *attr) { struct bpf_mount_opts *mnt_opts; struct bpf_token *token = NULL; struct user_namespace *userns; struct inode *inode; struct file *file; struct path path; struct fd f; umode_t mode; int err, fd; f = fdget(attr->token_create.bpffs_fd); if (!f.file) return -EBADF; path = f.file->f_path; path_get(&path); fdput(f); if (path.dentry != path.mnt->mnt_sb->s_root) { err = -EINVAL; goto out_path; } if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { err = -EINVAL; goto out_path; } err = path_permission(&path, MAY_ACCESS); if (err) goto out_path; userns = path.dentry->d_sb->s_user_ns; /* * Enforce that creators of BPF tokens are in the same user * namespace as the BPF FS instance. This makes reasoning about * permissions a lot easier and we can always relax this later. */ if (current_user_ns() != userns) { err = -EPERM; goto out_path; } if (!ns_capable(userns, CAP_BPF)) { err = -EPERM; goto out_path; } /* Creating BPF token in init_user_ns doesn't make much sense. */ if (current_user_ns() == &init_user_ns) { err = -EOPNOTSUPP; goto out_path; } mnt_opts = path.dentry->d_sb->s_fs_info; if (mnt_opts->delegate_cmds == 0 && mnt_opts->delegate_maps == 0 && mnt_opts->delegate_progs == 0 && mnt_opts->delegate_attachs == 0) { err = -ENOENT; /* no BPF token delegation is set up */ goto out_path; } mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_path; } inode->i_op = &bpf_token_iops; inode->i_fop = &bpf_token_fops; clear_nlink(inode); /* make sure it is unlinked */ file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); if (IS_ERR(file)) { iput(inode); err = PTR_ERR(file); goto out_path; } token = kzalloc(sizeof(*token), GFP_USER); if (!token) { err = -ENOMEM; goto out_file; } atomic64_set(&token->refcnt, 1); /* remember bpffs owning userns for future ns_capable() checks */ token->userns = get_user_ns(userns); token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; err = security_bpf_token_create(token, attr, &path); if (err) goto out_token; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_token; } file->private_data = token; fd_install(fd, file); path_put(&path); return fd; out_token: bpf_token_free(token); out_file: fput(file); out_path: path_put(&path); return err; } struct bpf_token *bpf_token_get_from_fd(u32 ufd) { struct fd f = fdget(ufd); struct bpf_token *token; if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &bpf_token_fops) { fdput(f); return ERR_PTR(-EINVAL); } token = f.file->private_data; bpf_token_inc(token); fdput(f); return token; } bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; if (!(token->allowed_cmds & BIT_ULL(cmd))) return false; return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) { if (!token || type >= __MAX_BPF_MAP_TYPE) return false; return token->allowed_maps & BIT_ULL(type); } bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type) { if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) return false; return (token->allowed_progs & BIT_ULL(prog_type)) && (token->allowed_attachs & BIT_ULL(attach_type)); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2001 Paul Stewart * Copyright (c) 2001 Vojtech Pavlik * * HID char devices, giving access to raw HID device events. */ /* * * Should you need to contact me, the author, you can do so either by * e-mail - mail your message to Paul Stewart <stewart@wetlogic.net> */ #include <linux/poll.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/module.h> #include <linux/init.h> #include <linux/input.h> #include <linux/usb.h> #include <linux/hid.h> #include <linux/hiddev.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/nospec.h> #include "usbhid.h" #ifdef CONFIG_USB_DYNAMIC_MINORS #define HIDDEV_MINOR_BASE 0 #define HIDDEV_MINORS 256 #else #define HIDDEV_MINOR_BASE 96 #define HIDDEV_MINORS 16 #endif #define HIDDEV_BUFFER_SIZE 2048 struct hiddev_list { struct hiddev_usage_ref buffer[HIDDEV_BUFFER_SIZE]; int head; int tail; unsigned flags; struct fasync_struct *fasync; struct hiddev *hiddev; struct list_head node; struct mutex thread_lock; }; /* * Find a report, given the report's type and ID. The ID can be specified * indirectly by REPORT_ID_FIRST (which returns the first report of the given * type) or by (REPORT_ID_NEXT | old_id), which returns the next report of the * given type which follows old_id. */ static struct hid_report * hiddev_lookup_report(struct hid_device *hid, struct hiddev_report_info *rinfo) { unsigned int flags = rinfo->report_id & ~HID_REPORT_ID_MASK; unsigned int rid = rinfo->report_id & HID_REPORT_ID_MASK; struct hid_report_enum *report_enum; struct hid_report *report; struct list_head *list; if (rinfo->report_type < HID_REPORT_TYPE_MIN || rinfo->report_type > HID_REPORT_TYPE_MAX) return NULL; report_enum = hid->report_enum + (rinfo->report_type - HID_REPORT_TYPE_MIN); switch (flags) { case 0: /* Nothing to do -- report_id is already set correctly */ break; case HID_REPORT_ID_FIRST: if (list_empty(&report_enum->report_list)) return NULL; list = report_enum->report_list.next; report = list_entry(list, struct hid_report, list); rinfo->report_id = report->id; break; case HID_REPORT_ID_NEXT: report = report_enum->report_id_hash[rid]; if (!report) return NULL; list = report->list.next; if (list == &report_enum->report_list) return NULL; report = list_entry(list, struct hid_report, list); rinfo->report_id = report->id; break; default: return NULL; } return report_enum->report_id_hash[rinfo->report_id]; } /* * Perform an exhaustive search of the report table for a usage, given its * type and usage id. */ static struct hid_field * hiddev_lookup_usage(struct hid_device *hid, struct hiddev_usage_ref *uref) { int i, j; struct hid_report *report; struct hid_report_enum *report_enum; struct hid_field *field; if (uref->report_type < HID_REPORT_TYPE_MIN || uref->report_type > HID_REPORT_TYPE_MAX) return NULL; report_enum = hid->report_enum + (uref->report_type - HID_REPORT_TYPE_MIN); list_for_each_entry(report, &report_enum->report_list, list) { for (i = 0; i < report->maxfield; i++) { field = report->field[i]; for (j = 0; j < field->maxusage; j++) { if (field->usage[j].hid == uref->usage_code) { uref->report_id = report->id; uref->field_index = i; uref->usage_index = j; return field; } } } } return NULL; } static void hiddev_send_event(struct hid_device *hid, struct hiddev_usage_ref *uref) { struct hiddev *hiddev = hid->hiddev; struct hiddev_list *list; unsigned long flags; spin_lock_irqsave(&hiddev->list_lock, flags); list_for_each_entry(list, &hiddev->list, node) { if (uref->field_index != HID_FIELD_INDEX_NONE || (list->flags & HIDDEV_FLAG_REPORT) != 0) { list->buffer[list->head] = *uref; list->head = (list->head + 1) & (HIDDEV_BUFFER_SIZE - 1); kill_fasync(&list->fasync, SIGIO, POLL_IN); } } spin_unlock_irqrestore(&hiddev->list_lock, flags); wake_up_interruptible(&hiddev->wait); } /* * This is where hid.c calls into hiddev to pass an event that occurred over * the interrupt pipe */ void hiddev_hid_event(struct hid_device *hid, struct hid_field *field, struct hid_usage *usage, __s32 value) { unsigned type = field->report_type; struct hiddev_usage_ref uref; uref.report_type = (type == HID_INPUT_REPORT) ? HID_REPORT_TYPE_INPUT : ((type == HID_OUTPUT_REPORT) ? HID_REPORT_TYPE_OUTPUT : ((type == HID_FEATURE_REPORT) ? HID_REPORT_TYPE_FEATURE : 0)); uref.report_id = field->report->id; uref.field_index = field->index; uref.usage_index = (usage - field->usage); uref.usage_code = usage->hid; uref.value = value; hiddev_send_event(hid, &uref); } EXPORT_SYMBOL_GPL(hiddev_hid_event); void hiddev_report_event(struct hid_device *hid, struct hid_report *report) { unsigned type = report->type; struct hiddev_usage_ref uref; memset(&uref, 0, sizeof(uref)); uref.report_type = (type == HID_INPUT_REPORT) ? HID_REPORT_TYPE_INPUT : ((type == HID_OUTPUT_REPORT) ? HID_REPORT_TYPE_OUTPUT : ((type == HID_FEATURE_REPORT) ? HID_REPORT_TYPE_FEATURE : 0)); uref.report_id = report->id; uref.field_index = HID_FIELD_INDEX_NONE; hiddev_send_event(hid, &uref); } /* * fasync file op */ static int hiddev_fasync(int fd, struct file *file, int on) { struct hiddev_list *list = file->private_data; return fasync_helper(fd, file, on, &list->fasync); } /* * release file op */ static int hiddev_release(struct inode * inode, struct file * file) { struct hiddev_list *list = file->private_data; unsigned long flags; spin_lock_irqsave(&list->hiddev->list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hiddev->list_lock, flags); mutex_lock(&list->hiddev->existancelock); if (!--list->hiddev->open) { if (list->hiddev->exist) { hid_hw_close(list->hiddev->hid); hid_hw_power(list->hiddev->hid, PM_HINT_NORMAL); } else { mutex_unlock(&list->hiddev->existancelock); kfree(list->hiddev); vfree(list); return 0; } } mutex_unlock(&list->hiddev->existancelock); vfree(list); return 0; } static int __hiddev_open(struct hiddev *hiddev, struct file *file) { struct hiddev_list *list; int error; lockdep_assert_held(&hiddev->existancelock); list = vzalloc(sizeof(*list)); if (!list) return -ENOMEM; mutex_init(&list->thread_lock); list->hiddev = hiddev; if (!hiddev->open++) { error = hid_hw_power(hiddev->hid, PM_HINT_FULLON); if (error < 0) goto err_drop_count; error = hid_hw_open(hiddev->hid); if (error < 0) goto err_normal_power; } spin_lock_irq(&hiddev->list_lock); list_add_tail(&list->node, &hiddev->list); spin_unlock_irq(&hiddev->list_lock); file->private_data = list; return 0; err_normal_power: hid_hw_power(hiddev->hid, PM_HINT_NORMAL); err_drop_count: hiddev->open--; vfree(list); return error; } /* * open file op */ static int hiddev_open(struct inode *inode, struct file *file) { struct usb_interface *intf; struct hid_device *hid; struct hiddev *hiddev; int res; intf = usbhid_find_interface(iminor(inode)); if (!intf) return -ENODEV; hid = usb_get_intfdata(intf); hiddev = hid->hiddev; mutex_lock(&hiddev->existancelock); res = hiddev->exist ? __hiddev_open(hiddev, file) : -ENODEV; mutex_unlock(&hiddev->existancelock); return res; } /* * "write" file op */ static ssize_t hiddev_write(struct file * file, const char __user * buffer, size_t count, loff_t *ppos) { return -EINVAL; } /* * "read" file op */ static ssize_t hiddev_read(struct file * file, char __user * buffer, size_t count, loff_t *ppos) { DEFINE_WAIT(wait); struct hiddev_list *list = file->private_data; int event_size; int retval; event_size = ((list->flags & HIDDEV_FLAG_UREF) != 0) ? sizeof(struct hiddev_usage_ref) : sizeof(struct hiddev_event); if (count < event_size) return 0; /* lock against other threads */ retval = mutex_lock_interruptible(&list->thread_lock); if (retval) return -ERESTARTSYS; while (retval == 0) { if (list->head == list->tail) { prepare_to_wait(&list->hiddev->wait, &wait, TASK_INTERRUPTIBLE); while (list->head == list->tail) { if (signal_pending(current)) { retval = -ERESTARTSYS; break; } if (!list->hiddev->exist) { retval = -EIO; break; } if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; break; } /* let O_NONBLOCK tasks run */ mutex_unlock(&list->thread_lock); schedule(); if (mutex_lock_interruptible(&list->thread_lock)) { finish_wait(&list->hiddev->wait, &wait); return -EINTR; } set_current_state(TASK_INTERRUPTIBLE); } finish_wait(&list->hiddev->wait, &wait); } if (retval) { mutex_unlock(&list->thread_lock); return retval; } while (list->head != list->tail && retval + event_size <= count) { if ((list->flags & HIDDEV_FLAG_UREF) == 0) { if (list->buffer[list->tail].field_index != HID_FIELD_INDEX_NONE) { struct hiddev_event event; event.hid = list->buffer[list->tail].usage_code; event.value = list->buffer[list->tail].value; if (copy_to_user(buffer + retval, &event, sizeof(struct hiddev_event))) { mutex_unlock(&list->thread_lock); return -EFAULT; } retval += sizeof(struct hiddev_event); } } else { if (list->buffer[list->tail].field_index != HID_FIELD_INDEX_NONE || (list->flags & HIDDEV_FLAG_REPORT) != 0) { if (copy_to_user(buffer + retval, list->buffer + list->tail, sizeof(struct hiddev_usage_ref))) { mutex_unlock(&list->thread_lock); return -EFAULT; } retval += sizeof(struct hiddev_usage_ref); } } list->tail = (list->tail + 1) & (HIDDEV_BUFFER_SIZE - 1); } } mutex_unlock(&list->thread_lock); return retval; } /* * "poll" file op * No kernel lock - fine */ static __poll_t hiddev_poll(struct file *file, poll_table *wait) { struct hiddev_list *list = file->private_data; poll_wait(file, &list->hiddev->wait, wait); if (list->head != list->tail) return EPOLLIN | EPOLLRDNORM | EPOLLOUT; if (!list->hiddev->exist) return EPOLLERR | EPOLLHUP; return 0; } /* * "ioctl" file op */ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, void __user *user_arg) { struct hid_device *hid = hiddev->hid; struct hiddev_report_info rinfo; struct hiddev_usage_ref_multi *uref_multi = NULL; struct hiddev_usage_ref *uref; struct hid_report *report; struct hid_field *field; int i; uref_multi = kmalloc(sizeof(struct hiddev_usage_ref_multi), GFP_KERNEL); if (!uref_multi) return -ENOMEM; uref = &uref_multi->uref; if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { if (copy_from_user(uref_multi, user_arg, sizeof(*uref_multi))) goto fault; } else { if (copy_from_user(uref, user_arg, sizeof(*uref))) goto fault; } switch (cmd) { case HIDIOCGUCODE: rinfo.report_type = uref->report_type; rinfo.report_id = uref->report_id; if ((report = hiddev_lookup_report(hid, &rinfo)) == NULL) goto inval; if (uref->field_index >= report->maxfield) goto inval; uref->field_index = array_index_nospec(uref->field_index, report->maxfield); field = report->field[uref->field_index]; if (uref->usage_index >= field->maxusage) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->maxusage); uref->usage_code = field->usage[uref->usage_index].hid; if (copy_to_user(user_arg, uref, sizeof(*uref))) goto fault; goto goodreturn; default: if (cmd != HIDIOCGUSAGE && cmd != HIDIOCGUSAGES && uref->report_type == HID_REPORT_TYPE_INPUT) goto inval; if (uref->report_id == HID_REPORT_ID_UNKNOWN) { field = hiddev_lookup_usage(hid, uref); if (field == NULL) goto inval; } else { rinfo.report_type = uref->report_type; rinfo.report_id = uref->report_id; if ((report = hiddev_lookup_report(hid, &rinfo)) == NULL) goto inval; if (uref->field_index >= report->maxfield) goto inval; uref->field_index = array_index_nospec(uref->field_index, report->maxfield); field = report->field[uref->field_index]; if (cmd == HIDIOCGCOLLECTIONINDEX) { if (uref->usage_index >= field->maxusage) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->maxusage); } else if (uref->usage_index >= field->report_count) goto inval; } if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { if (uref_multi->num_values > HID_MAX_MULTI_USAGES || uref->usage_index + uref_multi->num_values > field->report_count) goto inval; uref->usage_index = array_index_nospec(uref->usage_index, field->report_count - uref_multi->num_values); } switch (cmd) { case HIDIOCGUSAGE: if (uref->usage_index >= field->report_count) goto inval; uref->value = field->value[uref->usage_index]; if (copy_to_user(user_arg, uref, sizeof(*uref))) goto fault; goto goodreturn; case HIDIOCSUSAGE: if (uref->usage_index >= field->report_count) goto inval; field->value[uref->usage_index] = uref->value; goto goodreturn; case HIDIOCGCOLLECTIONINDEX: i = field->usage[uref->usage_index].collection_index; kfree(uref_multi); return i; case HIDIOCGUSAGES: for (i = 0; i < uref_multi->num_values; i++) uref_multi->values[i] = field->value[uref->usage_index + i]; if (copy_to_user(user_arg, uref_multi, sizeof(*uref_multi))) goto fault; goto goodreturn; case HIDIOCSUSAGES: for (i = 0; i < uref_multi->num_values; i++) field->value[uref->usage_index + i] = uref_multi->values[i]; goto goodreturn; } goodreturn: kfree(uref_multi); return 0; fault: kfree(uref_multi); return -EFAULT; inval: kfree(uref_multi); return -EINVAL; } } static noinline int hiddev_ioctl_string(struct hiddev *hiddev, unsigned int cmd, void __user *user_arg) { struct hid_device *hid = hiddev->hid; struct usb_device *dev = hid_to_usb_dev(hid); int idx, len; char *buf; if (get_user(idx, (int __user *)user_arg)) return -EFAULT; if ((buf = kmalloc(HID_STRING_SIZE, GFP_KERNEL)) == NULL) return -ENOMEM; if ((len = usb_string(dev, idx, buf, HID_STRING_SIZE-1)) < 0) { kfree(buf); return -EINVAL; } if (copy_to_user(user_arg+sizeof(int), buf, len+1)) { kfree(buf); return -EFAULT; } kfree(buf); return len; } static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct hiddev_list *list = file->private_data; struct hiddev *hiddev = list->hiddev; struct hid_device *hid; struct hiddev_collection_info cinfo; struct hiddev_report_info rinfo; struct hiddev_field_info finfo; struct hiddev_devinfo dinfo; struct hid_report *report; struct hid_field *field; void __user *user_arg = (void __user *)arg; int i, r = -EINVAL; /* Called without BKL by compat methods so no BKL taken */ mutex_lock(&hiddev->existancelock); if (!hiddev->exist) { r = -ENODEV; goto ret_unlock; } hid = hiddev->hid; switch (cmd) { case HIDIOCGVERSION: r = put_user(HID_VERSION, (int __user *)arg) ? -EFAULT : 0; break; case HIDIOCAPPLICATION: if (arg >= hid->maxapplication) break; for (i = 0; i < hid->maxcollection; i++) if (hid->collection[i].type == HID_COLLECTION_APPLICATION && arg-- == 0) break; if (i < hid->maxcollection) r = hid->collection[i].usage; break; case HIDIOCGDEVINFO: { struct usb_device *dev = hid_to_usb_dev(hid); struct usbhid_device *usbhid = hid->driver_data; memset(&dinfo, 0, sizeof(dinfo)); dinfo.bustype = BUS_USB; dinfo.busnum = dev->bus->busnum; dinfo.devnum = dev->devnum; dinfo.ifnum = usbhid->ifnum; dinfo.vendor = le16_to_cpu(dev->descriptor.idVendor); dinfo.product = le16_to_cpu(dev->descriptor.idProduct); dinfo.version = le16_to_cpu(dev->descriptor.bcdDevice); dinfo.num_applications = hid->maxapplication; r = copy_to_user(user_arg, &dinfo, sizeof(dinfo)) ? -EFAULT : 0; break; } case HIDIOCGFLAG: r = put_user(list->flags, (int __user *)arg) ? -EFAULT : 0; break; case HIDIOCSFLAG: { int newflags; if (get_user(newflags, (int __user *)arg)) { r = -EFAULT; break; } if ((newflags & ~HIDDEV_FLAGS) != 0 || ((newflags & HIDDEV_FLAG_REPORT) != 0 && (newflags & HIDDEV_FLAG_UREF) == 0)) break; list->flags = newflags; r = 0; break; } case HIDIOCGSTRING: r = hiddev_ioctl_string(hiddev, cmd, user_arg); break; case HIDIOCINITREPORT: usbhid_init_reports(hid); hiddev->initialized = true; r = 0; break; case HIDIOCGREPORT: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } if (rinfo.report_type == HID_REPORT_TYPE_OUTPUT) break; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; hid_hw_request(hid, report, HID_REQ_GET_REPORT); hid_hw_wait(hid); r = 0; break; case HIDIOCSREPORT: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } if (rinfo.report_type == HID_REPORT_TYPE_INPUT) break; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; hid_hw_request(hid, report, HID_REQ_SET_REPORT); hid_hw_wait(hid); r = 0; break; case HIDIOCGREPORTINFO: if (copy_from_user(&rinfo, user_arg, sizeof(rinfo))) { r = -EFAULT; break; } report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; rinfo.num_fields = report->maxfield; r = copy_to_user(user_arg, &rinfo, sizeof(rinfo)) ? -EFAULT : 0; break; case HIDIOCGFIELDINFO: if (copy_from_user(&finfo, user_arg, sizeof(finfo))) { r = -EFAULT; break; } rinfo.report_type = finfo.report_type; rinfo.report_id = finfo.report_id; report = hiddev_lookup_report(hid, &rinfo); if (report == NULL) break; if (finfo.field_index >= report->maxfield) break; finfo.field_index = array_index_nospec(finfo.field_index, report->maxfield); field = report->field[finfo.field_index]; memset(&finfo, 0, sizeof(finfo)); finfo.report_type = rinfo.report_type; finfo.report_id = rinfo.report_id; finfo.field_index = field->report_count - 1; finfo.maxusage = field->maxusage; finfo.flags = field->flags; finfo.physical = field->physical; finfo.logical = field->logical; finfo.application = field->application; finfo.logical_minimum = field->logical_minimum; finfo.logical_maximum = field->logical_maximum; finfo.physical_minimum = field->physical_minimum; finfo.physical_maximum = field->physical_maximum; finfo.unit_exponent = field->unit_exponent; finfo.unit = field->unit; r = copy_to_user(user_arg, &finfo, sizeof(finfo)) ? -EFAULT : 0; break; case HIDIOCGUCODE: case HIDIOCGUSAGE: case HIDIOCSUSAGE: case HIDIOCGUSAGES: case HIDIOCSUSAGES: case HIDIOCGCOLLECTIONINDEX: if (!hiddev->initialized) { usbhid_init_reports(hid); hiddev->initialized = true; } r = hiddev_ioctl_usage(hiddev, cmd, user_arg); break; case HIDIOCGCOLLECTIONINFO: if (copy_from_user(&cinfo, user_arg, sizeof(cinfo))) { r = -EFAULT; break; } if (cinfo.index >= hid->maxcollection) break; cinfo.index = array_index_nospec(cinfo.index, hid->maxcollection); cinfo.type = hid->collection[cinfo.index].type; cinfo.usage = hid->collection[cinfo.index].usage; cinfo.level = hid->collection[cinfo.index].level; r = copy_to_user(user_arg, &cinfo, sizeof(cinfo)) ? -EFAULT : 0; break; default: if (_IOC_TYPE(cmd) != 'H' || _IOC_DIR(cmd) != _IOC_READ) break; if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGNAME(0))) { int len = strlen(hid->name) + 1; if (len > _IOC_SIZE(cmd)) len = _IOC_SIZE(cmd); r = copy_to_user(user_arg, hid->name, len) ? -EFAULT : len; break; } if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGPHYS(0))) { int len = strlen(hid->phys) + 1; if (len > _IOC_SIZE(cmd)) len = _IOC_SIZE(cmd); r = copy_to_user(user_arg, hid->phys, len) ? -EFAULT : len; break; } } ret_unlock: mutex_unlock(&hiddev->existancelock); return r; } static const struct file_operations hiddev_fops = { .owner = THIS_MODULE, .read = hiddev_read, .write = hiddev_write, .poll = hiddev_poll, .open = hiddev_open, .release = hiddev_release, .unlocked_ioctl = hiddev_ioctl, .fasync = hiddev_fasync, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static char *hiddev_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "usb/%s", dev_name(dev)); } static struct usb_class_driver hiddev_class = { .name = "hiddev%d", .devnode = hiddev_devnode, .fops = &hiddev_fops, .minor_base = HIDDEV_MINOR_BASE, }; /* * This is where hid.c calls us to connect a hid device to the hiddev driver */ int hiddev_connect(struct hid_device *hid, unsigned int force) { struct hiddev *hiddev; struct usbhid_device *usbhid = hid->driver_data; int retval; if (!force) { unsigned int i; for (i = 0; i < hid->maxcollection; i++) if (hid->collection[i].type == HID_COLLECTION_APPLICATION && !IS_INPUT_APPLICATION(hid->collection[i].usage)) break; if (i == hid->maxcollection) return -EINVAL; } if (!(hiddev = kzalloc(sizeof(struct hiddev), GFP_KERNEL))) return -ENOMEM; init_waitqueue_head(&hiddev->wait); INIT_LIST_HEAD(&hiddev->list); spin_lock_init(&hiddev->list_lock); mutex_init(&hiddev->existancelock); hid->hiddev = hiddev; hiddev->hid = hid; hiddev->exist = 1; retval = usb_register_dev(usbhid->intf, &hiddev_class); if (retval) { hid_err(hid, "Not able to get a minor for this device\n"); hid->hiddev = NULL; kfree(hiddev); return retval; } /* * If HID_QUIRK_NO_INIT_REPORTS is set, make sure we don't initialize * the reports. */ hiddev->initialized = hid->quirks & HID_QUIRK_NO_INIT_REPORTS; hiddev->minor = usbhid->intf->minor; return 0; } /* * This is where hid.c calls us to disconnect a hiddev device from the * corresponding hid device (usually because the usb device has disconnected) */ static struct usb_class_driver hiddev_class; void hiddev_disconnect(struct hid_device *hid) { struct hiddev *hiddev = hid->hiddev; struct usbhid_device *usbhid = hid->driver_data; usb_deregister_dev(usbhid->intf, &hiddev_class); mutex_lock(&hiddev->existancelock); hiddev->exist = 0; if (hiddev->open) { hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); } } |
| 3 3 3 3 2 3 2 1 2 1 1 1 1 2 2 2 2 2 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * seq_oss_readq.c - MIDI input queue * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_readq.h" #include "seq_oss_event.h" #include <sound/seq_oss_legacy.h> #include "../seq_lock.h" #include <linux/wait.h> #include <linux/slab.h> /* * constants */ //#define SNDRV_SEQ_OSS_MAX_TIMEOUT (unsigned long)(-1) #define SNDRV_SEQ_OSS_MAX_TIMEOUT (HZ * 3600) /* * prototypes */ /* * create a read queue */ struct seq_oss_readq * snd_seq_oss_readq_new(struct seq_oss_devinfo *dp, int maxlen) { struct seq_oss_readq *q; q = kzalloc(sizeof(*q), GFP_KERNEL); if (!q) return NULL; q->q = kcalloc(maxlen, sizeof(union evrec), GFP_KERNEL); if (!q->q) { kfree(q); return NULL; } q->maxlen = maxlen; q->qlen = 0; q->head = q->tail = 0; init_waitqueue_head(&q->midi_sleep); spin_lock_init(&q->lock); q->pre_event_timeout = SNDRV_SEQ_OSS_MAX_TIMEOUT; q->input_time = (unsigned long)-1; return q; } /* * delete the read queue */ void snd_seq_oss_readq_delete(struct seq_oss_readq *q) { if (q) { kfree(q->q); kfree(q); } } /* * reset the read queue */ void snd_seq_oss_readq_clear(struct seq_oss_readq *q) { if (q->qlen) { q->qlen = 0; q->head = q->tail = 0; } /* if someone sleeping, wake'em up */ wake_up(&q->midi_sleep); q->input_time = (unsigned long)-1; } /* * put a midi byte */ int snd_seq_oss_readq_puts(struct seq_oss_readq *q, int dev, unsigned char *data, int len) { union evrec rec; int result; memset(&rec, 0, sizeof(rec)); rec.c[0] = SEQ_MIDIPUTC; rec.c[2] = dev; while (len-- > 0) { rec.c[1] = *data++; result = snd_seq_oss_readq_put_event(q, &rec); if (result < 0) return result; } return 0; } /* * put MIDI sysex bytes; the event buffer may be chained, thus it has * to be expanded via snd_seq_dump_var_event(). */ struct readq_sysex_ctx { struct seq_oss_readq *readq; int dev; }; static int readq_dump_sysex(void *ptr, void *buf, int count) { struct readq_sysex_ctx *ctx = ptr; return snd_seq_oss_readq_puts(ctx->readq, ctx->dev, buf, count); } int snd_seq_oss_readq_sysex(struct seq_oss_readq *q, int dev, struct snd_seq_event *ev) { struct readq_sysex_ctx ctx = { .readq = q, .dev = dev }; if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) return 0; return snd_seq_dump_var_event(ev, readq_dump_sysex, &ctx); } /* * copy an event to input queue: * return zero if enqueued */ int snd_seq_oss_readq_put_event(struct seq_oss_readq *q, union evrec *ev) { unsigned long flags; spin_lock_irqsave(&q->lock, flags); if (q->qlen >= q->maxlen - 1) { spin_unlock_irqrestore(&q->lock, flags); return -ENOMEM; } memcpy(&q->q[q->tail], ev, sizeof(*ev)); q->tail = (q->tail + 1) % q->maxlen; q->qlen++; /* wake up sleeper */ wake_up(&q->midi_sleep); spin_unlock_irqrestore(&q->lock, flags); return 0; } /* * pop queue * caller must hold lock */ int snd_seq_oss_readq_pick(struct seq_oss_readq *q, union evrec *rec) { if (q->qlen == 0) return -EAGAIN; memcpy(rec, &q->q[q->head], sizeof(*rec)); return 0; } /* * sleep until ready */ void snd_seq_oss_readq_wait(struct seq_oss_readq *q) { wait_event_interruptible_timeout(q->midi_sleep, (q->qlen > 0 || q->head == q->tail), q->pre_event_timeout); } /* * drain one record * caller must hold lock */ void snd_seq_oss_readq_free(struct seq_oss_readq *q) { if (q->qlen > 0) { q->head = (q->head + 1) % q->maxlen; q->qlen--; } } /* * polling/select: * return non-zero if readq is not empty. */ unsigned int snd_seq_oss_readq_poll(struct seq_oss_readq *q, struct file *file, poll_table *wait) { poll_wait(file, &q->midi_sleep, wait); return q->qlen; } /* * put a timestamp */ int snd_seq_oss_readq_put_timestamp(struct seq_oss_readq *q, unsigned long curt, int seq_mode) { if (curt != q->input_time) { union evrec rec; memset(&rec, 0, sizeof(rec)); switch (seq_mode) { case SNDRV_SEQ_OSS_MODE_SYNTH: rec.echo = (curt << 8) | SEQ_WAIT; snd_seq_oss_readq_put_event(q, &rec); break; case SNDRV_SEQ_OSS_MODE_MUSIC: rec.t.code = EV_TIMING; rec.t.cmd = TMR_WAIT_ABS; rec.t.time = curt; snd_seq_oss_readq_put_event(q, &rec); break; } q->input_time = curt; } return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ void snd_seq_oss_readq_info_read(struct seq_oss_readq *q, struct snd_info_buffer *buf) { snd_iprintf(buf, " read queue [%s] length = %d : tick = %ld\n", (waitqueue_active(&q->midi_sleep) ? "sleeping":"running"), q->qlen, q->input_time); } #endif /* CONFIG_SND_PROC_FS */ |
| 9 9 9 89 91 97 96 94 3 3 3 3 3 6 6 6 6 6 6 74 59 51 51 50 38 38 38 51 21 6 51 51 12 12 8 4 4 3 3 1 2 12 1 1 1 1 1 1 24 24 24 23 5 4 1 1 24 20 20 141 138 140 141 139 140 139 139 140 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 9 9 9 9 9 9 7 5 7 7 7 1 7 6 5 5 5 7 5 5 5 5 5 5 5 5 2 2 2 5 5 5 5 5 5 5 5 4 4 4 1 1 1 1 1 1 1 1 1 1 1 2 2 20 6 14 20 7 5 5 4 2 6 50 7 50 50 46 11 3 11 9 12 12 10 4 5 5 9 2 2 2 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -EINVAL; e_rpf: return -EXDEV; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -EINVAL; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return -ENODEV; *colon = ':'; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } rcu_read_unlock(); if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_unlock(); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET6; cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr); #else NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EINVAL; #endif break; default: NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA"); return -EINVAL; } return 0; } static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_config *cfg, struct netlink_ext_ack *extack) { bool has_gw = false, has_via = false; struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) goto errout; memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); if (!inet_validate_dscp(rtm->rtm_tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); err = -EINVAL; goto errout; } cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); cfg->fc_dst_len = rtm->rtm_dst_len; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; cfg->fc_type = rtm->rtm_type; cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (nla_type(attr)) { case RTA_DST: cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: has_gw = true; cfg->fc_gw4 = nla_get_be32(attr); if (cfg->fc_gw4) cfg->fc_gw_family = AF_INET; break; case RTA_VIA: has_via = true; err = fib_gw_from_via(cfg, attr, extack); if (err) goto errout; break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), nla_len(attr), extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; case RTA_ENCAP: cfg->fc_encap = attr; break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; break; case RTA_NH_ID: cfg->fc_nh_id = nla_get_u32(attr); break; } } if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); return -EINVAL; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); return -EINVAL; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; return 0; errout: return err; } static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; goto errout; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto errout; } err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; goto errout; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; errout: return err; } int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (filter->rtnl_held) ASSERT_RTNL(); if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } rtm = nlmsg_data(nlh); if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) { NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & RTM_F_CLONED) filter->dump_routes = false; else filter->dump_exceptions = false; filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; filter->table_id = rtm->rtm_table; err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (!tb[i]) continue; switch (i) { case RTA_TABLE: filter->table_id = nla_get_u32(tb[i]); break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); if (filter->rtnl_held) filter->dev = __dev_get_by_index(net, ifindex); else filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } if (filter->flags || filter->protocol || filter->rt_type || filter->table_id || filter->dev) { filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } return 0; } EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .dump_routes = true, .dump_exceptions = true, .rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; int dumped = 0, err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED); } /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); err = -ENOENT; goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) goto out; dumped = 1; next: e++; } } /* Don't let NLM_DONE coalesce into a message, even if it could. * Some user space expects NLM_DONE in a separate recv(). */ err = skb->len; out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); return err; } /* Prepare and feed intra-kernel routing request. * Really, it should be netlink message, but :-( netlink * can be not configured, so that we feed it directly * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, .fc_nlinfo = { .nl_net = net, }, }; if (!tb_id) tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; tb = fib_new_table(net, tb_id); if (!tb) return; cfg.fc_table = tb->tb_id; if (type != RTN_LOCAL) cfg.fc_scope = RT_SCOPE_LINK; else cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; __be32 prefix = ifa->ifa_address & mask; if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } } fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); arp_invalidate(dev, ifa->ifa_broadcast, false); } if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); arp_invalidate(dev, prefix | ~mask, false); } } } void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) { __be32 prefix = ifa->ifa_address & ifa->ifa_mask; struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, new_metric); /* delete the old */ fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); } /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. * In this case the secondary ifa can be in device list. */ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { /* if the device has been deleted, we don't perform * address promotion */ if (!in_dev->dead) pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } if (in_dev->dead) goto no_promotions; /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * * Scan address list to be sure that addresses are really gone. */ rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; continue; } /* Ignore IFAs from our subnet */ if (iprim && ifa1->ifa_mask == iprim->ifa_mask && inet_ifa_match(ifa1->ifa_address, iprim)) continue; /* Ignore ifa1 if it uses different primary IP (prefsrc) */ if (ifa1->ifa_flags & IFA_F_SECONDARY) { /* Another address from our subnet? */ if (ifa1->ifa_mask == prim->ifa_mask && inet_ifa_match(ifa1->ifa_address, prim)) prim1 = prim; else { /* We reached the secondaries, so * same_prefsrc should be determined. */ if (!same_prefsrc) continue; /* Search new prim1 if ifa1 is not * using the current prim1 */ if (!prim1 || ifa1->ifa_mask != prim1->ifa_mask || !inet_ifa_match(ifa1->ifa_address, prim1)) prim1 = inet_ifa_byprefix(in_dev, ifa1->ifa_address, ifa1->ifa_mask); if (!prim1) continue; if (prim1->ifa_local != prim->ifa_local) continue; } } else { if (prim->ifa_local != ifa1->ifa_local) continue; prim1 = ifa1; if (prim != prim1) same_prefsrc = 1; } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) ok |= BRD_OK; if (brd == ifa1->ifa_broadcast) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; /* primary has network specific broadcasts */ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; if (!ipv4_is_zeronet(any1)) { if (ifa->ifa_broadcast == brd1 || ifa->ifa_broadcast == any1) ok |= BRD_OK; if (brd == brd1 || brd == any1) ok |= BRD1_OK; if (any == brd1 || any == any1) ok |= BRD0_OK; } } } rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim, 0); if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, ifa->ifa_local); if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } #undef LOCAL_OK #undef BRD_OK #undef BRD0_OK #undef BRD1_OK } static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) { struct fib_result res; struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, .flowi4_tos = frn->fl_tos, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; rcu_read_lock(); tb = fib_get_table(net, frn->tb_id_in); frn->err = -ENOENT; if (tb) { local_bh_disable(); frn->tb_id = tb->tb_id; frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; } local_bh_enable(); } rcu_read_unlock(); } static void nl_fib_input(struct sk_buff *skb) { struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < nlmsg_total_size(sizeof(*frn)) || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; skb = netlink_skb_clone(skb, GFP_KERNEL); if (!skb) return; nlh = nlmsg_hdr(skb); frn = nlmsg_data(nlh); nl_fib_lookup(net, frn); portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; struct netlink_kernel_cfg cfg = { .input = nl_fib_input, }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { netlink_kernel_release(net->ipv4.fibnl); net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, unsigned long event, bool force) { if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); else rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ fib_disable_ip(dev, event, true); } else { rt_cache_flush(dev_net(dev)); } break; } return NOTIFY_DONE; } static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *upper_info = ptr; struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); rt_cache_flush(net); break; case NETDEV_CHANGEMTU: fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (upper_info->upper_dev && netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; err = fib4_notifier_init(net); if (err) return err; #ifdef CONFIG_IP_ROUTE_MULTIPATH /* Default to 3-tuple */ net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv4.fib_table_hash) { err = -ENOMEM; goto err_table_hash_alloc; } err = fib4_rules_init(net); if (err < 0) goto err_rules_init; return 0; err_rules_init: kfree(net->ipv4.fib_table_hash); err_table_hash_alloc: fib4_notifier_exit(net); return err; } static void ip_fib_net_exit(struct net *net) { int i; ASSERT_RTNL(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif /* Destroy the tables in reverse order to guarantee that the * local table, ID 255, is destroyed before the main table, ID * 254. This is necessary as the local table may contain * references to data contained in the main table. */ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(net, tb, true); fib_free_table(tb); } } #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) { int error; #ifdef CONFIG_IP_ROUTE_CLASSID atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) goto out; error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; error = fib_proc_init(net); if (error < 0) goto out_proc; out: return error; out_proc: nl_fib_lookup_exit(net); out_nlfl: rtnl_lock(); ip_fib_net_exit(net); rtnl_unlock(); goto out; } static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); } static void __net_exit fib_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip_fib_net_exit(net); rtnl_unlock(); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, .exit_batch = fib_net_exit_batch, }; void __init ip_fib_init(void) { fib_trie_init(); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, RTNL_FLAG_DUMP_UNLOCKED); } |
| 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 12 10 10 10 10 10 8 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Core driver for the pin control subsystem * * Copyright (C) 2011-2012 ST-Ericsson SA * Written on behalf of Linaro for ST-Ericsson * Based on bits of regulator core, gpio core and clk core * * Author: Linus Walleij <linus.walleij@linaro.org> * * Copyright (C) 2012 NVIDIA CORPORATION. All rights reserved. */ #define pr_fmt(fmt) "pinctrl core: " fmt #include <linux/array_size.h> #include <linux/cleanup.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/err.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/gpio.h> #include <linux/gpio/driver.h> #include <linux/pinctrl/consumer.h> #include <linux/pinctrl/devinfo.h> #include <linux/pinctrl/machine.h> #include <linux/pinctrl/pinctrl.h> #include "core.h" #include "devicetree.h" #include "pinconf.h" #include "pinmux.h" static bool pinctrl_dummy_state; /* Mutex taken to protect pinctrl_list */ static DEFINE_MUTEX(pinctrl_list_mutex); /* Mutex taken to protect pinctrl_maps */ DEFINE_MUTEX(pinctrl_maps_mutex); /* Mutex taken to protect pinctrldev_list */ static DEFINE_MUTEX(pinctrldev_list_mutex); /* Global list of pin control devices (struct pinctrl_dev) */ static LIST_HEAD(pinctrldev_list); /* List of pin controller handles (struct pinctrl) */ static LIST_HEAD(pinctrl_list); /* List of pinctrl maps (struct pinctrl_maps) */ LIST_HEAD(pinctrl_maps); /** * pinctrl_provide_dummies() - indicate if pinctrl provides dummy state support * * Usually this function is called by platforms without pinctrl driver support * but run with some shared drivers using pinctrl APIs. * After calling this function, the pinctrl core will return successfully * with creating a dummy state for the driver to keep going smoothly. */ void pinctrl_provide_dummies(void) { pinctrl_dummy_state = true; } const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev) { /* We're not allowed to register devices without name */ return pctldev->desc->name; } EXPORT_SYMBOL_GPL(pinctrl_dev_get_name); const char *pinctrl_dev_get_devname(struct pinctrl_dev *pctldev) { return dev_name(pctldev->dev); } EXPORT_SYMBOL_GPL(pinctrl_dev_get_devname); void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev) { return pctldev->driver_data; } EXPORT_SYMBOL_GPL(pinctrl_dev_get_drvdata); /** * get_pinctrl_dev_from_devname() - look up pin controller device * @devname: the name of a device instance, as returned by dev_name() * * Looks up a pin control device matching a certain device name or pure device * pointer, the pure device pointer will take precedence. */ struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *devname) { struct pinctrl_dev *pctldev; if (!devname) return NULL; mutex_lock(&pinctrldev_list_mutex); list_for_each_entry(pctldev, &pinctrldev_list, node) { if (!strcmp(dev_name(pctldev->dev), devname)) { /* Matched on device name */ mutex_unlock(&pinctrldev_list_mutex); return pctldev; } } mutex_unlock(&pinctrldev_list_mutex); return NULL; } struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np) { struct pinctrl_dev *pctldev; mutex_lock(&pinctrldev_list_mutex); list_for_each_entry(pctldev, &pinctrldev_list, node) if (device_match_of_node(pctldev->dev, np)) { mutex_unlock(&pinctrldev_list_mutex); return pctldev; } mutex_unlock(&pinctrldev_list_mutex); return NULL; } /** * pin_get_from_name() - look up a pin number from a name * @pctldev: the pin control device to lookup the pin on * @name: the name of the pin to look up */ int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name) { unsigned int i, pin; /* The pin number can be retrived from the pin controller descriptor */ for (i = 0; i < pctldev->desc->npins; i++) { struct pin_desc *desc; pin = pctldev->desc->pins[i].number; desc = pin_desc_get(pctldev, pin); /* Pin space may be sparse */ if (desc && !strcmp(name, desc->name)) return pin; } return -EINVAL; } /** * pin_get_name() - look up a pin name from a pin id * @pctldev: the pin control device to lookup the pin on * @pin: pin number/id to look up */ const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin) { const struct pin_desc *desc; desc = pin_desc_get(pctldev, pin); if (!desc) { dev_err(pctldev->dev, "failed to get pin(%d) name\n", pin); return NULL; } return desc->name; } EXPORT_SYMBOL_GPL(pin_get_name); /* Deletes a range of pin descriptors */ static void pinctrl_free_pindescs(struct pinctrl_dev *pctldev, const struct pinctrl_pin_desc *pins, unsigned int num_pins) { int i; for (i = 0; i < num_pins; i++) { struct pin_desc *pindesc; pindesc = radix_tree_lookup(&pctldev->pin_desc_tree, pins[i].number); if (pindesc) { radix_tree_delete(&pctldev->pin_desc_tree, pins[i].number); if (pindesc->dynamic_name) kfree(pindesc->name); } kfree(pindesc); } } static int pinctrl_register_one_pin(struct pinctrl_dev *pctldev, const struct pinctrl_pin_desc *pin) { struct pin_desc *pindesc; int error; pindesc = pin_desc_get(pctldev, pin->number); if (pindesc) { dev_err(pctldev->dev, "pin %d already registered\n", pin->number); return -EINVAL; } pindesc = kzalloc(sizeof(*pindesc), GFP_KERNEL); if (!pindesc) return -ENOMEM; /* Set owner */ pindesc->pctldev = pctldev; /* Copy basic pin info */ if (pin->name) { pindesc->name = pin->name; } else { pindesc->name = kasprintf(GFP_KERNEL, "PIN%u", pin->number); if (!pindesc->name) { error = -ENOMEM; goto failed; } pindesc->dynamic_name = true; } pindesc->drv_data = pin->drv_data; error = radix_tree_insert(&pctldev->pin_desc_tree, pin->number, pindesc); if (error) goto failed; pr_debug("registered pin %d (%s) on %s\n", pin->number, pindesc->name, pctldev->desc->name); return 0; failed: kfree(pindesc); return error; } static int pinctrl_register_pins(struct pinctrl_dev *pctldev, const struct pinctrl_pin_desc *pins, unsigned int num_descs) { unsigned int i; int ret = 0; for (i = 0; i < num_descs; i++) { ret = pinctrl_register_one_pin(pctldev, &pins[i]); if (ret) return ret; } return 0; } /** * gpio_to_pin() - GPIO range GPIO number to pin number translation * @range: GPIO range used for the translation * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * Finds the pin number for a given GPIO using the specified GPIO range * as a base for translation. The distinction between linear GPIO ranges * and pin list based GPIO ranges is managed correctly by this function. * * This function assumes the gpio is part of the specified GPIO range, use * only after making sure this is the case (e.g. by calling it on the * result of successful pinctrl_get_device_gpio_range calls)! */ static inline int gpio_to_pin(struct pinctrl_gpio_range *range, struct gpio_chip *gc, unsigned int offset) { unsigned int pin = gc->base + offset - range->base; if (range->pins) return range->pins[pin]; else return range->pin_base + pin; } /** * pinctrl_match_gpio_range() - check if a certain GPIO pin is in range * @pctldev: pin controller device to check * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * Tries to match a GPIO pin number to the ranges handled by a certain pin * controller, return the range or NULL */ static struct pinctrl_gpio_range * pinctrl_match_gpio_range(struct pinctrl_dev *pctldev, struct gpio_chip *gc, unsigned int offset) { struct pinctrl_gpio_range *range; mutex_lock(&pctldev->mutex); /* Loop over the ranges */ list_for_each_entry(range, &pctldev->gpio_ranges, node) { /* Check if we're in the valid range */ if ((gc->base + offset) >= range->base && (gc->base + offset) < range->base + range->npins) { mutex_unlock(&pctldev->mutex); return range; } } mutex_unlock(&pctldev->mutex); return NULL; } /** * pinctrl_ready_for_gpio_range() - check if other GPIO pins of * the same GPIO chip are in range * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * This function is complement of pinctrl_match_gpio_range(). If the return * value of pinctrl_match_gpio_range() is NULL, this function could be used * to check whether pinctrl device is ready or not. Maybe some GPIO pins * of the same GPIO chip don't have back-end pinctrl interface. * If the return value is true, it means that pinctrl device is ready & the * certain GPIO pin doesn't have back-end pinctrl device. If the return value * is false, it means that pinctrl device may not be ready. */ #ifdef CONFIG_GPIOLIB static bool pinctrl_ready_for_gpio_range(struct gpio_chip *gc, unsigned int offset) { struct pinctrl_dev *pctldev; struct pinctrl_gpio_range *range = NULL; mutex_lock(&pinctrldev_list_mutex); /* Loop over the pin controllers */ list_for_each_entry(pctldev, &pinctrldev_list, node) { /* Loop over the ranges */ mutex_lock(&pctldev->mutex); list_for_each_entry(range, &pctldev->gpio_ranges, node) { /* Check if any gpio range overlapped with gpio chip */ if (range->base + range->npins - 1 < gc->base || range->base > gc->base + gc->ngpio - 1) continue; mutex_unlock(&pctldev->mutex); mutex_unlock(&pinctrldev_list_mutex); return true; } mutex_unlock(&pctldev->mutex); } mutex_unlock(&pinctrldev_list_mutex); return false; } #else static inline bool pinctrl_ready_for_gpio_range(struct gpio_chip *gc, unsigned int offset) { return true; } #endif /** * pinctrl_get_device_gpio_range() - find device for GPIO range * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * @outdev: the pin control device if found * @outrange: the GPIO range if found * * Find the pin controller handling a certain GPIO pin from the pinspace of * the GPIO subsystem, return the device and the matching GPIO range. Returns * -EPROBE_DEFER if the GPIO range could not be found in any device since it * may still have not been registered. */ static int pinctrl_get_device_gpio_range(struct gpio_chip *gc, unsigned int offset, struct pinctrl_dev **outdev, struct pinctrl_gpio_range **outrange) { struct pinctrl_dev *pctldev; mutex_lock(&pinctrldev_list_mutex); /* Loop over the pin controllers */ list_for_each_entry(pctldev, &pinctrldev_list, node) { struct pinctrl_gpio_range *range; range = pinctrl_match_gpio_range(pctldev, gc, offset); if (range) { *outdev = pctldev; *outrange = range; mutex_unlock(&pinctrldev_list_mutex); return 0; } } mutex_unlock(&pinctrldev_list_mutex); return -EPROBE_DEFER; } /** * pinctrl_add_gpio_range() - register a GPIO range for a controller * @pctldev: pin controller device to add the range to * @range: the GPIO range to add * * DEPRECATED: Don't use this function in new code. See section 2 of * Documentation/devicetree/bindings/gpio/gpio.txt on how to bind pinctrl and * gpio drivers. * * This adds a range of GPIOs to be handled by a certain pin controller. Call * this to register handled ranges after registering your pin controller. */ void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range) { mutex_lock(&pctldev->mutex); list_add_tail(&range->node, &pctldev->gpio_ranges); mutex_unlock(&pctldev->mutex); } EXPORT_SYMBOL_GPL(pinctrl_add_gpio_range); void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *ranges, unsigned int nranges) { int i; for (i = 0; i < nranges; i++) pinctrl_add_gpio_range(pctldev, &ranges[i]); } EXPORT_SYMBOL_GPL(pinctrl_add_gpio_ranges); struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname, struct pinctrl_gpio_range *range) { struct pinctrl_dev *pctldev; pctldev = get_pinctrl_dev_from_devname(devname); /* * If we can't find this device, let's assume that is because * it has not probed yet, so the driver trying to register this * range need to defer probing. */ if (!pctldev) return ERR_PTR(-EPROBE_DEFER); pinctrl_add_gpio_range(pctldev, range); return pctldev; } EXPORT_SYMBOL_GPL(pinctrl_find_and_add_gpio_range); int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group, const unsigned int **pins, unsigned int *num_pins) { const struct pinctrl_ops *pctlops = pctldev->desc->pctlops; int gs; if (!pctlops->get_group_pins) return -EINVAL; gs = pinctrl_get_group_selector(pctldev, pin_group); if (gs < 0) return gs; return pctlops->get_group_pins(pctldev, gs, pins, num_pins); } EXPORT_SYMBOL_GPL(pinctrl_get_group_pins); struct pinctrl_gpio_range * pinctrl_find_gpio_range_from_pin_nolock(struct pinctrl_dev *pctldev, unsigned int pin) { struct pinctrl_gpio_range *range; /* Loop over the ranges */ list_for_each_entry(range, &pctldev->gpio_ranges, node) { /* Check if we're in the valid range */ if (range->pins) { int a; for (a = 0; a < range->npins; a++) { if (range->pins[a] == pin) return range; } } else if (pin >= range->pin_base && pin < range->pin_base + range->npins) return range; } return NULL; } EXPORT_SYMBOL_GPL(pinctrl_find_gpio_range_from_pin_nolock); /** * pinctrl_find_gpio_range_from_pin() - locate the GPIO range for a pin * @pctldev: the pin controller device to look in * @pin: a controller-local number to find the range for */ struct pinctrl_gpio_range * pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev, unsigned int pin) { struct pinctrl_gpio_range *range; mutex_lock(&pctldev->mutex); range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin); mutex_unlock(&pctldev->mutex); return range; } EXPORT_SYMBOL_GPL(pinctrl_find_gpio_range_from_pin); /** * pinctrl_remove_gpio_range() - remove a range of GPIOs from a pin controller * @pctldev: pin controller device to remove the range from * @range: the GPIO range to remove */ void pinctrl_remove_gpio_range(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range) { mutex_lock(&pctldev->mutex); list_del(&range->node); mutex_unlock(&pctldev->mutex); } EXPORT_SYMBOL_GPL(pinctrl_remove_gpio_range); #ifdef CONFIG_GENERIC_PINCTRL_GROUPS /** * pinctrl_generic_get_group_count() - returns the number of pin groups * @pctldev: pin controller device */ int pinctrl_generic_get_group_count(struct pinctrl_dev *pctldev) { return pctldev->num_groups; } EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_count); /** * pinctrl_generic_get_group_name() - returns the name of a pin group * @pctldev: pin controller device * @selector: group number */ const char *pinctrl_generic_get_group_name(struct pinctrl_dev *pctldev, unsigned int selector) { struct group_desc *group; group = radix_tree_lookup(&pctldev->pin_group_tree, selector); if (!group) return NULL; return group->grp.name; } EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_name); /** * pinctrl_generic_get_group_pins() - gets the pin group pins * @pctldev: pin controller device * @selector: group number * @pins: pins in the group * @num_pins: number of pins in the group */ int pinctrl_generic_get_group_pins(struct pinctrl_dev *pctldev, unsigned int selector, const unsigned int **pins, unsigned int *num_pins) { struct group_desc *group; group = radix_tree_lookup(&pctldev->pin_group_tree, selector); if (!group) { dev_err(pctldev->dev, "%s could not find pingroup%i\n", __func__, selector); return -EINVAL; } *pins = group->grp.pins; *num_pins = group->grp.npins; return 0; } EXPORT_SYMBOL_GPL(pinctrl_generic_get_group_pins); /** * pinctrl_generic_get_group() - returns a pin group based on the number * @pctldev: pin controller device * @selector: group number */ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev, unsigned int selector) { struct group_desc *group; group = radix_tree_lookup(&pctldev->pin_group_tree, selector); if (!group) return NULL; return group; } EXPORT_SYMBOL_GPL(pinctrl_generic_get_group); static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev, const char *function) { const struct pinctrl_ops *ops = pctldev->desc->pctlops; int ngroups = ops->get_groups_count(pctldev); int selector = 0; /* See if this pctldev has this group */ while (selector < ngroups) { const char *gname = ops->get_group_name(pctldev, selector); if (gname && !strcmp(function, gname)) return selector; selector++; } return -EINVAL; } /** * pinctrl_generic_add_group() - adds a new pin group * @pctldev: pin controller device * @name: name of the pin group * @pins: pins in the pin group * @num_pins: number of pins in the pin group * @data: pin controller driver specific data * * Note that the caller must take care of locking. */ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name, const unsigned int *pins, int num_pins, void *data) { struct group_desc *group; int selector, error; if (!name) return -EINVAL; selector = pinctrl_generic_group_name_to_selector(pctldev, name); if (selector >= 0) return selector; selector = pctldev->num_groups; group = devm_kzalloc(pctldev->dev, sizeof(*group), GFP_KERNEL); if (!group) return -ENOMEM; *group = PINCTRL_GROUP_DESC(name, pins, num_pins, data); error = radix_tree_insert(&pctldev->pin_group_tree, selector, group); if (error) return error; pctldev->num_groups++; return selector; } EXPORT_SYMBOL_GPL(pinctrl_generic_add_group); /** * pinctrl_generic_remove_group() - removes a numbered pin group * @pctldev: pin controller device * @selector: group number * * Note that the caller must take care of locking. */ int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev, unsigned int selector) { struct group_desc *group; group = radix_tree_lookup(&pctldev->pin_group_tree, selector); if (!group) return -ENOENT; radix_tree_delete(&pctldev->pin_group_tree, selector); devm_kfree(pctldev->dev, group); pctldev->num_groups--; return 0; } EXPORT_SYMBOL_GPL(pinctrl_generic_remove_group); /** * pinctrl_generic_free_groups() - removes all pin groups * @pctldev: pin controller device * * Note that the caller must take care of locking. The pinctrl groups * are allocated with devm_kzalloc() so no need to free them here. */ static void pinctrl_generic_free_groups(struct pinctrl_dev *pctldev) { struct radix_tree_iter iter; void __rcu **slot; radix_tree_for_each_slot(slot, &pctldev->pin_group_tree, &iter, 0) radix_tree_delete(&pctldev->pin_group_tree, iter.index); pctldev->num_groups = 0; } #else static inline void pinctrl_generic_free_groups(struct pinctrl_dev *pctldev) { } #endif /* CONFIG_GENERIC_PINCTRL_GROUPS */ /** * pinctrl_get_group_selector() - returns the group selector for a group * @pctldev: the pin controller handling the group * @pin_group: the pin group to look up */ int pinctrl_get_group_selector(struct pinctrl_dev *pctldev, const char *pin_group) { const struct pinctrl_ops *pctlops = pctldev->desc->pctlops; unsigned int ngroups = pctlops->get_groups_count(pctldev); unsigned int group_selector = 0; while (group_selector < ngroups) { const char *gname = pctlops->get_group_name(pctldev, group_selector); if (gname && !strcmp(gname, pin_group)) { dev_dbg(pctldev->dev, "found group selector %u for %s\n", group_selector, pin_group); return group_selector; } group_selector++; } dev_err(pctldev->dev, "does not have pin group %s\n", pin_group); return -EINVAL; } bool pinctrl_gpio_can_use_line(struct gpio_chip *gc, unsigned int offset) { struct pinctrl_dev *pctldev; struct pinctrl_gpio_range *range; bool result; int pin; /* * Try to obtain GPIO range, if it fails * we're probably dealing with GPIO driver * without a backing pin controller - bail out. */ if (pinctrl_get_device_gpio_range(gc, offset, &pctldev, &range)) return true; mutex_lock(&pctldev->mutex); /* Convert to the pin controllers number space */ pin = gpio_to_pin(range, gc, offset); result = pinmux_can_be_used_for_gpio(pctldev, pin); mutex_unlock(&pctldev->mutex); return result; } EXPORT_SYMBOL_GPL(pinctrl_gpio_can_use_line); /** * pinctrl_gpio_request() - request a single pin to be used as GPIO * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * This function should *ONLY* be used from gpiolib-based GPIO drivers, * as part of their gpio_request() semantics, platforms and individual drivers * shall *NOT* request GPIO pins to be muxed in. */ int pinctrl_gpio_request(struct gpio_chip *gc, unsigned int offset) { struct pinctrl_gpio_range *range; struct pinctrl_dev *pctldev; int ret, pin; ret = pinctrl_get_device_gpio_range(gc, offset, &pctldev, &range); if (ret) { if (pinctrl_ready_for_gpio_range(gc, offset)) ret = 0; return ret; } mutex_lock(&pctldev->mutex); /* Convert to the pin controllers number space */ pin = gpio_to_pin(range, gc, offset); ret = pinmux_request_gpio(pctldev, range, pin, gc->base + offset); mutex_unlock(&pctldev->mutex); return ret; } EXPORT_SYMBOL_GPL(pinctrl_gpio_request); /** * pinctrl_gpio_free() - free control on a single pin, currently used as GPIO * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * This function should *ONLY* be used from gpiolib-based GPIO drivers, * as part of their gpio_request() semantics, platforms and individual drivers * shall *NOT* request GPIO pins to be muxed in. */ void pinctrl_gpio_free(struct gpio_chip *gc, unsigned int offset) { struct pinctrl_gpio_range *range; struct pinctrl_dev *pctldev; int ret, pin; ret = pinctrl_get_device_gpio_range(gc, offset, &pctldev, &range); if (ret) return; mutex_lock(&pctldev->mutex); /* Convert to the pin controllers number space */ pin = gpio_to_pin(range, gc, offset); pinmux_free_gpio(pctldev, pin, range); mutex_unlock(&pctldev->mutex); } EXPORT_SYMBOL_GPL(pinctrl_gpio_free); static int pinctrl_gpio_direction(struct gpio_chip *gc, unsigned int offset, bool input) { struct pinctrl_dev *pctldev; struct pinctrl_gpio_range *range; int ret; int pin; ret = pinctrl_get_device_gpio_range(gc, offset, &pctldev, &range); if (ret) { return ret; } mutex_lock(&pctldev->mutex); /* Convert to the pin controllers number space */ pin = gpio_to_pin(range, gc, offset); ret = pinmux_gpio_direction(pctldev, range, pin, input); mutex_unlock(&pctldev->mutex); return ret; } /** * pinctrl_gpio_direction_input() - request a GPIO pin to go into input mode * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * This function should *ONLY* be used from gpiolib-based GPIO drivers, * as part of their gpio_direction_input() semantics, platforms and individual * drivers shall *NOT* touch pin control GPIO calls. */ int pinctrl_gpio_direction_input(struct gpio_chip *gc, unsigned int offset) { return pinctrl_gpio_direction(gc, offset, true); } EXPORT_SYMBOL_GPL(pinctrl_gpio_direction_input); /** * pinctrl_gpio_direction_output() - request a GPIO pin to go into output mode * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * * This function should *ONLY* be used from gpiolib-based GPIO drivers, * as part of their gpio_direction_output() semantics, platforms and individual * drivers shall *NOT* touch pin control GPIO calls. */ int pinctrl_gpio_direction_output(struct gpio_chip *gc, unsigned int offset) { return pinctrl_gpio_direction(gc, offset, false); } EXPORT_SYMBOL_GPL(pinctrl_gpio_direction_output); /** * pinctrl_gpio_set_config() - Apply config to given GPIO pin * @gc: GPIO chip structure from the GPIO subsystem * @offset: hardware offset of the GPIO relative to the controller * @config: the configuration to apply to the GPIO * * This function should *ONLY* be used from gpiolib-based GPIO drivers, if * they need to call the underlying pin controller to change GPIO config * (for example set debounce time). */ int pinctrl_gpio_set_config(struct gpio_chip *gc, unsigned int offset, unsigned long config) { unsigned long configs[] = { config }; struct pinctrl_gpio_range *range; struct pinctrl_dev *pctldev; int ret, pin; ret = pinctrl_get_device_gpio_range(gc, offset, &pctldev, &range); if (ret) return ret; mutex_lock(&pctldev->mutex); pin = gpio_to_pin(range, gc, offset); ret = pinconf_set_config(pctldev, pin, configs, ARRAY_SIZE(configs)); mutex_unlock(&pctldev->mutex); return ret; } EXPORT_SYMBOL_GPL(pinctrl_gpio_set_config); static struct pinctrl_state *find_state(struct pinctrl *p, const char *name) { struct pinctrl_state *state; list_for_each_entry(state, &p->states, node) if (!strcmp(state->name, name)) return state; return NULL; } static struct pinctrl_state *create_state(struct pinctrl *p, const char *name) { struct pinctrl_state *state; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return ERR_PTR(-ENOMEM); state->name = name; INIT_LIST_HEAD(&state->settings); list_add_tail(&state->node, &p->states); return state; } static int add_setting(struct pinctrl *p, struct pinctrl_dev *pctldev, const struct pinctrl_map *map) { struct pinctrl_state *state; struct pinctrl_setting *setting; int ret; state = find_state(p, map->name); if (!state) state = create_state(p, map->name); if (IS_ERR(state)) return PTR_ERR(state); if (map->type == PIN_MAP_TYPE_DUMMY_STATE) return 0; setting = kzalloc(sizeof(*setting), GFP_KERNEL); if (!setting) return -ENOMEM; setting->type = map->type; if (pctldev) setting->pctldev = pctldev; else setting->pctldev = get_pinctrl_dev_from_devname(map->ctrl_dev_name); if (!setting->pctldev) { kfree(setting); /* Do not defer probing of hogs (circular loop) */ if (!strcmp(map->ctrl_dev_name, map->dev_name)) return -ENODEV; /* * OK let us guess that the driver is not there yet, and * let's defer obtaining this pinctrl handle to later... */ dev_info(p->dev, "unknown pinctrl device %s in map entry, deferring probe", map->ctrl_dev_name); return -EPROBE_DEFER; } setting->dev_name = map->dev_name; switch (map->type) { case PIN_MAP_TYPE_MUX_GROUP: ret = pinmux_map_to_setting(map, setting); break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: ret = pinconf_map_to_setting(map, setting); break; default: ret = -EINVAL; break; } if (ret < 0) { kfree(setting); return ret; } list_add_tail(&setting->node, &state->settings); return 0; } static struct pinctrl *find_pinctrl(struct device *dev) { struct pinctrl *p; mutex_lock(&pinctrl_list_mutex); list_for_each_entry(p, &pinctrl_list, node) if (p->dev == dev) { mutex_unlock(&pinctrl_list_mutex); return p; } mutex_unlock(&pinctrl_list_mutex); return NULL; } static void pinctrl_free(struct pinctrl *p, bool inlist); static struct pinctrl *create_pinctrl(struct device *dev, struct pinctrl_dev *pctldev) { struct pinctrl *p; const char *devname; struct pinctrl_maps *maps_node; const struct pinctrl_map *map; int ret; /* * create the state cookie holder struct pinctrl for each * mapping, this is what consumers will get when requesting * a pin control handle with pinctrl_get() */ p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); p->dev = dev; INIT_LIST_HEAD(&p->states); INIT_LIST_HEAD(&p->dt_maps); ret = pinctrl_dt_to_map(p, pctldev); if (ret < 0) { kfree(p); return ERR_PTR(ret); } devname = dev_name(dev); mutex_lock(&pinctrl_maps_mutex); /* Iterate over the pin control maps to locate the right ones */ for_each_pin_map(maps_node, map) { /* Map must be for this device */ if (strcmp(map->dev_name, devname)) continue; /* * If pctldev is not null, we are claiming hog for it, * that means, setting that is served by pctldev by itself. * * Thus we must skip map that is for this device but is served * by other device. */ if (pctldev && strcmp(dev_name(pctldev->dev), map->ctrl_dev_name)) continue; ret = add_setting(p, pctldev, map); /* * At this point the adding of a setting may: * * - Defer, if the pinctrl device is not yet available * - Fail, if the pinctrl device is not yet available, * AND the setting is a hog. We cannot defer that, since * the hog will kick in immediately after the device * is registered. * * If the error returned was not -EPROBE_DEFER then we * accumulate the errors to see if we end up with * an -EPROBE_DEFER later, as that is the worst case. */ if (ret == -EPROBE_DEFER) { pinctrl_free(p, false); mutex_unlock(&pinctrl_maps_mutex); return ERR_PTR(ret); } } mutex_unlock(&pinctrl_maps_mutex); if (ret < 0) { /* If some other error than deferral occurred, return here */ pinctrl_free(p, false); return ERR_PTR(ret); } kref_init(&p->users); /* Add the pinctrl handle to the global list */ mutex_lock(&pinctrl_list_mutex); list_add_tail(&p->node, &pinctrl_list); mutex_unlock(&pinctrl_list_mutex); return p; } /** * pinctrl_get() - retrieves the pinctrl handle for a device * @dev: the device to obtain the handle for */ struct pinctrl *pinctrl_get(struct device *dev) { struct pinctrl *p; if (WARN_ON(!dev)) return ERR_PTR(-EINVAL); /* * See if somebody else (such as the device core) has already * obtained a handle to the pinctrl for this device. In that case, * return another pointer to it. */ p = find_pinctrl(dev); if (p) { dev_dbg(dev, "obtain a copy of previously claimed pinctrl\n"); kref_get(&p->users); return p; } return create_pinctrl(dev, NULL); } EXPORT_SYMBOL_GPL(pinctrl_get); static void pinctrl_free_setting(bool disable_setting, struct pinctrl_setting *setting) { switch (setting->type) { case PIN_MAP_TYPE_MUX_GROUP: if (disable_setting) pinmux_disable_setting(setting); pinmux_free_setting(setting); break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: pinconf_free_setting(setting); break; default: break; } } static void pinctrl_free(struct pinctrl *p, bool inlist) { struct pinctrl_state *state, *n1; struct pinctrl_setting *setting, *n2; mutex_lock(&pinctrl_list_mutex); list_for_each_entry_safe(state, n1, &p->states, node) { list_for_each_entry_safe(setting, n2, &state->settings, node) { pinctrl_free_setting(state == p->state, setting); list_del(&setting->node); kfree(setting); } list_del(&state->node); kfree(state); } pinctrl_dt_free_maps(p); if (inlist) list_del(&p->node); kfree(p); mutex_unlock(&pinctrl_list_mutex); } /** * pinctrl_release() - release the pinctrl handle * @kref: the kref in the pinctrl being released */ static void pinctrl_release(struct kref *kref) { struct pinctrl *p = container_of(kref, struct pinctrl, users); pinctrl_free(p, true); } /** * pinctrl_put() - decrease use count on a previously claimed pinctrl handle * @p: the pinctrl handle to release */ void pinctrl_put(struct pinctrl *p) { kref_put(&p->users, pinctrl_release); } EXPORT_SYMBOL_GPL(pinctrl_put); /** * pinctrl_lookup_state() - retrieves a state handle from a pinctrl handle * @p: the pinctrl handle to retrieve the state from * @name: the state name to retrieve */ struct pinctrl_state *pinctrl_lookup_state(struct pinctrl *p, const char *name) { struct pinctrl_state *state; state = find_state(p, name); if (!state) { if (pinctrl_dummy_state) { /* create dummy state */ dev_dbg(p->dev, "using pinctrl dummy state (%s)\n", name); state = create_state(p, name); } else state = ERR_PTR(-ENODEV); } return state; } EXPORT_SYMBOL_GPL(pinctrl_lookup_state); static void pinctrl_link_add(struct pinctrl_dev *pctldev, struct device *consumer) { if (pctldev->desc->link_consumers) device_link_add(consumer, pctldev->dev, DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER); } /** * pinctrl_commit_state() - select/activate/program a pinctrl state to HW * @p: the pinctrl handle for the device that requests configuration * @state: the state handle to select/activate/program */ static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) { struct pinctrl_setting *setting, *setting2; struct pinctrl_state *old_state = READ_ONCE(p->state); int ret; if (old_state) { /* * For each pinmux setting in the old state, forget SW's record * of mux owner for that pingroup. Any pingroups which are * still owned by the new state will be re-acquired by the call * to pinmux_enable_setting() in the loop below. */ list_for_each_entry(setting, &old_state->settings, node) { if (setting->type != PIN_MAP_TYPE_MUX_GROUP) continue; pinmux_disable_setting(setting); } } p->state = NULL; /* Apply all the settings for the new state - pinmux first */ list_for_each_entry(setting, &state->settings, node) { switch (setting->type) { case PIN_MAP_TYPE_MUX_GROUP: ret = pinmux_enable_setting(setting); break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: ret = 0; break; default: ret = -EINVAL; break; } if (ret < 0) goto unapply_new_state; /* Do not link hogs (circular dependency) */ if (p != setting->pctldev->p) pinctrl_link_add(setting->pctldev, p->dev); } /* Apply all the settings for the new state - pinconf after */ list_for_each_entry(setting, &state->settings, node) { switch (setting->type) { case PIN_MAP_TYPE_MUX_GROUP: ret = 0; break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: ret = pinconf_apply_setting(setting); break; default: ret = -EINVAL; break; } if (ret < 0) { goto unapply_new_state; } /* Do not link hogs (circular dependency) */ if (p != setting->pctldev->p) pinctrl_link_add(setting->pctldev, p->dev); } p->state = state; return 0; unapply_new_state: dev_err(p->dev, "Error applying setting, reverse things back\n"); list_for_each_entry(setting2, &state->settings, node) { if (&setting2->node == &setting->node) break; /* * All we can do here is pinmux_disable_setting. * That means that some pins are muxed differently now * than they were before applying the setting (We can't * "unmux a pin"!), but it's not a big deal since the pins * are free to be muxed by another apply_setting. */ if (setting2->type == PIN_MAP_TYPE_MUX_GROUP) pinmux_disable_setting(setting2); } /* There's no infinite recursive loop here because p->state is NULL */ if (old_state) pinctrl_select_state(p, old_state); return ret; } /** * pinctrl_select_state() - select/activate/program a pinctrl state to HW * @p: the pinctrl handle for the device that requests configuration * @state: the state handle to select/activate/program */ int pinctrl_select_state(struct pinctrl *p, struct pinctrl_state *state) { if (p->state == state) return 0; return pinctrl_commit_state(p, state); } EXPORT_SYMBOL_GPL(pinctrl_select_state); static void devm_pinctrl_release(struct device *dev, void *res) { pinctrl_put(*(struct pinctrl **)res); } /** * devm_pinctrl_get() - Resource managed pinctrl_get() * @dev: the device to obtain the handle for * * If there is a need to explicitly destroy the returned struct pinctrl, * devm_pinctrl_put() should be used, rather than plain pinctrl_put(). */ struct pinctrl *devm_pinctrl_get(struct device *dev) { struct pinctrl **ptr, *p; ptr = devres_alloc(devm_pinctrl_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); p = pinctrl_get(dev); if (!IS_ERR(p)) { *ptr = p; devres_add(dev, ptr); } else { devres_free(ptr); } return p; } EXPORT_SYMBOL_GPL(devm_pinctrl_get); static int devm_pinctrl_match(struct device *dev, void *res, void *data) { struct pinctrl **p = res; return *p == data; } /** * devm_pinctrl_put() - Resource managed pinctrl_put() * @p: the pinctrl handle to release * * Deallocate a struct pinctrl obtained via devm_pinctrl_get(). Normally * this function will not need to be called and the resource management * code will ensure that the resource is freed. */ void devm_pinctrl_put(struct pinctrl *p) { WARN_ON(devres_release(p->dev, devm_pinctrl_release, devm_pinctrl_match, p)); } EXPORT_SYMBOL_GPL(devm_pinctrl_put); /** * pinctrl_register_mappings() - register a set of pin controller mappings * @maps: the pincontrol mappings table to register. Note the pinctrl-core * keeps a reference to the passed in maps, so they should _not_ be * marked with __initdata. * @num_maps: the number of maps in the mapping table */ int pinctrl_register_mappings(const struct pinctrl_map *maps, unsigned int num_maps) { int i, ret; struct pinctrl_maps *maps_node; pr_debug("add %u pinctrl maps\n", num_maps); /* First sanity check the new mapping */ for (i = 0; i < num_maps; i++) { if (!maps[i].dev_name) { pr_err("failed to register map %s (%d): no device given\n", maps[i].name, i); return -EINVAL; } if (!maps[i].name) { pr_err("failed to register map %d: no map name given\n", i); return -EINVAL; } if (maps[i].type != PIN_MAP_TYPE_DUMMY_STATE && !maps[i].ctrl_dev_name) { pr_err("failed to register map %s (%d): no pin control device given\n", maps[i].name, i); return -EINVAL; } switch (maps[i].type) { case PIN_MAP_TYPE_DUMMY_STATE: break; case PIN_MAP_TYPE_MUX_GROUP: ret = pinmux_validate_map(&maps[i], i); if (ret < 0) return ret; break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: ret = pinconf_validate_map(&maps[i], i); if (ret < 0) return ret; break; default: pr_err("failed to register map %s (%d): invalid type given\n", maps[i].name, i); return -EINVAL; } } maps_node = kzalloc(sizeof(*maps_node), GFP_KERNEL); if (!maps_node) return -ENOMEM; maps_node->maps = maps; maps_node->num_maps = num_maps; mutex_lock(&pinctrl_maps_mutex); list_add_tail(&maps_node->node, &pinctrl_maps); mutex_unlock(&pinctrl_maps_mutex); return 0; } EXPORT_SYMBOL_GPL(pinctrl_register_mappings); /** * pinctrl_unregister_mappings() - unregister a set of pin controller mappings * @map: the pincontrol mappings table passed to pinctrl_register_mappings() * when registering the mappings. */ void pinctrl_unregister_mappings(const struct pinctrl_map *map) { struct pinctrl_maps *maps_node; mutex_lock(&pinctrl_maps_mutex); list_for_each_entry(maps_node, &pinctrl_maps, node) { if (maps_node->maps == map) { list_del(&maps_node->node); kfree(maps_node); mutex_unlock(&pinctrl_maps_mutex); return; } } mutex_unlock(&pinctrl_maps_mutex); } EXPORT_SYMBOL_GPL(pinctrl_unregister_mappings); /** * pinctrl_force_sleep() - turn a given controller device into sleep state * @pctldev: pin controller device */ int pinctrl_force_sleep(struct pinctrl_dev *pctldev) { if (!IS_ERR(pctldev->p) && !IS_ERR(pctldev->hog_sleep)) return pinctrl_commit_state(pctldev->p, pctldev->hog_sleep); return 0; } EXPORT_SYMBOL_GPL(pinctrl_force_sleep); /** * pinctrl_force_default() - turn a given controller device into default state * @pctldev: pin controller device */ int pinctrl_force_default(struct pinctrl_dev *pctldev) { if (!IS_ERR(pctldev->p) && !IS_ERR(pctldev->hog_default)) return pinctrl_commit_state(pctldev->p, pctldev->hog_default); return 0; } EXPORT_SYMBOL_GPL(pinctrl_force_default); /** * pinctrl_init_done() - tell pinctrl probe is done * * We'll use this time to switch the pins from "init" to "default" unless the * driver selected some other state. * * @dev: device to that's done probing */ int pinctrl_init_done(struct device *dev) { struct dev_pin_info *pins = dev->pins; int ret; if (!pins) return 0; if (IS_ERR(pins->init_state)) return 0; /* No such state */ if (pins->p->state != pins->init_state) return 0; /* Not at init anyway */ if (IS_ERR(pins->default_state)) return 0; /* No default state */ ret = pinctrl_select_state(pins->p, pins->default_state); if (ret) dev_err(dev, "failed to activate default pinctrl state\n"); return ret; } static int pinctrl_select_bound_state(struct device *dev, struct pinctrl_state *state) { struct dev_pin_info *pins = dev->pins; int ret; if (IS_ERR(state)) return 0; /* No such state */ ret = pinctrl_select_state(pins->p, state); if (ret) dev_err(dev, "failed to activate pinctrl state %s\n", state->name); return ret; } /** * pinctrl_select_default_state() - select default pinctrl state * @dev: device to select default state for */ int pinctrl_select_default_state(struct device *dev) { if (!dev->pins) return 0; return pinctrl_select_bound_state(dev, dev->pins->default_state); } EXPORT_SYMBOL_GPL(pinctrl_select_default_state); #ifdef CONFIG_PM /** * pinctrl_pm_select_default_state() - select default pinctrl state for PM * @dev: device to select default state for */ int pinctrl_pm_select_default_state(struct device *dev) { return pinctrl_select_default_state(dev); } EXPORT_SYMBOL_GPL(pinctrl_pm_select_default_state); /** * pinctrl_pm_select_sleep_state() - select sleep pinctrl state for PM * @dev: device to select sleep state for */ int pinctrl_pm_select_sleep_state(struct device *dev) { if (!dev->pins) return 0; return pinctrl_select_bound_state(dev, dev->pins->sleep_state); } EXPORT_SYMBOL_GPL(pinctrl_pm_select_sleep_state); /** * pinctrl_pm_select_idle_state() - select idle pinctrl state for PM * @dev: device to select idle state for */ int pinctrl_pm_select_idle_state(struct device *dev) { if (!dev->pins) return 0; return pinctrl_select_bound_state(dev, dev->pins->idle_state); } EXPORT_SYMBOL_GPL(pinctrl_pm_select_idle_state); #endif #ifdef CONFIG_DEBUG_FS static int pinctrl_pins_show(struct seq_file *s, void *what) { struct pinctrl_dev *pctldev = s->private; const struct pinctrl_ops *ops = pctldev->desc->pctlops; unsigned int i, pin; #ifdef CONFIG_GPIOLIB struct gpio_device *gdev = NULL; struct pinctrl_gpio_range *range; int gpio_num; #endif seq_printf(s, "registered pins: %d\n", pctldev->desc->npins); mutex_lock(&pctldev->mutex); /* The pin number can be retrived from the pin controller descriptor */ for (i = 0; i < pctldev->desc->npins; i++) { struct pin_desc *desc; pin = pctldev->desc->pins[i].number; desc = pin_desc_get(pctldev, pin); /* Pin space may be sparse */ if (!desc) continue; seq_printf(s, "pin %d (%s) ", pin, desc->name); #ifdef CONFIG_GPIOLIB gpio_num = -1; list_for_each_entry(range, &pctldev->gpio_ranges, node) { if ((pin >= range->pin_base) && (pin < (range->pin_base + range->npins))) { gpio_num = range->base + (pin - range->pin_base); break; } } if (gpio_num >= 0) /* * FIXME: gpio_num comes from the global GPIO numberspace. * we need to get rid of the range->base eventually and * get the descriptor directly from the gpio_chip. */ gdev = gpiod_to_gpio_device(gpio_to_desc(gpio_num)); if (gdev) seq_printf(s, "%u:%s ", gpio_num - gpio_device_get_base(gdev), gpio_device_get_label(gdev)); else seq_puts(s, "0:? "); #endif /* Driver-specific info per pin */ if (ops->pin_dbg_show) ops->pin_dbg_show(pctldev, s, pin); seq_puts(s, "\n"); } mutex_unlock(&pctldev->mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl_pins); static int pinctrl_groups_show(struct seq_file *s, void *what) { struct pinctrl_dev *pctldev = s->private; const struct pinctrl_ops *ops = pctldev->desc->pctlops; unsigned int ngroups, selector = 0; mutex_lock(&pctldev->mutex); ngroups = ops->get_groups_count(pctldev); seq_puts(s, "registered pin groups:\n"); while (selector < ngroups) { const unsigned int *pins = NULL; unsigned int num_pins = 0; const char *gname = ops->get_group_name(pctldev, selector); const char *pname; int ret = 0; int i; if (ops->get_group_pins) ret = ops->get_group_pins(pctldev, selector, &pins, &num_pins); if (ret) seq_printf(s, "%s [ERROR GETTING PINS]\n", gname); else { seq_printf(s, "group: %s\n", gname); for (i = 0; i < num_pins; i++) { pname = pin_get_name(pctldev, pins[i]); if (WARN_ON(!pname)) { mutex_unlock(&pctldev->mutex); return -EINVAL; } seq_printf(s, "pin %d (%s)\n", pins[i], pname); } seq_puts(s, "\n"); } selector++; } mutex_unlock(&pctldev->mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl_groups); static int pinctrl_gpioranges_show(struct seq_file *s, void *what) { struct pinctrl_dev *pctldev = s->private; struct pinctrl_gpio_range *range; seq_puts(s, "GPIO ranges handled:\n"); mutex_lock(&pctldev->mutex); /* Loop over the ranges */ list_for_each_entry(range, &pctldev->gpio_ranges, node) { if (range->pins) { int a; seq_printf(s, "%u: %s GPIOS [%u - %u] PINS {", range->id, range->name, range->base, (range->base + range->npins - 1)); for (a = 0; a < range->npins - 1; a++) seq_printf(s, "%u, ", range->pins[a]); seq_printf(s, "%u}\n", range->pins[a]); } else seq_printf(s, "%u: %s GPIOS [%u - %u] PINS [%u - %u]\n", range->id, range->name, range->base, (range->base + range->npins - 1), range->pin_base, (range->pin_base + range->npins - 1)); } mutex_unlock(&pctldev->mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl_gpioranges); static int pinctrl_devices_show(struct seq_file *s, void *what) { struct pinctrl_dev *pctldev; seq_puts(s, "name [pinmux] [pinconf]\n"); mutex_lock(&pinctrldev_list_mutex); list_for_each_entry(pctldev, &pinctrldev_list, node) { seq_printf(s, "%s ", pctldev->desc->name); if (pctldev->desc->pmxops) seq_puts(s, "yes "); else seq_puts(s, "no "); if (pctldev->desc->confops) seq_puts(s, "yes"); else seq_puts(s, "no"); seq_puts(s, "\n"); } mutex_unlock(&pinctrldev_list_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl_devices); static inline const char *map_type(enum pinctrl_map_type type) { static const char * const names[] = { "INVALID", "DUMMY_STATE", "MUX_GROUP", "CONFIGS_PIN", "CONFIGS_GROUP", }; if (type >= ARRAY_SIZE(names)) return "UNKNOWN"; return names[type]; } static int pinctrl_maps_show(struct seq_file *s, void *what) { struct pinctrl_maps *maps_node; const struct pinctrl_map *map; seq_puts(s, "Pinctrl maps:\n"); mutex_lock(&pinctrl_maps_mutex); for_each_pin_map(maps_node, map) { seq_printf(s, "device %s\nstate %s\ntype %s (%d)\n", map->dev_name, map->name, map_type(map->type), map->type); if (map->type != PIN_MAP_TYPE_DUMMY_STATE) seq_printf(s, "controlling device %s\n", map->ctrl_dev_name); switch (map->type) { case PIN_MAP_TYPE_MUX_GROUP: pinmux_show_map(s, map); break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: pinconf_show_map(s, map); break; default: break; } seq_putc(s, '\n'); } mutex_unlock(&pinctrl_maps_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl_maps); static int pinctrl_show(struct seq_file *s, void *what) { struct pinctrl *p; struct pinctrl_state *state; struct pinctrl_setting *setting; seq_puts(s, "Requested pin control handlers their pinmux maps:\n"); mutex_lock(&pinctrl_list_mutex); list_for_each_entry(p, &pinctrl_list, node) { seq_printf(s, "device: %s current state: %s\n", dev_name(p->dev), p->state ? p->state->name : "none"); list_for_each_entry(state, &p->states, node) { seq_printf(s, " state: %s\n", state->name); list_for_each_entry(setting, &state->settings, node) { struct pinctrl_dev *pctldev = setting->pctldev; seq_printf(s, " type: %s controller %s ", map_type(setting->type), pinctrl_dev_get_name(pctldev)); switch (setting->type) { case PIN_MAP_TYPE_MUX_GROUP: pinmux_show_setting(s, setting); break; case PIN_MAP_TYPE_CONFIGS_PIN: case PIN_MAP_TYPE_CONFIGS_GROUP: pinconf_show_setting(s, setting); break; default: break; } } } } mutex_unlock(&pinctrl_list_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(pinctrl); static struct dentry *debugfs_root; static void pinctrl_init_device_debugfs(struct pinctrl_dev *pctldev) { struct dentry *device_root; const char *debugfs_name; if (pctldev->desc->name && strcmp(dev_name(pctldev->dev), pctldev->desc->name)) { debugfs_name = devm_kasprintf(pctldev->dev, GFP_KERNEL, "%s-%s", dev_name(pctldev->dev), pctldev->desc->name); if (!debugfs_name) { pr_warn("failed to determine debugfs dir name for %s\n", dev_name(pctldev->dev)); return; } } else { debugfs_name = dev_name(pctldev->dev); } device_root = debugfs_create_dir(debugfs_name, debugfs_root); pctldev->device_root = device_root; if (IS_ERR(device_root) || !device_root) { pr_warn("failed to create debugfs directory for %s\n", dev_name(pctldev->dev)); return; } debugfs_create_file("pins", 0444, device_root, pctldev, &pinctrl_pins_fops); debugfs_create_file("pingroups", 0444, device_root, pctldev, &pinctrl_groups_fops); debugfs_create_file("gpio-ranges", 0444, device_root, pctldev, &pinctrl_gpioranges_fops); if (pctldev->desc->pmxops) pinmux_init_device_debugfs(device_root, pctldev); if (pctldev->desc->confops) pinconf_init_device_debugfs(device_root, pctldev); } static void pinctrl_remove_device_debugfs(struct pinctrl_dev *pctldev) { debugfs_remove_recursive(pctldev->device_root); } static void pinctrl_init_debugfs(void) { debugfs_root = debugfs_create_dir("pinctrl", NULL); if (IS_ERR(debugfs_root) || !debugfs_root) { pr_warn("failed to create debugfs directory\n"); debugfs_root = NULL; return; } debugfs_create_file("pinctrl-devices", 0444, debugfs_root, NULL, &pinctrl_devices_fops); debugfs_create_file("pinctrl-maps", 0444, debugfs_root, NULL, &pinctrl_maps_fops); debugfs_create_file("pinctrl-handles", 0444, debugfs_root, NULL, &pinctrl_fops); } #else /* CONFIG_DEBUG_FS */ static void pinctrl_init_device_debugfs(struct pinctrl_dev *pctldev) { } static void pinctrl_init_debugfs(void) { } static void pinctrl_remove_device_debugfs(struct pinctrl_dev *pctldev) { } #endif static int pinctrl_check_ops(struct pinctrl_dev *pctldev) { const struct pinctrl_ops *ops = pctldev->desc->pctlops; if (!ops || !ops->get_groups_count || !ops->get_group_name) return -EINVAL; return 0; } /** * pinctrl_init_controller() - init a pin controller device * @pctldesc: descriptor for this pin controller * @dev: parent device for this pin controller * @driver_data: private pin controller data for this pin controller */ static struct pinctrl_dev * pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data) { struct pinctrl_dev *pctldev; int ret; if (!pctldesc) return ERR_PTR(-EINVAL); if (!pctldesc->name) return ERR_PTR(-EINVAL); pctldev = kzalloc(sizeof(*pctldev), GFP_KERNEL); if (!pctldev) return ERR_PTR(-ENOMEM); /* Initialize pin control device struct */ pctldev->owner = pctldesc->owner; pctldev->desc = pctldesc; pctldev->driver_data = driver_data; INIT_RADIX_TREE(&pctldev->pin_desc_tree, GFP_KERNEL); #ifdef CONFIG_GENERIC_PINCTRL_GROUPS INIT_RADIX_TREE(&pctldev->pin_group_tree, GFP_KERNEL); #endif #ifdef CONFIG_GENERIC_PINMUX_FUNCTIONS INIT_RADIX_TREE(&pctldev->pin_function_tree, GFP_KERNEL); #endif INIT_LIST_HEAD(&pctldev->gpio_ranges); INIT_LIST_HEAD(&pctldev->node); pctldev->dev = dev; mutex_init(&pctldev->mutex); /* check core ops for sanity */ ret = pinctrl_check_ops(pctldev); if (ret) { dev_err(dev, "pinctrl ops lacks necessary functions\n"); goto out_err; } /* If we're implementing pinmuxing, check the ops for sanity */ if (pctldesc->pmxops) { ret = pinmux_check_ops(pctldev); if (ret) goto out_err; } /* If we're implementing pinconfig, check the ops for sanity */ if (pctldesc->confops) { ret = pinconf_check_ops(pctldev); if (ret) goto out_err; } /* Register all the pins */ dev_dbg(dev, "try to register %d pins ...\n", pctldesc->npins); ret = pinctrl_register_pins(pctldev, pctldesc->pins, pctldesc->npins); if (ret) { dev_err(dev, "error during pin registration\n"); pinctrl_free_pindescs(pctldev, pctldesc->pins, pctldesc->npins); goto out_err; } return pctldev; out_err: mutex_destroy(&pctldev->mutex); kfree(pctldev); return ERR_PTR(ret); } static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev) { pctldev->p = create_pinctrl(pctldev->dev, pctldev); if (PTR_ERR(pctldev->p) == -ENODEV) { dev_dbg(pctldev->dev, "no hogs found\n"); return 0; } if (IS_ERR(pctldev->p)) { dev_err(pctldev->dev, "error claiming hogs: %li\n", PTR_ERR(pctldev->p)); return PTR_ERR(pctldev->p); } pctldev->hog_default = pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT); if (IS_ERR(pctldev->hog_default)) { dev_dbg(pctldev->dev, "failed to lookup the default state\n"); } else { if (pinctrl_select_state(pctldev->p, pctldev->hog_default)) dev_err(pctldev->dev, "failed to select default state\n"); } pctldev->hog_sleep = pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_SLEEP); if (IS_ERR(pctldev->hog_sleep)) dev_dbg(pctldev->dev, "failed to lookup the sleep state\n"); return 0; } int pinctrl_enable(struct pinctrl_dev *pctldev) { int error; error = pinctrl_claim_hogs(pctldev); if (error) { dev_err(pctldev->dev, "could not claim hogs: %i\n", error); return error; } mutex_lock(&pinctrldev_list_mutex); list_add_tail(&pctldev->node, &pinctrldev_list); mutex_unlock(&pinctrldev_list_mutex); pinctrl_init_device_debugfs(pctldev); return 0; } EXPORT_SYMBOL_GPL(pinctrl_enable); /** * pinctrl_register() - register a pin controller device * @pctldesc: descriptor for this pin controller * @dev: parent device for this pin controller * @driver_data: private pin controller data for this pin controller * * Note that pinctrl_register() is known to have problems as the pin * controller driver functions are called before the driver has a * struct pinctrl_dev handle. To avoid issues later on, please use the * new pinctrl_register_and_init() below instead. */ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data) { struct pinctrl_dev *pctldev; int error; pctldev = pinctrl_init_controller(pctldesc, dev, driver_data); if (IS_ERR(pctldev)) return pctldev; error = pinctrl_enable(pctldev); if (error) return ERR_PTR(error); return pctldev; } EXPORT_SYMBOL_GPL(pinctrl_register); /** * pinctrl_register_and_init() - register and init pin controller device * @pctldesc: descriptor for this pin controller * @dev: parent device for this pin controller * @driver_data: private pin controller data for this pin controller * @pctldev: pin controller device * * Note that pinctrl_enable() still needs to be manually called after * this once the driver is ready. */ int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data, struct pinctrl_dev **pctldev) { struct pinctrl_dev *p; p = pinctrl_init_controller(pctldesc, dev, driver_data); if (IS_ERR(p)) return PTR_ERR(p); /* * We have pinctrl_start() call functions in the pin controller * driver with create_pinctrl() for at least dt_node_to_map(). So * let's make sure pctldev is properly initialized for the * pin controller driver before we do anything. */ *pctldev = p; return 0; } EXPORT_SYMBOL_GPL(pinctrl_register_and_init); /** * pinctrl_unregister() - unregister pinmux * @pctldev: pin controller to unregister * * Called by pinmux drivers to unregister a pinmux. */ void pinctrl_unregister(struct pinctrl_dev *pctldev) { struct pinctrl_gpio_range *range, *n; if (!pctldev) return; mutex_lock(&pctldev->mutex); pinctrl_remove_device_debugfs(pctldev); mutex_unlock(&pctldev->mutex); if (!IS_ERR_OR_NULL(pctldev->p)) pinctrl_put(pctldev->p); mutex_lock(&pinctrldev_list_mutex); mutex_lock(&pctldev->mutex); /* TODO: check that no pinmuxes are still active? */ list_del(&pctldev->node); pinmux_generic_free_functions(pctldev); pinctrl_generic_free_groups(pctldev); /* Destroy descriptor tree */ pinctrl_free_pindescs(pctldev, pctldev->desc->pins, pctldev->desc->npins); /* remove gpio ranges map */ list_for_each_entry_safe(range, n, &pctldev->gpio_ranges, node) list_del(&range->node); mutex_unlock(&pctldev->mutex); mutex_destroy(&pctldev->mutex); kfree(pctldev); mutex_unlock(&pinctrldev_list_mutex); } EXPORT_SYMBOL_GPL(pinctrl_unregister); static void devm_pinctrl_dev_release(struct device *dev, void *res) { struct pinctrl_dev *pctldev = *(struct pinctrl_dev **)res; pinctrl_unregister(pctldev); } static int devm_pinctrl_dev_match(struct device *dev, void *res, void *data) { struct pctldev **r = res; if (WARN_ON(!r || !*r)) return 0; return *r == data; } /** * devm_pinctrl_register() - Resource managed version of pinctrl_register(). * @dev: parent device for this pin controller * @pctldesc: descriptor for this pin controller * @driver_data: private pin controller data for this pin controller * * Returns an error pointer if pincontrol register failed. Otherwise * it returns valid pinctrl handle. * * The pinctrl device will be automatically released when the device is unbound. */ struct pinctrl_dev *devm_pinctrl_register(struct device *dev, struct pinctrl_desc *pctldesc, void *driver_data) { struct pinctrl_dev **ptr, *pctldev; ptr = devres_alloc(devm_pinctrl_dev_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); pctldev = pinctrl_register(pctldesc, dev, driver_data); if (IS_ERR(pctldev)) { devres_free(ptr); return pctldev; } *ptr = pctldev; devres_add(dev, ptr); return pctldev; } EXPORT_SYMBOL_GPL(devm_pinctrl_register); /** * devm_pinctrl_register_and_init() - Resource managed pinctrl register and init * @dev: parent device for this pin controller * @pctldesc: descriptor for this pin controller * @driver_data: private pin controller data for this pin controller * @pctldev: pin controller device * * Returns zero on success or an error number on failure. * * The pinctrl device will be automatically released when the device is unbound. */ int devm_pinctrl_register_and_init(struct device *dev, struct pinctrl_desc *pctldesc, void *driver_data, struct pinctrl_dev **pctldev) { struct pinctrl_dev **ptr; int error; ptr = devres_alloc(devm_pinctrl_dev_release, sizeof(*ptr), GFP_KERNEL); if (!ptr) return -ENOMEM; error = pinctrl_register_and_init(pctldesc, dev, driver_data, pctldev); if (error) { devres_free(ptr); return error; } *ptr = *pctldev; devres_add(dev, ptr); return 0; } EXPORT_SYMBOL_GPL(devm_pinctrl_register_and_init); /** * devm_pinctrl_unregister() - Resource managed version of pinctrl_unregister(). * @dev: device for which resource was allocated * @pctldev: the pinctrl device to unregister. */ void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev) { WARN_ON(devres_release(dev, devm_pinctrl_dev_release, devm_pinctrl_dev_match, pctldev)); } EXPORT_SYMBOL_GPL(devm_pinctrl_unregister); static int __init pinctrl_init(void) { pr_info("initialized pinctrl subsystem\n"); pinctrl_init_debugfs(); return 0; } /* init early since many drivers really need to initialized pinmux early */ core_initcall(pinctrl_init); |
| 18 6 6 6 18 18 18 18 18 18 15 15 6 6 6 6 6 6 1 1 7 7 7 7 7 1 6 7 7 7 7 6 6 6 1 1 1 6 6 6 6 6 5 6 6 6 6 6 6 2 5 6 6 6 2 8 8 1 10 1 2 1 1 1 2 1 1 1 1 1 1 1 1 1 1 18 18 18 15 16 2 10 1 1 1 1 1 18 18 18 18 18 16 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 6 6 6 7 7 7 8 1 6 2 2 6 6 6 6 6 6 6 5 2 2 6 1 1 8 8 1 1 1 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * * Copyright (C) 2012 Google, Inc. * Will Drewry <wad@chromium.org> * * This defines a simple but solid secure-computing facility. * * Mode 1 uses a fixed list of allowed system calls. * Mode 2 allows user-defined system call filters in the form * of Berkeley Packet Filters/Linux Socket Filters. */ #define pr_fmt(fmt) "seccomp: " fmt #include <linux/refcount.h> #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> #include <linux/kmemleak.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/sysctl.h> /* Not exposed in headers: strictly internal use only. */ #define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> #endif #ifdef CONFIG_SECCOMP_FILTER #include <linux/file.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> #include <linux/capability.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> #include <linux/lockdep.h> /* * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the * wrong direction flag in the ioctl number. This is the broken one, * which the kernel needs to keep supporting until all userspaces stop * using the wrong command number. */ #define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, SECCOMP_NOTIFY_REPLIED, }; struct seccomp_knotif { /* The struct pid of the task whose filter triggered the notification */ struct task_struct *task; /* The "cookie" for this request; this is unique for this filter. */ u64 id; /* * The seccomp data. This pointer is valid the entire time this * notification is active, since it comes from __seccomp_filter which * eclipses the entire lifecycle here. */ const struct seccomp_data *data; /* * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a * struct seccomp_knotif is created and starts out in INIT. Once the * handler reads the notification off of an FD, it transitions to SENT. * If a signal is received the state transitions back to INIT and * another message is sent. When the userspace handler replies, state * transitions to REPLIED. */ enum notify_state state; /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ int error; long val; u32 flags; /* * Signals when this has changed states, such as the listener * dying, a new seccomp addfd message, or changing to REPLIED */ struct completion ready; struct list_head list; /* outstanding addfd requests */ struct list_head addfd; }; /** * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages * * @file: A reference to the file to install in the other task * @fd: The fd number to install it at. If the fd number is -1, it means the * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. * @ioctl_flags: The flags used for the seccomp_addfd ioctl. * @setfd: whether or not SECCOMP_ADDFD_FLAG_SETFD was set during notify_addfd * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd * installation, or gone away (either due to successful * reply, or signal) * @list: list_head for chaining seccomp_kaddfd together. * */ struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; __u32 ioctl_flags; union { bool setfd; /* To only be set on reply */ int ret; }; struct completion completion; struct list_head list; }; /** * struct notification - container for seccomp userspace notifications. Since * most seccomp filters will not have notification listeners attached and this * structure is fairly large, we store the notification-specific stuff in a * separate structure. * * @requests: A semaphore that users of this notification can wait on for * changes. Actual reads and writes are still controlled with * filter->notify_lock. * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags. * @next_id: The id of the next request. * @notifications: A list of struct seccomp_knotif elements. */ struct notification { atomic_t requests; u32 flags; u64 next_id; struct list_head notifications; }; #ifdef SECCOMP_ARCH_NATIVE /** * struct action_cache - per-filter cache of seccomp actions per * arch/syscall pair * * @allow_native: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * native architecture. * @allow_compat: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * compat architecture. */ struct action_cache { DECLARE_BITMAP(allow_native, SECCOMP_ARCH_NATIVE_NR); #ifdef SECCOMP_ARCH_COMPAT DECLARE_BITMAP(allow_compat, SECCOMP_ARCH_COMPAT_NR); #endif }; #else struct action_cache { }; static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { return false; } static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter) { } #endif /* SECCOMP_ARCH_NATIVE */ /** * struct seccomp_filter - container for seccomp BPF programs * * @refs: Reference count to manage the object lifetime. * A filter's reference count is incremented for each directly * attached task, once for the dependent filter, and if * requested for the user notifier. When @refs reaches zero, * the filter can be freed. * @users: A filter's @users count is incremented for each directly * attached task (filter installation, fork(), thread_sync), * and once for the dependent filter (tracked in filter->prev). * When it reaches zero it indicates that no direct or indirect * users of that filter exist. No new tasks can get associated with * this filter after reaching 0. The @users count is always smaller * or equal to @refs. Hence, reaching 0 for @users does not mean * the filter can be freed. * @cache: cache of arch/syscall mappings to actions * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @wait_killable_recv: Put notifying process in killable state once the * notification is received by the userspace listener. * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information * @notify_lock: A lock for all notification-related accesses. * @wqh: A wait queue for poll if a notifier is in use. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting * with current->seccomp.filter, the most recently attached or inherited filter. * However, multiple filters may share a @prev node, by way of fork(), which * results in a unidirectional tree existing in memory. This is similar to * how namespaces work. * * seccomp_filter objects should never be modified after being attached * to a task_struct (other than @refs). */ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; bool wait_killable_recv; struct action_cache cache; struct seccomp_filter *prev; struct bpf_prog *prog; struct notification *notif; struct mutex notify_lock; wait_queue_head_t wqh; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) /* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ static void populate_seccomp_data(struct seccomp_data *sd) { /* * Instead of using current_pt_reg(), we're already doing the work * to safely fetch "current", so just use "task" everywhere below. */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(task); syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; sd->args[3] = args[3]; sd->args[4] = args[4]; sd->args[5] = args[5]; sd->instruction_pointer = KSTK_EIP(task); } /** * seccomp_check_filter - verify seccomp filter code * @filter: filter to verify * @flen: length of filter * * Takes a previously checked filter (by bpf_check_classic) and * redirects all filter code that loads struct sk_buff data * and related data through seccomp_bpf_load. It also * enforces length and alignment checking of those loads. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) { int pc; for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; u16 code = ftest->code; u32 k = ftest->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; } } return 0; } #ifdef SECCOMP_ARCH_NATIVE static inline bool seccomp_cache_check_allow_bitmap(const void *bitmap, size_t bitmap_size, int syscall_nr) { if (unlikely(syscall_nr < 0 || syscall_nr >= bitmap_size)) return false; syscall_nr = array_index_nospec(syscall_nr, bitmap_size); return test_bit(syscall_nr, bitmap); } /** * seccomp_cache_check_allow - lookup seccomp cache * @sfilter: The seccomp filter * @sd: The seccomp data to lookup the cache with * * Returns true if the seccomp_data is cached and allowed. */ static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { int syscall_nr = sd->nr; const struct action_cache *cache = &sfilter->cache; #ifndef SECCOMP_ARCH_COMPAT /* A native-only architecture doesn't need to check sd->arch. */ return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); #else if (likely(sd->arch == SECCOMP_ARCH_NATIVE)) return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); if (likely(sd->arch == SECCOMP_ARCH_COMPAT)) return seccomp_cache_check_allow_bitmap(cache->allow_compat, SECCOMP_ARCH_COMPAT_NR, syscall_nr); #endif /* SECCOMP_ARCH_COMPAT */ WARN_ON_ONCE(true); return false; } #endif /* SECCOMP_ARCH_NATIVE */ #define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters * @match: stores struct seccomp_filter that resulted in the return value, * unless filter returned SECCOMP_RET_ALLOW, in which case it will * be unchanged. * * Returns valid seccomp BPF response codes. */ static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; if (seccomp_cache_check_allow(f, sd)) return SECCOMP_RET_ALLOW; /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } return ret; } #endif /* CONFIG_SECCOMP_FILTER */ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) { assert_spin_locked(¤t->sighand->siglock); if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) return false; return true; } void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } static inline void seccomp_assign_mode(struct task_struct *task, unsigned long seccomp_mode, unsigned long flags) { assert_spin_locked(&task->sighand->siglock); task->seccomp.mode = seccomp_mode; /* * Make sure SYSCALL_WORK_SECCOMP cannot be set before the mode (and * filter) is set. */ smp_mb__before_atomic(); /* Assume default seccomp processes want spec flaw mitigation. */ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) arch_seccomp_spec_mitigate(task); set_task_syscall_work(task, SECCOMP); } #ifdef CONFIG_SECCOMP_FILTER /* Returns 1 if the parent is an ancestor of the child. */ static int is_ancestor(struct seccomp_filter *parent, struct seccomp_filter *child) { /* NULL is the root ancestor. */ if (parent == NULL) return 1; for (; child; child = child->prev) if (child == parent) return 1; return 0; } /** * seccomp_can_sync_threads: checks if all threads can be synchronized * * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */ static inline pid_t seccomp_can_sync_threads(void) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Validate all threads being eligible for synchronization. */ caller = current; for_each_thread(caller, thread) { pid_t failed; /* Skip current, since it is initiating the sync. */ if (thread == caller) continue; if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || (thread->seccomp.mode == SECCOMP_MODE_FILTER && is_ancestor(thread->seccomp.filter, caller->seccomp.filter))) continue; /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } return 0; } static inline void seccomp_filter_free(struct seccomp_filter *filter) { if (filter) { bpf_prog_destroy(filter->prog); kfree(filter); } } static void __seccomp_filter_orphan(struct seccomp_filter *orig) { while (orig && refcount_dec_and_test(&orig->users)) { if (waitqueue_active(&orig->wqh)) wake_up_poll(&orig->wqh, EPOLLHUP); orig = orig->prev; } } static void __put_seccomp_filter(struct seccomp_filter *orig) { /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->refs)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); } } static void __seccomp_filter_release(struct seccomp_filter *orig) { /* Notify about any unused filters in the task's former filter tree. */ __seccomp_filter_orphan(orig); /* Finally drop all references to the task's former tree. */ __put_seccomp_filter(orig); } /** * seccomp_filter_release - Detach the task from its filter tree, * drop its reference count, and notify * about unused filters * * @tsk: task the filter should be released from. * * This function should only be called when the task is exiting as * it detaches it from its filter tree. As such, READ_ONCE() and * barriers are not needed here, as would normally be needed. */ void seccomp_filter_release(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; /* We are effectively holding the siglock by not having any sighand. */ WARN_ON(tsk->sighand != NULL); /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; __seccomp_filter_release(orig); } /** * seccomp_sync_threads: sets all threads to use current's filter * * @flags: SECCOMP_FILTER_FLAG_* flags to set during sync. * * Expects sighand and cred_guard_mutex locks to be held, and for * seccomp_can_sync_threads() to have returned success already * without dropping the locks. * */ static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Synchronize all threads. */ caller = current; for_each_thread(caller, thread) { /* Skip current, since it needs no changes. */ if (thread == caller) continue; /* Get a task reference for the new leaf node. */ get_seccomp_filter(caller); /* * Drop the task reference to the shared ancestor since * current's path will hold a reference. (This also * allows a put before the assignment.) */ __seccomp_filter_release(thread->seccomp.filter); /* Make our new filter tree visible. */ smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); atomic_set(&thread->seccomp.filter_count, atomic_read(&caller->seccomp.filter_count)); /* * Don't let an unprivileged task work around * the no_new_privs restriction by creating * a thread that sets it up, enters seccomp, * then dies. */ if (task_no_new_privs(caller)) task_set_no_new_privs(thread); /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, flags); } } /** * seccomp_prepare_filter: Prepares a seccomp filter for use. * @fprog: BPF program to install * * Returns filter on success or an ERR_PTR on failure. */ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) { struct seccomp_filter *sfilter; int ret; const bool save_orig = #if defined(CONFIG_CHECKPOINT_RESTORE) || defined(SECCOMP_ARCH_NATIVE) true; #else false; #endif if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return ERR_PTR(-EINVAL); BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter)); /* * Installing a seccomp filter requires that the task has * CAP_SYS_ADMIN in its namespace or be running with no_new_privs. * This avoids scenarios where unprivileged tasks can affect the * behavior of privileged children. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ sfilter = kzalloc(sizeof(*sfilter), GFP_KERNEL | __GFP_NOWARN); if (!sfilter) return ERR_PTR(-ENOMEM); mutex_init(&sfilter->notify_lock); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, seccomp_check_filter, save_orig); if (ret < 0) { kfree(sfilter); return ERR_PTR(ret); } refcount_set(&sfilter->refs, 1); refcount_set(&sfilter->users, 1); init_waitqueue_head(&sfilter->wqh); return sfilter; } /** * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog * @user_filter: pointer to the user data containing a sock_fprog. * * Returns 0 on success and non-zero otherwise. */ static struct seccomp_filter * seccomp_prepare_user_filter(const char __user *user_filter) { struct sock_fprog fprog; struct seccomp_filter *filter = ERR_PTR(-EFAULT); #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; fprog.len = fprog32.len; fprog.filter = compat_ptr(fprog32.filter); } else /* falls through to the if below. */ #endif if (copy_from_user(&fprog, user_filter, sizeof(fprog))) goto out; filter = seccomp_prepare_filter(&fprog); out: return filter; } #ifdef SECCOMP_ARCH_NATIVE /** * seccomp_is_const_allow - check if filter is constant allow with given data * @fprog: The BPF programs * @sd: The seccomp data to check against, only syscall number and arch * number are considered constant. */ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, struct seccomp_data *sd) { unsigned int reg_value = 0; unsigned int pc; bool op_res; if (WARN_ON_ONCE(!fprog)) return false; for (pc = 0; pc < fprog->len; pc++) { struct sock_filter *insn = &fprog->filter[pc]; u16 code = insn->code; u32 k = insn->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: switch (k) { case offsetof(struct seccomp_data, nr): reg_value = sd->nr; break; case offsetof(struct seccomp_data, arch): reg_value = sd->arch; break; default: /* can't optimize (non-constant value load) */ return false; } break; case BPF_RET | BPF_K: /* reached return with constant values only, check allow */ return k == SECCOMP_RET_ALLOW; case BPF_JMP | BPF_JA: pc += insn->k; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: switch (BPF_OP(code)) { case BPF_JEQ: op_res = reg_value == k; break; case BPF_JGE: op_res = reg_value >= k; break; case BPF_JGT: op_res = reg_value > k; break; case BPF_JSET: op_res = !!(reg_value & k); break; default: /* can't optimize (unknown jump) */ return false; } pc += op_res ? insn->jt : insn->jf; break; case BPF_ALU | BPF_AND | BPF_K: reg_value &= k; break; default: /* can't optimize (unknown insn) */ return false; } } /* ran off the end of the filter?! */ WARN_ON(1); return false; } static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter, void *bitmap, const void *bitmap_prev, size_t bitmap_size, int arch) { struct sock_fprog_kern *fprog = sfilter->prog->orig_prog; struct seccomp_data sd; int nr; if (bitmap_prev) { /* The new filter must be as restrictive as the last. */ bitmap_copy(bitmap, bitmap_prev, bitmap_size); } else { /* Before any filters, all syscalls are always allowed. */ bitmap_fill(bitmap, bitmap_size); } for (nr = 0; nr < bitmap_size; nr++) { /* No bitmap change: not a cacheable action. */ if (!test_bit(nr, bitmap)) continue; sd.nr = nr; sd.arch = arch; /* No bitmap change: continue to always allow. */ if (seccomp_is_const_allow(fprog, &sd)) continue; /* * Not a cacheable action: always run filters. * atomic clear_bit() not needed, filter not visible yet. */ __clear_bit(nr, bitmap); } } /** * seccomp_cache_prepare - emulate the filter to find cacheable syscalls * @sfilter: The seccomp filter * * Returns 0 if successful or -errno if error occurred. */ static void seccomp_cache_prepare(struct seccomp_filter *sfilter) { struct action_cache *cache = &sfilter->cache; const struct action_cache *cache_prev = sfilter->prev ? &sfilter->prev->cache : NULL; seccomp_cache_prepare_bitmap(sfilter, cache->allow_native, cache_prev ? cache_prev->allow_native : NULL, SECCOMP_ARCH_NATIVE_NR, SECCOMP_ARCH_NATIVE); #ifdef SECCOMP_ARCH_COMPAT seccomp_cache_prepare_bitmap(sfilter, cache->allow_compat, cache_prev ? cache_prev->allow_compat : NULL, SECCOMP_ARCH_COMPAT_NR, SECCOMP_ARCH_COMPAT); #endif /* SECCOMP_ARCH_COMPAT */ } #endif /* SECCOMP_ARCH_NATIVE */ /** * seccomp_attach_filter: validate and attach filter * @flags: flags to change filter behavior * @filter: seccomp filter to add to the current process * * Caller must be holding current->sighand->siglock lock. * * Returns 0 on success, -ve on error, or * - in TSYNC mode: the pid of a thread which was either not in the correct * seccomp mode or did not have an ancestral seccomp filter * - in NEW_LISTENER mode: the fd of the new listener */ static long seccomp_attach_filter(unsigned int flags, struct seccomp_filter *filter) { unsigned long total_insns; struct seccomp_filter *walker; assert_spin_locked(¤t->sighand->siglock); /* Validate resulting filter length. */ total_insns = filter->prog->len; for (walker = current->seccomp.filter; walker; walker = walker->prev) total_insns += walker->prog->len + 4; /* 4 instr penalty */ if (total_insns > MAX_INSNS_PER_PATH) return -ENOMEM; /* If thread sync has been requested, check that it is possible. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) { int ret; ret = seccomp_can_sync_threads(); if (ret) { if (flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) return -ESRCH; else return ret; } } /* Set log flag, if present. */ if (flags & SECCOMP_FILTER_FLAG_LOG) filter->log = true; /* Set wait killable flag, if present. */ if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) filter->wait_killable_recv = true; /* * If there is an existing filter, make it the prev and don't drop its * task reference. */ filter->prev = current->seccomp.filter; seccomp_cache_prepare(filter); current->seccomp.filter = filter; atomic_inc(¤t->seccomp.filter_count); /* Now that the new filter is in place, synchronize to all threads. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) seccomp_sync_threads(flags); return 0; } static void __get_seccomp_filter(struct seccomp_filter *filter) { refcount_inc(&filter->refs); } /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; __get_seccomp_filter(orig); refcount_inc(&orig->users); } #endif /* CONFIG_SECCOMP_FILTER */ /* For use with seccomp_actions_logged */ #define SECCOMP_LOG_KILL_PROCESS (1 << 0) #define SECCOMP_LOG_KILL_THREAD (1 << 1) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) #define SECCOMP_LOG_LOG (1 << 5) #define SECCOMP_LOG_ALLOW (1 << 6) #define SECCOMP_LOG_USER_NOTIF (1 << 7) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | SECCOMP_LOG_KILL_THREAD | SECCOMP_LOG_TRAP | SECCOMP_LOG_ERRNO | SECCOMP_LOG_USER_NOTIF | SECCOMP_LOG_TRACE | SECCOMP_LOG_LOG; static inline void seccomp_log(unsigned long syscall, long signr, u32 action, bool requested) { bool log = false; switch (action) { case SECCOMP_RET_ALLOW: break; case SECCOMP_RET_TRAP: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP; break; case SECCOMP_RET_ERRNO: log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO; break; case SECCOMP_RET_TRACE: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; case SECCOMP_RET_USER_NOTIF: log = requested && seccomp_actions_logged & SECCOMP_LOG_USER_NOTIF; break; case SECCOMP_RET_LOG: log = seccomp_actions_logged & SECCOMP_LOG_LOG; break; case SECCOMP_RET_KILL_THREAD: log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; break; case SECCOMP_RET_KILL_PROCESS: default: log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS; } /* * Emit an audit message when the action is RET_KILL_*, RET_LOG, or the * FILTER_FLAG_LOG bit was set. The admin has the ability to silence * any action from being logged by removing the action name from the * seccomp_actions_logged sysctl. */ if (!log) return; audit_seccomp(syscall, signr, action); } /* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit * to limit the stack allocations too. */ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, -1, /* negative terminated */ }; static void __secure_computing_strict(int this_syscall) { const int *allowed_syscalls = mode1_syscalls; #ifdef CONFIG_COMPAT if (in_compat_syscall()) allowed_syscalls = get_compat_mode1_syscalls(); #endif do { if (*allowed_syscalls == this_syscall) return; } while (*++allowed_syscalls != -1); #ifdef SECCOMP_DEBUG dump_stack(); #endif current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } #ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER void secure_computing_strict(int this_syscall) { int mode = current->seccomp.mode; if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return; if (mode == SECCOMP_MODE_DISABLED) return; else if (mode == SECCOMP_MODE_STRICT) __secure_computing_strict(this_syscall); else BUG(); } #else #ifdef CONFIG_SECCOMP_FILTER static u64 seccomp_next_notify_id(struct seccomp_filter *filter) { /* * Note: overflow is ok here, the id just needs to be unique per * filter. */ lockdep_assert_held(&filter->notify_lock); return filter->notif->next_id++; } static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_knotif *n) { int fd; /* * Remove the notification, and reset the list pointers, indicating * that it has been handled. */ list_del_init(&addfd->list); if (!addfd->setfd) fd = receive_fd(addfd->file, NULL, addfd->flags); else fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); addfd->ret = fd; if (addfd->ioctl_flags & SECCOMP_ADDFD_FLAG_SEND) { /* If we fail reset and return an error to the notifier */ if (fd < 0) { n->state = SECCOMP_NOTIFY_SENT; } else { /* Return the FD we just added */ n->flags = 0; n->error = 0; n->val = fd; } } /* * Mark the notification as completed. From this point, addfd mem * might be invalidated and we can't safely read it anymore. */ complete(&addfd->completion); } static bool should_sleep_killable(struct seccomp_filter *match, struct seccomp_knotif *n) { return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT; } static int seccomp_do_user_notification(int this_syscall, struct seccomp_filter *match, const struct seccomp_data *sd) { int err; u32 flags = 0; long ret = 0; struct seccomp_knotif n = {}; struct seccomp_kaddfd *addfd, *tmp; mutex_lock(&match->notify_lock); err = -ENOSYS; if (!match->notif) goto out; n.task = current; n.state = SECCOMP_NOTIFY_INIT; n.data = sd; n.id = seccomp_next_notify_id(match); init_completion(&n.ready); list_add_tail(&n.list, &match->notif->notifications); INIT_LIST_HEAD(&n.addfd); atomic_inc(&match->notif->requests); if (match->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP) wake_up_poll_on_current_cpu(&match->wqh, EPOLLIN | EPOLLRDNORM); else wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM); /* * This is where we wait for a reply from userspace. */ do { bool wait_killable = should_sleep_killable(match, &n); mutex_unlock(&match->notify_lock); if (wait_killable) err = wait_for_completion_killable(&n.ready); else err = wait_for_completion_interruptible(&n.ready); mutex_lock(&match->notify_lock); if (err != 0) { /* * Check to see if the notifcation got picked up and * whether we should switch to wait killable. */ if (!wait_killable && should_sleep_killable(match, &n)) continue; goto interrupted; } addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); /* Check if we were woken up by a addfd message */ if (addfd) seccomp_handle_addfd(addfd, &n); } while (n.state != SECCOMP_NOTIFY_REPLIED); ret = n.val; err = n.error; flags = n.flags; interrupted: /* If there were any pending addfd calls, clear them out */ list_for_each_entry_safe(addfd, tmp, &n.addfd, list) { /* The process went away before we got a chance to handle it */ addfd->ret = -ESRCH; list_del_init(&addfd->list); complete(&addfd->completion); } /* * Note that it's possible the listener died in between the time when * we were notified of a response (or a signal) and when we were able to * re-acquire the lock, so only delete from the list if the * notification actually exists. * * Also note that this test is only valid because there's no way to * *reattach* to a notifier right now. If one is added, we'll need to * keep track of the notif itself and make sure they match here. */ if (match->notif) list_del(&n.list); out: mutex_unlock(&match->notify_lock); /* Userspace requests to continue the syscall. */ if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) return 0; syscall_set_return_value(current, current_pt_regs(), err, ret); return -1; } static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { u32 filter_ret, action; struct seccomp_filter *match = NULL; int data; struct seccomp_data sd_local; /* * Make sure that any changes to mode from another thread have * been seen after SYSCALL_WORK_SECCOMP was seen. */ smp_rmb(); if (!sd) { populate_seccomp_data(&sd_local); sd = &sd_local; } filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; action = filter_ret & SECCOMP_RET_ACTION_FULL; switch (action) { case SECCOMP_RET_ERRNO: /* Set low-order bits as an errno, capped at MAX_ERRNO. */ if (data > MAX_ERRNO) data = MAX_ERRNO; syscall_set_return_value(current, current_pt_regs(), -data, 0); goto skip; case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ syscall_rollback(current, current_pt_regs()); /* Let the filter pass back 16 bits of data. */ force_sig_seccomp(this_syscall, data, false); goto skip; case SECCOMP_RET_TRACE: /* We've been put in this state by the ptracer already. */ if (recheck_after_trace) return 0; /* ENOSYS these calls if there is no tracer attached. */ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { syscall_set_return_value(current, current_pt_regs(), -ENOSYS, 0); goto skip; } /* Allow the BPF to provide the event message */ ptrace_event(PTRACE_EVENT_SECCOMP, data); /* * The delivery of a fatal signal during event * notification may silently skip tracer notification, * which could leave us with a potentially unmodified * syscall that the tracer would have liked to have * changed. Since the process is about to die, we just * force the syscall to be skipped and let the signal * kill the process and correctly handle any tracer exit * notifications. */ if (fatal_signal_pending(current)) goto skip; /* Check if the tracer forced the syscall to be skipped. */ this_syscall = syscall_get_nr(current, current_pt_regs()); if (this_syscall < 0) goto skip; /* * Recheck the syscall, since it may have changed. This * intentionally uses a NULL struct seccomp_data to force * a reload of all registers. This does not goto skip since * a skip would have already been reported. */ if (__seccomp_filter(this_syscall, NULL, true)) return -1; return 0; case SECCOMP_RET_USER_NOTIF: if (seccomp_do_user_notification(this_syscall, match, sd)) goto skip; return 0; case SECCOMP_RET_LOG: seccomp_log(this_syscall, 0, action, true); return 0; case SECCOMP_RET_ALLOW: /* * Note that the "match" filter will always be NULL for * this action since SECCOMP_RET_ALLOW is the starting * state in seccomp_run_filters(). */ return 0; case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_KILL_PROCESS: default: current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (action != SECCOMP_RET_KILL_THREAD || (atomic_read(¤t->signal->live) == 1)) { /* Show the original registers in the dump. */ syscall_rollback(current, current_pt_regs()); /* Trigger a coredump with SIGSYS */ force_sig_seccomp(this_syscall, data, true); } else { do_exit(SIGSYS); } return -1; /* skip the syscall go directly to signal handling */ } unreachable(); skip: seccomp_log(this_syscall, 0, action, match ? match->log : false); return -1; } #else static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { BUG(); return -1; } #endif int __secure_computing(const struct seccomp_data *sd) { int mode = current->seccomp.mode; int this_syscall; if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return 0; this_syscall = sd ? sd->nr : syscall_get_nr(current, current_pt_regs()); switch (mode) { case SECCOMP_MODE_STRICT: __secure_computing_strict(this_syscall); /* may call do_exit */ return 0; case SECCOMP_MODE_FILTER: return __seccomp_filter(this_syscall, sd, false); /* Surviving SECCOMP_RET_KILL_* must be proactively impossible. */ case SECCOMP_MODE_DEAD: WARN_ON_ONCE(1); do_exit(SIGKILL); return -1; default: BUG(); } } #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ long prctl_get_seccomp(void) { return current->seccomp.mode; } /** * seccomp_set_mode_strict: internal function for setting strict seccomp * * Once current->seccomp.mode is non-zero, it may not be changed. * * Returns 0 on success or -EINVAL on failure. */ static long seccomp_set_mode_strict(void) { const unsigned long seccomp_mode = SECCOMP_MODE_STRICT; long ret = -EINVAL; spin_lock_irq(¤t->sighand->siglock); if (!seccomp_may_assign_mode(seccomp_mode)) goto out; #ifdef TIF_NOTSC disable_TSC(); #endif seccomp_assign_mode(current, seccomp_mode, 0); ret = 0; out: spin_unlock_irq(¤t->sighand->siglock); return ret; } #ifdef CONFIG_SECCOMP_FILTER static void seccomp_notify_free(struct seccomp_filter *filter) { kfree(filter->notif); filter->notif = NULL; } static void seccomp_notify_detach(struct seccomp_filter *filter) { struct seccomp_knotif *knotif; if (!filter) return; mutex_lock(&filter->notify_lock); /* * If this file is being closed because e.g. the task who owned it * died, let's wake everyone up who was waiting on us. */ list_for_each_entry(knotif, &filter->notif->notifications, list) { if (knotif->state == SECCOMP_NOTIFY_REPLIED) continue; knotif->state = SECCOMP_NOTIFY_REPLIED; knotif->error = -ENOSYS; knotif->val = 0; /* * We do not need to wake up any pending addfd messages, as * the notifier will do that for us, as this just looks * like a standard reply. */ complete(&knotif->ready); } seccomp_notify_free(filter); mutex_unlock(&filter->notify_lock); } static int seccomp_notify_release(struct inode *inode, struct file *file) { struct seccomp_filter *filter = file->private_data; seccomp_notify_detach(filter); __put_seccomp_filter(filter); return 0; } /* must be called with notif_lock held */ static inline struct seccomp_knotif * find_notification(struct seccomp_filter *filter, u64 id) { struct seccomp_knotif *cur; lockdep_assert_held(&filter->notify_lock); list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->id == id) return cur; } return NULL; } static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { /* Avoid a wakeup if event not interesting for us. */ if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR))) return 0; return autoremove_wake_function(wait, mode, sync, key); } static int recv_wait_event(struct seccomp_filter *filter) { DEFINE_WAIT_FUNC(wait, recv_wake_function); int ret; if (atomic_dec_if_positive(&filter->notif->requests) >= 0) return 0; for (;;) { ret = prepare_to_wait_event(&filter->wqh, &wait, TASK_INTERRUPTIBLE); if (atomic_dec_if_positive(&filter->notif->requests) >= 0) break; if (ret) return ret; schedule(); } finish_wait(&filter->wqh, &wait); return 0; } static long seccomp_notify_recv(struct seccomp_filter *filter, void __user *buf) { struct seccomp_knotif *knotif = NULL, *cur; struct seccomp_notif unotif; ssize_t ret; /* Verify that we're not given garbage to keep struct extensible. */ ret = check_zeroed_user(buf, sizeof(unotif)); if (ret < 0) return ret; if (!ret) return -EINVAL; memset(&unotif, 0, sizeof(unotif)); ret = recv_wait_event(filter); if (ret < 0) return ret; mutex_lock(&filter->notify_lock); list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->state == SECCOMP_NOTIFY_INIT) { knotif = cur; break; } } /* * If we didn't find a notification, it could be that the task was * interrupted by a fatal signal between the time we were woken and * when we were able to acquire the rw lock. */ if (!knotif) { ret = -ENOENT; goto out; } unotif.id = knotif->id; unotif.pid = task_pid_vnr(knotif->task); unotif.data = *(knotif->data); knotif->state = SECCOMP_NOTIFY_SENT; wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM); ret = 0; out: mutex_unlock(&filter->notify_lock); if (ret == 0 && copy_to_user(buf, &unotif, sizeof(unotif))) { ret = -EFAULT; /* * Userspace screwed up. To make sure that we keep this * notification alive, let's reset it back to INIT. It * may have died when we released the lock, so we need to make * sure it's still around. */ mutex_lock(&filter->notify_lock); knotif = find_notification(filter, unotif.id); if (knotif) { /* Reset the process to make sure it's not stuck */ if (should_sleep_killable(filter, knotif)) complete(&knotif->ready); knotif->state = SECCOMP_NOTIFY_INIT; atomic_inc(&filter->notif->requests); wake_up_poll(&filter->wqh, EPOLLIN | EPOLLRDNORM); } mutex_unlock(&filter->notify_lock); } return ret; } static long seccomp_notify_send(struct seccomp_filter *filter, void __user *buf) { struct seccomp_notif_resp resp = {}; struct seccomp_knotif *knotif; long ret; if (copy_from_user(&resp, buf, sizeof(resp))) return -EFAULT; if (resp.flags & ~SECCOMP_USER_NOTIF_FLAG_CONTINUE) return -EINVAL; if ((resp.flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) && (resp.error || resp.val)) return -EINVAL; ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) return ret; knotif = find_notification(filter, resp.id); if (!knotif) { ret = -ENOENT; goto out; } /* Allow exactly one reply. */ if (knotif->state != SECCOMP_NOTIFY_SENT) { ret = -EINPROGRESS; goto out; } ret = 0; knotif->state = SECCOMP_NOTIFY_REPLIED; knotif->error = resp.error; knotif->val = resp.val; knotif->flags = resp.flags; if (filter->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP) complete_on_current_cpu(&knotif->ready); else complete(&knotif->ready); out: mutex_unlock(&filter->notify_lock); return ret; } static long seccomp_notify_id_valid(struct seccomp_filter *filter, void __user *buf) { struct seccomp_knotif *knotif; u64 id; long ret; if (copy_from_user(&id, buf, sizeof(id))) return -EFAULT; ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) return ret; knotif = find_notification(filter, id); if (knotif && knotif->state == SECCOMP_NOTIFY_SENT) ret = 0; else ret = -ENOENT; mutex_unlock(&filter->notify_lock); return ret; } static long seccomp_notify_set_flags(struct seccomp_filter *filter, unsigned long flags) { long ret; if (flags & ~SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP) return -EINVAL; ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) return ret; filter->notif->flags = flags; mutex_unlock(&filter->notify_lock); return 0; } static long seccomp_notify_addfd(struct seccomp_filter *filter, struct seccomp_notif_addfd __user *uaddfd, unsigned int size) { struct seccomp_notif_addfd addfd; struct seccomp_knotif *knotif; struct seccomp_kaddfd kaddfd; int ret; BUILD_BUG_ON(sizeof(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0); BUILD_BUG_ON(sizeof(addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST); if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE) return -EINVAL; ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size); if (ret) return ret; if (addfd.newfd_flags & ~O_CLOEXEC) return -EINVAL; if (addfd.flags & ~(SECCOMP_ADDFD_FLAG_SETFD | SECCOMP_ADDFD_FLAG_SEND)) return -EINVAL; if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD)) return -EINVAL; kaddfd.file = fget(addfd.srcfd); if (!kaddfd.file) return -EBADF; kaddfd.ioctl_flags = addfd.flags; kaddfd.flags = addfd.newfd_flags; kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD; kaddfd.fd = addfd.newfd; init_completion(&kaddfd.completion); ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) goto out; knotif = find_notification(filter, addfd.id); if (!knotif) { ret = -ENOENT; goto out_unlock; } /* * We do not want to allow for FD injection to occur before the * notification has been picked up by a userspace handler, or after * the notification has been replied to. */ if (knotif->state != SECCOMP_NOTIFY_SENT) { ret = -EINPROGRESS; goto out_unlock; } if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) { /* * Disallow queuing an atomic addfd + send reply while there are * some addfd requests still to process. * * There is no clear reason to support it and allows us to keep * the loop on the other side straight-forward. */ if (!list_empty(&knotif->addfd)) { ret = -EBUSY; goto out_unlock; } /* Allow exactly only one reply */ knotif->state = SECCOMP_NOTIFY_REPLIED; } list_add(&kaddfd.list, &knotif->addfd); complete(&knotif->ready); mutex_unlock(&filter->notify_lock); /* Now we wait for it to be processed or be interrupted */ ret = wait_for_completion_interruptible(&kaddfd.completion); if (ret == 0) { /* * We had a successful completion. The other side has already * removed us from the addfd queue, and * wait_for_completion_interruptible has a memory barrier upon * success that lets us read this value directly without * locking. */ ret = kaddfd.ret; goto out; } mutex_lock(&filter->notify_lock); /* * Even though we were woken up by a signal and not a successful * completion, a completion may have happened in the mean time. * * We need to check again if the addfd request has been handled, * and if not, we will remove it from the queue. */ if (list_empty(&kaddfd.list)) ret = kaddfd.ret; else list_del(&kaddfd.list); out_unlock: mutex_unlock(&filter->notify_lock); out: fput(kaddfd.file); return ret; } static long seccomp_notify_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seccomp_filter *filter = file->private_data; void __user *buf = (void __user *)arg; /* Fixed-size ioctls */ switch (cmd) { case SECCOMP_IOCTL_NOTIF_RECV: return seccomp_notify_recv(filter, buf); case SECCOMP_IOCTL_NOTIF_SEND: return seccomp_notify_send(filter, buf); case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR: case SECCOMP_IOCTL_NOTIF_ID_VALID: return seccomp_notify_id_valid(filter, buf); case SECCOMP_IOCTL_NOTIF_SET_FLAGS: return seccomp_notify_set_flags(filter, arg); } /* Extensible Argument ioctls */ #define EA_IOCTL(cmd) ((cmd) & ~(IOC_INOUT | IOCSIZE_MASK)) switch (EA_IOCTL(cmd)) { case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD): return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd)); default: return -EINVAL; } } static __poll_t seccomp_notify_poll(struct file *file, struct poll_table_struct *poll_tab) { struct seccomp_filter *filter = file->private_data; __poll_t ret = 0; struct seccomp_knotif *cur; poll_wait(file, &filter->wqh, poll_tab); if (mutex_lock_interruptible(&filter->notify_lock) < 0) return EPOLLERR; list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->state == SECCOMP_NOTIFY_INIT) ret |= EPOLLIN | EPOLLRDNORM; if (cur->state == SECCOMP_NOTIFY_SENT) ret |= EPOLLOUT | EPOLLWRNORM; if ((ret & EPOLLIN) && (ret & EPOLLOUT)) break; } mutex_unlock(&filter->notify_lock); if (refcount_read(&filter->users) == 0) ret |= EPOLLHUP; return ret; } static const struct file_operations seccomp_notify_ops = { .poll = seccomp_notify_poll, .release = seccomp_notify_release, .unlocked_ioctl = seccomp_notify_ioctl, .compat_ioctl = seccomp_notify_ioctl, }; static struct file *init_listener(struct seccomp_filter *filter) { struct file *ret; ret = ERR_PTR(-ENOMEM); filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL); if (!filter->notif) goto out; filter->notif->next_id = get_random_u64(); INIT_LIST_HEAD(&filter->notif->notifications); ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops, filter, O_RDWR); if (IS_ERR(ret)) goto out_notif; /* The file has a reference to it now */ __get_seccomp_filter(filter); out_notif: if (IS_ERR(ret)) seccomp_notify_free(filter); out: return ret; } /* * Does @new_child have a listener while an ancestor also has a listener? * If so, we'll want to reject this filter. * This only has to be tested for the current process, even in the TSYNC case, * because TSYNC installs @child with the same parent on all threads. * Note that @new_child is not hooked up to its parent at this point yet, so * we use current->seccomp.filter. */ static bool has_duplicate_listener(struct seccomp_filter *new_child) { struct seccomp_filter *cur; /* must be protected against concurrent TSYNC */ lockdep_assert_held(¤t->sighand->siglock); if (!new_child->notif) return false; for (cur = current->seccomp.filter; cur; cur = cur->prev) { if (cur->notif) return true; } return false; } /** * seccomp_set_mode_filter: internal function for setting seccomp filter * @flags: flags to change filter behavior * @filter: struct sock_fprog containing filter * * This function may be called repeatedly to install additional filters. * Every filter successfully installed will be evaluated (in reverse order) * for each system call the task makes. * * Once current->seccomp.mode is non-zero, it may not be changed. * * Returns 0 on success or -EINVAL on failure. */ static long seccomp_set_mode_filter(unsigned int flags, const char __user *filter) { const unsigned long seccomp_mode = SECCOMP_MODE_FILTER; struct seccomp_filter *prepared = NULL; long ret = -EINVAL; int listener = -1; struct file *listener_f = NULL; /* Validate flags. */ if (flags & ~SECCOMP_FILTER_FLAG_MASK) return -EINVAL; /* * In the successful case, NEW_LISTENER returns the new listener fd. * But in the failure case, TSYNC returns the thread that died. If you * combine these two flags, there's no way to tell whether something * succeeded or failed. So, let's disallow this combination if the user * has not explicitly requested no errors from TSYNC. */ if ((flags & SECCOMP_FILTER_FLAG_TSYNC) && (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) && ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0)) return -EINVAL; /* * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag. */ if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) && ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0)) return -EINVAL; /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) return PTR_ERR(prepared); if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { listener = get_unused_fd_flags(O_CLOEXEC); if (listener < 0) { ret = listener; goto out_free; } listener_f = init_listener(prepared); if (IS_ERR(listener_f)) { put_unused_fd(listener); ret = PTR_ERR(listener_f); goto out_free; } } /* * Make sure we cannot change seccomp or nnp state via TSYNC * while another thread is in the middle of calling exec. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC && mutex_lock_killable(¤t->signal->cred_guard_mutex)) goto out_put_fd; spin_lock_irq(¤t->sighand->siglock); if (!seccomp_may_assign_mode(seccomp_mode)) goto out; if (has_duplicate_listener(prepared)) { ret = -EBUSY; goto out; } ret = seccomp_attach_filter(flags, prepared); if (ret) goto out; /* Do not free the successfully attached filter. */ prepared = NULL; seccomp_assign_mode(current, seccomp_mode, flags); out: spin_unlock_irq(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) mutex_unlock(¤t->signal->cred_guard_mutex); out_put_fd: if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { if (ret) { listener_f->private_data = NULL; fput(listener_f); put_unused_fd(listener); seccomp_notify_detach(prepared); } else { fd_install(listener, listener_f); ret = listener; } } out_free: seccomp_filter_free(prepared); return ret; } #else static inline long seccomp_set_mode_filter(unsigned int flags, const char __user *filter) { return -EINVAL; } #endif static long seccomp_get_action_avail(const char __user *uaction) { u32 action; if (copy_from_user(&action, uaction, sizeof(action))) return -EFAULT; switch (action) { case SECCOMP_RET_KILL_PROCESS: case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: case SECCOMP_RET_USER_NOTIF: case SECCOMP_RET_TRACE: case SECCOMP_RET_LOG: case SECCOMP_RET_ALLOW: break; default: return -EOPNOTSUPP; } return 0; } static long seccomp_get_notif_sizes(void __user *usizes) { struct seccomp_notif_sizes sizes = { .seccomp_notif = sizeof(struct seccomp_notif), .seccomp_notif_resp = sizeof(struct seccomp_notif_resp), .seccomp_data = sizeof(struct seccomp_data), }; if (copy_to_user(usizes, &sizes, sizeof(sizes))) return -EFAULT; return 0; } /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, void __user *uargs) { switch (op) { case SECCOMP_SET_MODE_STRICT: if (flags != 0 || uargs != NULL) return -EINVAL; return seccomp_set_mode_strict(); case SECCOMP_SET_MODE_FILTER: return seccomp_set_mode_filter(flags, uargs); case SECCOMP_GET_ACTION_AVAIL: if (flags != 0) return -EINVAL; return seccomp_get_action_avail(uargs); case SECCOMP_GET_NOTIF_SIZES: if (flags != 0) return -EINVAL; return seccomp_get_notif_sizes(uargs); default: return -EINVAL; } } SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags, void __user *, uargs) { return do_seccomp(op, flags, uargs); } /** * prctl_set_seccomp: configures current->seccomp.mode * @seccomp_mode: requested mode to use * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER * * Returns 0 on success or -EINVAL on failure. */ long prctl_set_seccomp(unsigned long seccomp_mode, void __user *filter) { unsigned int op; void __user *uargs; switch (seccomp_mode) { case SECCOMP_MODE_STRICT: op = SECCOMP_SET_MODE_STRICT; /* * Setting strict mode through prctl always ignored filter, * so make sure it is always NULL here to pass the internal * check in do_seccomp(). */ uargs = NULL; break; case SECCOMP_MODE_FILTER: op = SECCOMP_SET_MODE_FILTER; uargs = filter; break; default: return -EINVAL; } /* prctl interface doesn't have flags, so they are always zero. */ return do_seccomp(op, 0, uargs); } #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) static struct seccomp_filter *get_nth_filter(struct task_struct *task, unsigned long filter_off) { struct seccomp_filter *orig, *filter; unsigned long count; /* * Note: this is only correct because the caller should be the (ptrace) * tracer of the task, otherwise lock_task_sighand is needed. */ spin_lock_irq(&task->sighand->siglock); if (task->seccomp.mode != SECCOMP_MODE_FILTER) { spin_unlock_irq(&task->sighand->siglock); return ERR_PTR(-EINVAL); } orig = task->seccomp.filter; __get_seccomp_filter(orig); spin_unlock_irq(&task->sighand->siglock); count = 0; for (filter = orig; filter; filter = filter->prev) count++; if (filter_off >= count) { filter = ERR_PTR(-ENOENT); goto out; } count -= filter_off; for (filter = orig; filter && count > 1; filter = filter->prev) count--; if (WARN_ON(count != 1 || !filter)) { filter = ERR_PTR(-ENOENT); goto out; } __get_seccomp_filter(filter); out: __put_seccomp_filter(orig); return filter; } long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, void __user *data) { struct seccomp_filter *filter; struct sock_fprog_kern *fprog; long ret; if (!capable(CAP_SYS_ADMIN) || current->seccomp.mode != SECCOMP_MODE_DISABLED) { return -EACCES; } filter = get_nth_filter(task, filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); fprog = filter->prog->orig_prog; if (!fprog) { /* This must be a new non-cBPF filter, since we save * every cBPF filter's orig_prog above when * CONFIG_CHECKPOINT_RESTORE is enabled. */ ret = -EMEDIUMTYPE; goto out; } ret = fprog->len; if (!data) goto out; if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; out: __put_seccomp_filter(filter); return ret; } long seccomp_get_metadata(struct task_struct *task, unsigned long size, void __user *data) { long ret; struct seccomp_filter *filter; struct seccomp_metadata kmd = {}; if (!capable(CAP_SYS_ADMIN) || current->seccomp.mode != SECCOMP_MODE_DISABLED) { return -EACCES; } size = min_t(unsigned long, size, sizeof(kmd)); if (size < sizeof(kmd.filter_off)) return -EINVAL; if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off))) return -EFAULT; filter = get_nth_filter(task, kmd.filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); if (filter->log) kmd.flags |= SECCOMP_FILTER_FLAG_LOG; ret = size; if (copy_to_user(data, &kmd, size)) ret = -EFAULT; __put_seccomp_filter(filter); return ret; } #endif #ifdef CONFIG_SYSCTL /* Human readable action names for friendly sysctl interaction */ #define SECCOMP_RET_KILL_PROCESS_NAME "kill_process" #define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" #define SECCOMP_RET_USER_NOTIF_NAME "user_notif" #define SECCOMP_RET_TRACE_NAME "trace" #define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_PROCESS_NAME " " SECCOMP_RET_KILL_THREAD_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " SECCOMP_RET_USER_NOTIF_NAME " " SECCOMP_RET_TRACE_NAME " " SECCOMP_RET_LOG_NAME " " SECCOMP_RET_ALLOW_NAME; struct seccomp_log_name { u32 log; const char *name; }; static const struct seccomp_log_name seccomp_log_names[] = { { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME }, { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, { SECCOMP_LOG_USER_NOTIF, SECCOMP_RET_USER_NOTIF_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, { } }; static bool seccomp_names_from_actions_logged(char *names, size_t size, u32 actions_logged, const char *sep) { const struct seccomp_log_name *cur; bool append_sep = false; for (cur = seccomp_log_names; cur->name && size; cur++) { ssize_t ret; if (!(actions_logged & cur->log)) continue; if (append_sep) { ret = strscpy(names, sep, size); if (ret < 0) return false; names += ret; size -= ret; } else append_sep = true; ret = strscpy(names, cur->name, size); if (ret < 0) return false; names += ret; size -= ret; } return true; } static bool seccomp_action_logged_from_name(u32 *action_logged, const char *name) { const struct seccomp_log_name *cur; for (cur = seccomp_log_names; cur->name; cur++) { if (!strcmp(cur->name, name)) { *action_logged = cur->log; return true; } } return false; } static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) { char *name; *actions_logged = 0; while ((name = strsep(&names, " ")) && *name) { u32 action_logged = 0; if (!seccomp_action_logged_from_name(&action_logged, name)) return false; *actions_logged |= action_logged; } return true; } static int read_actions_logged(const struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; memset(names, 0, sizeof(names)); if (!seccomp_names_from_actions_logged(names, sizeof(names), seccomp_actions_logged, " ")) return -EINVAL; table = *ro_table; table.data = names; table.maxlen = sizeof(names); return proc_dostring(&table, 0, buffer, lenp, ppos); } static int write_actions_logged(const struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos, u32 *actions_logged) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(names, 0, sizeof(names)); table = *ro_table; table.data = names; table.maxlen = sizeof(names); ret = proc_dostring(&table, 1, buffer, lenp, ppos); if (ret) return ret; if (!seccomp_actions_logged_from_names(actions_logged, table.data)) return -EINVAL; if (*actions_logged & SECCOMP_LOG_ALLOW) return -EINVAL; seccomp_actions_logged = *actions_logged; return 0; } static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged, int ret) { char names[sizeof(seccomp_actions_avail)]; char old_names[sizeof(seccomp_actions_avail)]; const char *new = names; const char *old = old_names; if (!audit_enabled) return; memset(names, 0, sizeof(names)); memset(old_names, 0, sizeof(old_names)); if (ret) new = "?"; else if (!actions_logged) new = "(none)"; else if (!seccomp_names_from_actions_logged(names, sizeof(names), actions_logged, ",")) new = "?"; if (!old_actions_logged) old = "(none)"; else if (!seccomp_names_from_actions_logged(old_names, sizeof(old_names), old_actions_logged, ",")) old = "?"; return audit_seccomp_actions_logged(new, old, !ret); } static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; if (write) { u32 actions_logged = 0; u32 old_actions_logged = seccomp_actions_logged; ret = write_actions_logged(ro_table, buffer, lenp, ppos, &actions_logged); audit_actions_logged(actions_logged, old_actions_logged, ret); } else ret = read_actions_logged(ro_table, buffer, lenp, ppos); return ret; } static struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", .data = (void *) &seccomp_actions_avail, .maxlen = sizeof(seccomp_actions_avail), .mode = 0444, .proc_handler = proc_dostring, }, { .procname = "actions_logged", .mode = 0644, .proc_handler = seccomp_actions_logged_handler, }, }; static int __init seccomp_sysctl_init(void) { register_sysctl_init("kernel/seccomp", seccomp_sysctl_table); return 0; } device_initcall(seccomp_sysctl_init) #endif /* CONFIG_SYSCTL */ #ifdef CONFIG_SECCOMP_CACHE_DEBUG /* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */ static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name, const void *bitmap, size_t bitmap_size) { int nr; for (nr = 0; nr < bitmap_size; nr++) { bool cached = test_bit(nr, bitmap); char *status = cached ? "ALLOW" : "FILTER"; seq_printf(m, "%s %d %s\n", name, nr, status); } } int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct seccomp_filter *f; unsigned long flags; /* * We don't want some sandboxed process to know what their seccomp * filters consist of. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; if (!lock_task_sighand(task, &flags)) return -ESRCH; f = READ_ONCE(task->seccomp.filter); if (!f) { unlock_task_sighand(task, &flags); return 0; } /* prevent filter from being freed while we are printing it */ __get_seccomp_filter(f); unlock_task_sighand(task, &flags); proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME, f->cache.allow_native, SECCOMP_ARCH_NATIVE_NR); #ifdef SECCOMP_ARCH_COMPAT proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME, f->cache.allow_compat, SECCOMP_ARCH_COMPAT_NR); #endif /* SECCOMP_ARCH_COMPAT */ __put_seccomp_filter(f); return 0; } #endif /* CONFIG_SECCOMP_CACHE_DEBUG */ |
| 1 1 1 1 4 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 1 49 3 50 9 49 8 50 5 4 3 2 2 2 2 2 2 2 2 2 2 2 49 5 4 4 3 2 1 1 1 1 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; * Correct all the locking - David S. Miller <davem@redhat.com>; * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/uaccess.h> #include <linux/if_vlan.h> #include "vlan.h" #include "vlanproc.h" #define DRV_VERSION "1.8" /* Global VLAN variables */ unsigned int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; /* End of global variables definitions. */ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; unsigned int vidx; unsigned int size; int pidx; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return -EINVAL; vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; array = kzalloc(size, GFP_KERNEL_ACCOUNT); if (array == NULL) return -ENOBUFS; /* paired with smp_rmb() in __vlan_group_get_device() */ smp_wmb(); vg->vlan_devices_arrays[pidx][vidx] = array; return 0; } static void vlan_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev, struct vlan_dev_priv *vlan) { if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_stacked_transfer_operstate(rootdev, dev); } void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct vlan_info *vlan_info; struct vlan_group *grp; u16 vlan_id = vlan->vlan_id; ASSERT_RTNL(); vlan_info = rtnl_dereference(real_dev->vlan_info); BUG_ON(!vlan_info); grp = &vlan_info->grp; grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); } int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; } if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) { NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists"); return -EEXIST; } return 0; } int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; u16 vlan_id = vlan->vlan_id; struct vlan_info *vlan_info; struct vlan_group *grp; int err; err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id); if (err) return err; vlan_info = rtnl_dereference(real_dev->vlan_info); /* vlan_info should be there now. vlan_vid_add took care of it */ BUG_ON(!vlan_info); grp = &vlan_info->grp; if (grp->nr_vlan_devs == 0) { err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; err = vlan_mvrp_init_applicant(real_dev); if (err < 0) goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id); if (err < 0) goto out_uninit_mvrp; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place * it into our local structure. */ vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; return 0; out_unregister_netdev: unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); return err; } /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id, NULL); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; vlan = vlan_dev_priv(new_dev); vlan->vlan_proto = htons(ETH_P_8021Q); vlan->vlan_id = vlan_id; vlan->real_dev = real_dev; vlan->dent = NULL; vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: free_netdev(new_dev); return err; } static void vlan_sync_address(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan continues to inherit address of lower device */ if (vlan_dev_inherit_address(vlandev, dev)) goto out; /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); netif_inherit_tso_max(vlandev, dev); if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; #if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE; vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev); netdev_update_features(vlandev); } static int __vlan_device_event(struct net_device *dev, unsigned long event) { int err = 0; switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; struct net_device *vlandev; struct vlan_dev_priv *vlan; bool last = false; LIST_HEAD(list); int err; if (is_vlan_dev(dev)) { int err = __vlan_device_event(dev, event); if (err) return notifier_from_errno(err); } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } if (event == NETDEV_DOWN && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) goto out; grp = &vlan_info->grp; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); break; case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan_sync_address(dev, vlandev); } break; case NETDEV_CHANGEMTU: vlan_group_for_each_dev(grp, i, vlandev) { if (vlandev->mtu <= dev->mtu) continue; dev_set_mtu(vlandev, dev->mtu); } break; case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ vlan_group_for_each_dev(grp, i, vlandev) vlan_transfer_features(dev, vlandev); break; case NETDEV_DOWN: { struct net_device *tmp; LIST_HEAD(close_list); /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) list_add(&vlandev->close_list, &close_list); } dev_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); list_del_init(&vlandev->close_list); } list_del(&close_list); break; } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP, extack); vlan_stacked_transfer_operstate(dev, vlandev, vlan); } break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; vlan_group_for_each_dev(grp, i, vlandev) { /* removal of last vid destroys vlan_info, abort * afterwards */ if (vlan_info->nr_vids == 1) last = true; unregister_vlan_dev(vlandev, &list); if (last) break; } unregister_netdevice_many(&list); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ if (vlan_uses_dev(dev)) return NOTIFY_BAD; break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); break; case NETDEV_CVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021Q)); if (err) return notifier_from_errno(err); break; case NETDEV_CVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021Q)); break; case NETDEV_SVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021AD)); if (err) return notifier_from_errno(err); break; case NETDEV_SVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021AD)); break; } out: return NOTIFY_DONE; } static struct notifier_block vlan_notifier_block __read_mostly = { .notifier_call = vlan_device_event, }; /* * VLAN IOCTL handler. * o execute requested action or pass command to the device driver * arg is really a struct vlan_ioctl_args __user *. */ static int vlan_ioctl_handler(struct net *net, void __user *arg) { int err; struct vlan_ioctl_args args; struct net_device *dev = NULL; if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) return -EFAULT; /* Null terminate this sucker, just in case. */ args.device1[sizeof(args.device1) - 1] = 0; args.u.device2[sizeof(args.u.device2) - 1] = 0; rtnl_lock(); switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: case SET_VLAN_EGRESS_PRIORITY_CMD: case SET_VLAN_FLAG_CMD: case ADD_VLAN_CMD: case DEL_VLAN_CMD: case GET_VLAN_REALDEV_NAME_CMD: case GET_VLAN_VID_CMD: err = -ENODEV; dev = __dev_get_by_name(net, args.device1); if (!dev) goto out; err = -EINVAL; if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev)) goto out; } switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, args.vlan_qos); break; case SET_VLAN_FLAG_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (args.u.name_type < VLAN_NAME_TYPE_HIGHEST) { struct vlan_net *vn; vn = net_generic(net, vlan_net_id); vn->name_type = args.u.name_type; err = 0; } else { err = -EINVAL; } break; case ADD_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; break; case GET_VLAN_REALDEV_NAME_CMD: err = 0; vlan_dev_get_realdev_name(dev, args.u.device2, sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; case GET_VLAN_VID_CMD: err = 0; args.u.VID = vlan_dev_vlan_id(dev); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; default: err = -EOPNOTSUPP; break; } out: rtnl_unlock(); return err; } static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); return err; } static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) { int err; pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; err = register_netdevice_notifier(&vlan_notifier_block); if (err < 0) goto err2; err = vlan_gvrp_init(); if (err < 0) goto err3; err = vlan_mvrp_init(); if (err < 0) goto err4; err = vlan_netlink_init(); if (err < 0) goto err5; vlan_ioctl_set(vlan_ioctl_handler); return 0; err5: vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: unregister_pernet_subsys(&vlan_net_ops); err0: return err; } static void __exit vlan_cleanup_module(void) { vlan_ioctl_set(NULL); vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_mvrp_uninit(); vlan_gvrp_uninit(); } module_init(vlan_proto_init); module_exit(vlan_cleanup_module); MODULE_DESCRIPTION("802.1Q/802.1ad VLAN Protocol"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); |
| 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 | /* * Copyright (c) 2006, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/errqueue.h> #include "rds.h" static unsigned int rds_exthdr_size[__RDS_EXTHDR_MAX] = { [RDS_EXTHDR_NONE] = 0, [RDS_EXTHDR_VERSION] = sizeof(struct rds_ext_header_version), [RDS_EXTHDR_RDMA] = sizeof(struct rds_ext_header_rdma), [RDS_EXTHDR_RDMA_DEST] = sizeof(struct rds_ext_header_rdma_dest), [RDS_EXTHDR_NPATHS] = sizeof(u16), [RDS_EXTHDR_GEN_NUM] = sizeof(u32), }; void rds_message_addref(struct rds_message *rm) { rdsdebug("addref rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); refcount_inc(&rm->m_refcount); } EXPORT_SYMBOL_GPL(rds_message_addref); static inline bool rds_zcookie_add(struct rds_msg_zcopy_info *info, u32 cookie) { struct rds_zcopy_cookies *ck = &info->zcookies; int ncookies = ck->num; if (ncookies == RDS_MAX_ZCOOKIES) return false; ck->cookies[ncookies] = cookie; ck->num = ++ncookies; return true; } static struct rds_msg_zcopy_info *rds_info_from_znotifier(struct rds_znotifier *znotif) { return container_of(znotif, struct rds_msg_zcopy_info, znotif); } void rds_notify_msg_zcopy_purge(struct rds_msg_zcopy_queue *q) { unsigned long flags; LIST_HEAD(copy); struct rds_msg_zcopy_info *info, *tmp; spin_lock_irqsave(&q->lock, flags); list_splice(&q->zcookie_head, ©); INIT_LIST_HEAD(&q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); list_for_each_entry_safe(info, tmp, ©, rs_zcookie_next) { list_del(&info->rs_zcookie_next); kfree(info); } } static void rds_rm_zerocopy_callback(struct rds_sock *rs, struct rds_znotifier *znotif) { struct rds_msg_zcopy_info *info; struct rds_msg_zcopy_queue *q; u32 cookie = znotif->z_cookie; struct rds_zcopy_cookies *ck; struct list_head *head; unsigned long flags; mm_unaccount_pinned_pages(&znotif->z_mmp); q = &rs->rs_zcookie_queue; spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { info = list_first_entry(head, struct rds_msg_zcopy_info, rs_zcookie_next); if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ return; } } info = rds_info_from_znotifier(znotif); ck = &info->zcookies; memset(ck, 0, sizeof(*ck)); WARN_ON(!rds_zcookie_add(info, cookie)); list_add_tail(&info->rs_zcookie_next, &q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); /* caller invokes rds_wake_sk_sleep() */ } /* * This relies on dma_map_sg() not touching sg[].page during merging. */ static void rds_message_purge(struct rds_message *rm) { unsigned long i, flags; bool zcopy = false; if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags))) return; spin_lock_irqsave(&rm->m_rs_lock, flags); if (rm->m_rs) { struct rds_sock *rs = rm->m_rs; if (rm->data.op_mmp_znotifier) { zcopy = true; rds_rm_zerocopy_callback(rs, rm->data.op_mmp_znotifier); rds_wake_sk_sleep(rs); rm->data.op_mmp_znotifier = NULL; } sock_put(rds_rs_to_sk(rs)); rm->m_rs = NULL; } spin_unlock_irqrestore(&rm->m_rs_lock, flags); for (i = 0; i < rm->data.op_nents; i++) { /* XXX will have to put_page for page refs */ if (!zcopy) __free_page(sg_page(&rm->data.op_sg[i])); else put_page(sg_page(&rm->data.op_sg[i])); } rm->data.op_nents = 0; if (rm->rdma.op_active) rds_rdma_free_op(&rm->rdma); if (rm->rdma.op_rdma_mr) kref_put(&rm->rdma.op_rdma_mr->r_kref, __rds_put_mr_final); if (rm->atomic.op_active) rds_atomic_free_op(&rm->atomic); if (rm->atomic.op_rdma_mr) kref_put(&rm->atomic.op_rdma_mr->r_kref, __rds_put_mr_final); } void rds_message_put(struct rds_message *rm) { rdsdebug("put rm %p ref %d\n", rm, refcount_read(&rm->m_refcount)); WARN(!refcount_read(&rm->m_refcount), "danger refcount zero on %p\n", rm); if (refcount_dec_and_test(&rm->m_refcount)) { BUG_ON(!list_empty(&rm->m_sock_item)); BUG_ON(!list_empty(&rm->m_conn_item)); rds_message_purge(rm); kfree(rm); } } EXPORT_SYMBOL_GPL(rds_message_put); void rds_message_populate_header(struct rds_header *hdr, __be16 sport, __be16 dport, u64 seq) { hdr->h_flags = 0; hdr->h_sport = sport; hdr->h_dport = dport; hdr->h_sequence = cpu_to_be64(seq); hdr->h_exthdr[0] = RDS_EXTHDR_NONE; } EXPORT_SYMBOL_GPL(rds_message_populate_header); int rds_message_add_extension(struct rds_header *hdr, unsigned int type, const void *data, unsigned int len) { unsigned int ext_len = sizeof(u8) + len; unsigned char *dst; /* For now, refuse to add more than one extension header */ if (hdr->h_exthdr[0] != RDS_EXTHDR_NONE) return 0; if (type >= __RDS_EXTHDR_MAX || len != rds_exthdr_size[type]) return 0; if (ext_len >= RDS_HEADER_EXT_SPACE) return 0; dst = hdr->h_exthdr; *dst++ = type; memcpy(dst, data, len); dst[len] = RDS_EXTHDR_NONE; return 1; } EXPORT_SYMBOL_GPL(rds_message_add_extension); /* * If a message has extension headers, retrieve them here. * Call like this: * * unsigned int pos = 0; * * while (1) { * buflen = sizeof(buffer); * type = rds_message_next_extension(hdr, &pos, buffer, &buflen); * if (type == RDS_EXTHDR_NONE) * break; * ... * } */ int rds_message_next_extension(struct rds_header *hdr, unsigned int *pos, void *buf, unsigned int *buflen) { unsigned int offset, ext_type, ext_len; u8 *src = hdr->h_exthdr; offset = *pos; if (offset >= RDS_HEADER_EXT_SPACE) goto none; /* Get the extension type and length. For now, the * length is implied by the extension type. */ ext_type = src[offset++]; if (ext_type == RDS_EXTHDR_NONE || ext_type >= __RDS_EXTHDR_MAX) goto none; ext_len = rds_exthdr_size[ext_type]; if (offset + ext_len > RDS_HEADER_EXT_SPACE) goto none; *pos = offset + ext_len; if (ext_len < *buflen) *buflen = ext_len; memcpy(buf, src + offset, *buflen); return ext_type; none: *pos = RDS_HEADER_EXT_SPACE; *buflen = 0; return RDS_EXTHDR_NONE; } int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset) { struct rds_ext_header_rdma_dest ext_hdr; ext_hdr.h_rdma_rkey = cpu_to_be32(r_key); ext_hdr.h_rdma_offset = cpu_to_be32(offset); return rds_message_add_extension(hdr, RDS_EXTHDR_RDMA_DEST, &ext_hdr, sizeof(ext_hdr)); } EXPORT_SYMBOL_GPL(rds_message_add_rdma_dest_extension); /* * Each rds_message is allocated with extra space for the scatterlist entries * rds ops will need. This is to minimize memory allocation count. Then, each rds op * can grab SGs when initializing its part of the rds_message. */ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) { struct rds_message *rm; if (extra_len > KMALLOC_MAX_SIZE - sizeof(struct rds_message)) return NULL; rm = kzalloc(sizeof(struct rds_message) + extra_len, gfp); if (!rm) goto out; rm->m_used_sgs = 0; rm->m_total_sgs = extra_len / sizeof(struct scatterlist); refcount_set(&rm->m_refcount, 1); INIT_LIST_HEAD(&rm->m_sock_item); INIT_LIST_HEAD(&rm->m_conn_item); spin_lock_init(&rm->m_rs_lock); init_waitqueue_head(&rm->m_flush_wait); out: return rm; } /* * RDS ops use this to grab SG entries from the rm's sg pool. */ struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; sg_init_table(sg_ret, nents); rm->m_used_sgs += nents; return sg_ret; } struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len) { struct rds_message *rm; unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) return ERR_PTR(-ENOMEM); set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (IS_ERR(rm->data.op_sg)) { void *err = ERR_CAST(rm->data.op_sg); rds_message_put(rm); return err; } for (i = 0; i < rm->data.op_nents; ++i) { sg_set_page(&rm->data.op_sg[i], virt_to_page((void *)page_addrs[i]), PAGE_SIZE, 0); } return rm; } static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *from) { struct scatterlist *sg; int ret = 0; int length = iov_iter_count(from); struct rds_msg_zcopy_info *info; rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); /* * now allocate and copy in the data payload. */ sg = rm->data.op_sg; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; INIT_LIST_HEAD(&info->rs_zcookie_next); rm->data.op_mmp_znotifier = &info->znotif; if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp, length)) { ret = -ENOMEM; goto err; } while (iov_iter_count(from)) { struct page *pages; size_t start; ssize_t copied; copied = iov_iter_get_pages2(from, &pages, PAGE_SIZE, 1, &start); if (copied < 0) { struct mmpin *mmp; int i; for (i = 0; i < rm->data.op_nents; i++) put_page(sg_page(&rm->data.op_sg[i])); mmp = &rm->data.op_mmp_znotifier->z_mmp; mm_unaccount_pinned_pages(mmp); ret = -EFAULT; goto err; } length -= copied; sg_set_page(sg, pages, copied, start); rm->data.op_nents++; sg++; } WARN_ON_ONCE(length != 0); return ret; err: kfree(info); rm->data.op_mmp_znotifier = NULL; return ret; } int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy) { unsigned long to_copy, nbytes; unsigned long sg_off; struct scatterlist *sg; int ret = 0; rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); /* now allocate and copy in the data payload. */ sg = rm->data.op_sg; sg_off = 0; /* Dear gcc, sg->page will be null from kzalloc. */ if (zcopy) return rds_message_zcopy_from_user(rm, from); while (iov_iter_count(from)) { if (!sg_page(sg)) { ret = rds_page_remainder_alloc(sg, iov_iter_count(from), GFP_HIGHUSER); if (ret) return ret; rm->data.op_nents++; sg_off = 0; } to_copy = min_t(unsigned long, iov_iter_count(from), sg->length - sg_off); rds_stats_add(s_copy_from_user, to_copy); nbytes = copy_page_from_iter(sg_page(sg), sg->offset + sg_off, to_copy, from); if (nbytes != to_copy) return -EFAULT; sg_off += to_copy; if (sg_off == sg->length) sg++; } return ret; } int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to) { struct rds_message *rm; struct scatterlist *sg; unsigned long to_copy; unsigned long vec_off; int copied; int ret; u32 len; rm = container_of(inc, struct rds_message, m_inc); len = be32_to_cpu(rm->m_inc.i_hdr.h_len); sg = rm->data.op_sg; vec_off = 0; copied = 0; while (iov_iter_count(to) && copied < len) { to_copy = min_t(unsigned long, iov_iter_count(to), sg->length - vec_off); to_copy = min_t(unsigned long, to_copy, len - copied); rds_stats_add(s_copy_to_user, to_copy); ret = copy_page_to_iter(sg_page(sg), sg->offset + vec_off, to_copy, to); if (ret != to_copy) return -EFAULT; vec_off += to_copy; copied += to_copy; if (vec_off == sg->length) { vec_off = 0; sg++; } } return copied; } /* * If the message is still on the send queue, wait until the transport * is done with it. This is particularly important for RDMA operations. */ void rds_message_wait(struct rds_message *rm) { wait_event_interruptible(rm->m_flush_wait, !test_bit(RDS_MSG_MAPPED, &rm->m_flags)); } void rds_message_unmapped(struct rds_message *rm) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); } EXPORT_SYMBOL_GPL(rds_message_unmapped); |
| 20 22 20 18 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GUE_H #define __NET_GUE_H /* Definitions for the GUE header, standard and private flags, lengths * of optional fields are below. * * Diagram of GUE header: * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |Ver|C| Hlen | Proto/ctype | Standard flags |P| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * ~ Fields (optional) ~ * | | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Private flags (optional, P bit is set) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * ~ Private fields (optional) ~ * | | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * C bit indicates control message when set, data message when unset. * For a control message, proto/ctype is interpreted as a type of * control message. For data messages, proto/ctype is the IP protocol * of the next header. * * P bit indicates private flags field is present. The private flags * may refer to options placed after this field. */ #include <asm/byteorder.h> #include <linux/types.h> struct guehdr { union { struct { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 hlen:5, control:1, version:2; #elif defined (__BIG_ENDIAN_BITFIELD) __u8 version:2, control:1, hlen:5; #else #error "Please fix <asm/byteorder.h>" #endif __u8 proto_ctype; __be16 flags; }; __be32 word; }; }; /* Standard flags in GUE header */ #define GUE_FLAG_PRIV htons(1<<0) /* Private flags are in options */ #define GUE_LEN_PRIV 4 #define GUE_FLAGS_ALL (GUE_FLAG_PRIV) /* Private flags in the private option extension */ #define GUE_PFLAG_REMCSUM htonl(1U << 31) #define GUE_PLEN_REMCSUM 4 #define GUE_PFLAGS_ALL (GUE_PFLAG_REMCSUM) /* Functions to compute options length corresponding to flags. * If we ever have a lot of flags this can be potentially be * converted to a more optimized algorithm (table lookup * for instance). */ static inline size_t guehdr_flags_len(__be16 flags) { return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0); } static inline size_t guehdr_priv_flags_len(__be32 flags) { return 0; } /* Validate standard and private flags. Returns non-zero (meaning invalid) * if there is an unknown standard or private flags, or the options length for * the flags exceeds the options length specific in hlen of the GUE header. */ static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen) { __be16 flags = guehdr->flags; size_t len; if (flags & ~GUE_FLAGS_ALL) return 1; len = guehdr_flags_len(flags); if (len > optlen) return 1; if (flags & GUE_FLAG_PRIV) { /* Private flags are last four bytes accounted in * guehdr_flags_len */ __be32 pflags = *(__be32 *)((void *)&guehdr[1] + len - GUE_LEN_PRIV); if (pflags & ~GUE_PFLAGS_ALL) return 1; len += guehdr_priv_flags_len(pflags); if (len > optlen) return 1; } return 0; } #endif |
| 5 5 6 6 7 7 7 2 2 2 2 2 2 2 2 1 1 1 1 6 6 6 5 6 6 3 4 4 3 6 6 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 3 3 3 3 3 3 3 3 3 2 3 3 8 6 8 8 8 8 8 8 6 8 8 8 8 8 8 8 8 6 6 6 6 6 6 6 6 1 1 11 3 3 19 18 18 17 1 16 1 19 15 15 15 15 15 15 14 6 10 3 3 11 1 8 8 10 10 5 3 6 7 1 7 10 3 11 9 9 3 2 3 15 15 15 10 15 5 5 5 5 5 5 2 5 4 4 5 5 5 4 5 5 5 5 5 4 3 3 5 5 5 5 5 4 5 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 7 5 5 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * "splice": joining two ropes together by interweaving their strands. * * This is the "extended pipe" functionality, where a pipe is used as * an arbitrary in-memory buffer. Think of a pipe as a small kernel * buffer that you can use to transfer data from one end to the other. * * The traditional unix read/write is extended with a "splice()" operation * that transfers data buffers to or from a pipe buffer. * * Named by Larry McVoy, original implementation from Linus, extended by * Jens to support splicing to files, network, direct splicing, etc and * fixing lots of bugs. * * Copyright (C) 2005-2006 Jens Axboe <axboe@kernel.dk> * Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org> * Copyright (C) 2006 Ingo Molnar <mingo@elte.hu> * */ #include <linux/bvec.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/gfp.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/sched/signal.h> #include "internal.h" /* * Splice doesn't support FMODE_NOWAIT. Since pipes may set this flag to * indicate they support non-blocking reads or writes, we must clear it * here if set to avoid blocking other users of this pipe if splice is * being done on it. */ static noinline void noinline pipe_clear_nowait(struct file *file) { fmode_t fmode = READ_ONCE(file->f_mode); do { if (!(fmode & FMODE_NOWAIT)) break; } while (!try_cmpxchg(&file->f_mode, &fmode, fmode & ~FMODE_NOWAIT)); } /* * Attempt to steal a page from a pipe buffer. This should perhaps go into * a vm helper function, it's already simplified quite a bit by the * addition of remove_mapping(). If success is returned, the caller may * attempt to reuse this page for another destination. */ static bool page_cache_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct folio *folio = page_folio(buf->page); struct address_space *mapping; folio_lock(folio); mapping = folio_mapping(folio); if (mapping) { WARN_ON(!folio_test_uptodate(folio)); /* * At least for ext2 with nobh option, we need to wait on * writeback completing on this folio, since we'll remove it * from the pagecache. Otherwise truncate wont wait on the * folio, allowing the disk blocks to be reused by someone else * before we actually wrote our data to them. fs corruption * ensues. */ folio_wait_writeback(folio); if (!filemap_release_folio(folio, GFP_KERNEL)) goto out_unlock; /* * If we succeeded in removing the mapping, set LRU flag * and return good. */ if (remove_mapping(mapping, folio)) { buf->flags |= PIPE_BUF_FLAG_LRU; return true; } } /* * Raced with truncate or failed to remove folio from current * address space, unlock and return failure. */ out_unlock: folio_unlock(folio); return false; } static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); buf->flags &= ~PIPE_BUF_FLAG_LRU; } /* * Check whether the contents of buf is OK to access. Since the content * is a page cache page, IO may be in flight. */ static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct folio *folio = page_folio(buf->page); int err; if (!folio_test_uptodate(folio)) { folio_lock(folio); /* * Folio got truncated/unhashed. This will cause a 0-byte * splice, if this is the first page. */ if (!folio->mapping) { err = -ENODATA; goto error; } /* * Uh oh, read-error from disk. */ if (!folio_test_uptodate(folio)) { err = -EIO; goto error; } /* Folio is ok after all, we are done */ folio_unlock(folio); } return 0; error: folio_unlock(folio); return err; } const struct pipe_buf_operations page_cache_pipe_buf_ops = { .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .try_steal = page_cache_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; static bool user_page_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!(buf->flags & PIPE_BUF_FLAG_GIFT)) return false; buf->flags |= PIPE_BUF_FLAG_LRU; return generic_pipe_buf_try_steal(pipe, buf); } static const struct pipe_buf_operations user_page_pipe_buf_ops = { .release = page_cache_pipe_buf_release, .try_steal = user_page_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; static void wakeup_pipe_readers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->rd_wait)) wake_up_interruptible(&pipe->rd_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } /** * splice_to_pipe - fill passed data into a pipe * @pipe: pipe to fill * @spd: data to fill * * Description: * @spd contains a map of pages and len/offset tuples, along with * the struct pipe_buf_operations associated with these pages. This * function will link that data to the pipe. * */ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int spd_pages = spd->nr_pages; unsigned int tail = pipe->tail; unsigned int head = pipe->head; unsigned int mask = pipe->ring_size - 1; ssize_t ret = 0; int page_nr = 0; if (!spd_pages) return 0; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } while (!pipe_full(head, tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[head & mask]; buf->page = spd->pages[page_nr]; buf->offset = spd->partial[page_nr].offset; buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; buf->flags = 0; head++; pipe->head = head; page_nr++; ret += buf->len; if (!--spd->nr_pages) break; } if (!ret) ret = -EAGAIN; out: while (page_nr < spd_pages) spd->spd_release(spd, page_nr++); return ret; } EXPORT_SYMBOL_GPL(splice_to_pipe); ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; } else if (pipe_full(head, tail, pipe->max_usage)) { ret = -EAGAIN; } else { pipe->bufs[head & mask] = *buf; pipe->head = head + 1; return buf->len; } pipe_buf_release(pipe, buf); return ret; } EXPORT_SYMBOL(add_to_pipe); /* * Check if we need to grow the arrays holding pages and partial page * descriptions. */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int max_usage = READ_ONCE(pipe->max_usage); spd->nr_pages_max = max_usage; if (max_usage <= PIPE_DEF_BUFFERS) return 0; spd->pages = kmalloc_array(max_usage, sizeof(struct page *), GFP_KERNEL); spd->partial = kmalloc_array(max_usage, sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; kfree(spd->pages); kfree(spd->partial); return -ENOMEM; } void splice_shrink_spd(struct splice_pipe_desc *spd) { if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); kfree(spd->partial); } /** * copy_splice_read - Copy data from a file and splice the copy into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function allocates a bunch of pages sufficient to hold the requested * amount of data (but limited by the remaining pipe capacity), passes it to * the file's ->read_iter() to read into and then splices the used pages into * the pipe. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct iov_iter to; struct bio_vec *bv; struct kiocb kiocb; struct page **pages; ssize_t ret; size_t used, npages, chunk, remain, keep = 0; int i; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); npages = DIV_ROUND_UP(len, PAGE_SIZE); bv = kzalloc(array_size(npages, sizeof(bv[0])) + array_size(npages, sizeof(struct page *)), GFP_KERNEL); if (!bv) return -ENOMEM; pages = (struct page **)(bv + npages); npages = alloc_pages_bulk_array(GFP_USER, npages, pages); if (!npages) { kfree(bv); return -ENOMEM; } remain = len = min_t(size_t, len, npages * PAGE_SIZE); for (i = 0; i < npages; i++) { chunk = min_t(size_t, PAGE_SIZE, remain); bv[i].bv_page = pages[i]; bv[i].bv_offset = 0; bv[i].bv_len = chunk; remain -= chunk; } /* Do the I/O */ iov_iter_bvec(&to, ITER_DEST, bv, npages, len); init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; ret = in->f_op->read_iter(&kiocb, &to); if (ret > 0) { keep = DIV_ROUND_UP(ret, PAGE_SIZE); *ppos = kiocb.ki_pos; } /* * Callers of ->splice_read() expect -EAGAIN on "can't put anything in * there", rather than -EFAULT. */ if (ret == -EFAULT) ret = -EAGAIN; /* Free any pages that didn't get touched at all. */ if (keep < npages) release_pages(pages + keep, npages - keep); /* Push the remaining pages into the pipe. */ remain = ret; for (i = 0; i < keep; i++) { struct pipe_buffer *buf = pipe_head_buf(pipe); chunk = min_t(size_t, remain, PAGE_SIZE); *buf = (struct pipe_buffer) { .ops = &default_pipe_buf_ops, .page = bv[i].bv_page, .offset = 0, .len = chunk, }; pipe->head++; remain -= chunk; } kfree(bv); return ret; } EXPORT_SYMBOL(copy_splice_read); const struct pipe_buf_operations default_pipe_buf_ops = { .release = generic_pipe_buf_release, .try_steal = generic_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Pipe buffer operations for a socket and similar. */ const struct pipe_buf_operations nosteal_pipe_buf_ops = { .release = generic_pipe_buf_release, .get = generic_pipe_buf_get, }; EXPORT_SYMBOL(nosteal_pipe_buf_ops); static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->wr_wait)) wake_up_interruptible(&pipe->wr_wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } /** * splice_from_pipe_feed - feed available data from a pipe to a file * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function loops over the pipe and calls @actor to do the * actual moving of a single struct pipe_buffer to the desired * destination. It returns when there's no more buffers left in * the pipe or if the requested number of bytes (@sd->total_len) * have been copied. It returns a positive number (one) if the * pipe needs to be filled with more data, zero if the required * number of bytes have been copied and -errno on error. * * This, together with splice_from_pipe_{begin,end,next}, may be * used to implement the functionality of __splice_from_pipe() when * locking is required around copying the pipe buffers to the * destination. */ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; while (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; sd->len = buf->len; if (sd->len > sd->total_len) sd->len = sd->total_len; ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; return ret; } ret = actor(pipe, buf, sd); if (ret <= 0) return ret; buf->offset += ret; buf->len -= ret; sd->num_spliced += ret; sd->len -= ret; sd->pos += ret; sd->total_len -= ret; if (!buf->len) { pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd->need_wakeup = true; } if (!sd->total_len) return 0; } return 1; } /* We know we have a pipe buffer, but maybe it's empty? */ static inline bool eat_empty_buffer(struct pipe_inode_info *pipe) { unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (unlikely(!buf->len)) { pipe_buf_release(pipe, buf); pipe->tail = tail+1; return true; } return false; } /** * splice_from_pipe_next - wait for some data to splice from * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wait for some data and return a positive * value (one) if pipe buffers are available. It will return zero * or -errno if no more data needs to be spliced. */ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) { /* * Check for signal early to make process killable when there are * always buffers available */ if (signal_pending(current)) return -ERESTARTSYS; repeat: while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; if (sd->num_spliced) return 0; if (sd->flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; if (sd->need_wakeup) { wakeup_pipe_writers(pipe); sd->need_wakeup = false; } pipe_wait_readable(pipe); } if (eat_empty_buffer(pipe)) goto repeat; return 1; } /** * splice_from_pipe_begin - start splicing from pipe * @sd: information about the splice operation * * Description: * This function should be called before a loop containing * splice_from_pipe_next() and splice_from_pipe_feed() to * initialize the necessary fields of @sd. */ static void splice_from_pipe_begin(struct splice_desc *sd) { sd->num_spliced = 0; sd->need_wakeup = false; } /** * splice_from_pipe_end - finish splicing from pipe * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wake up pipe writers if necessary. It should * be called after a loop containing splice_from_pipe_next() and * splice_from_pipe_feed(). */ static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) { if (sd->need_wakeup) wakeup_pipe_writers(pipe); } /** * __splice_from_pipe - splice data from a pipe to given actor * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function does little more than loop over the pipe and call * @actor to do the actual moving of a single struct pipe_buffer to * the desired destination. See pipe_to_file, pipe_to_sendmsg, or * pipe_to_user. * */ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { int ret; splice_from_pipe_begin(sd); do { cond_resched(); ret = splice_from_pipe_next(pipe, sd); if (ret > 0) ret = splice_from_pipe_feed(pipe, sd, actor); } while (ret > 0); splice_from_pipe_end(pipe, sd); return sd->num_spliced ? sd->num_spliced : ret; } EXPORT_SYMBOL(__splice_from_pipe); /** * splice_from_pipe - splice data from a pipe to a file * @pipe: pipe to splice from * @out: file to splice to * @ppos: position in @out * @len: how many bytes to splice * @flags: splice modifier flags * @actor: handler that splices the data * * Description: * See __splice_from_pipe. This function locks the pipe inode, * otherwise it's identical to __splice_from_pipe(). * */ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, splice_actor *actor) { ssize_t ret; struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, actor); pipe_unlock(pipe); return ret; } /** * iter_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will either move or copy pages (determined by @flags options) from * the given pipe inode to the given file. * This one is ->write_iter-based. * */ ssize_t iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; int nbufs = pipe->max_usage; struct bio_vec *array; ssize_t ret; if (!out->f_op->write_iter) return -EINVAL; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (unlikely(!array)) return -ENOMEM; pipe_lock(pipe); splice_from_pipe_begin(&sd); while (sd.total_len) { struct kiocb kiocb; struct iov_iter from; unsigned int head, tail, mask; size_t left; int n; ret = splice_from_pipe_next(pipe, &sd); if (ret <= 0) break; if (unlikely(nbufs < pipe->max_usage)) { kfree(array); nbufs = pipe->max_usage; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (!array) { ret = -ENOMEM; break; } } head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; /* build the vector */ left = sd.total_len; for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t this_len = buf->len; /* zero-length bvecs are not supported, skip them */ if (!this_len) continue; this_len = min(this_len, left); ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; goto done; } bvec_set_page(&array[n], buf->page, this_len, buf->offset); left -= this_len; n++; } iov_iter_bvec(&from, ITER_SOURCE, array, n, sd.total_len - left); init_sync_kiocb(&kiocb, out); kiocb.ki_pos = sd.pos; ret = out->f_op->write_iter(&kiocb, &from); sd.pos = kiocb.ki_pos; if (ret <= 0) break; sd.num_spliced += ret; sd.total_len -= ret; *ppos = sd.pos; /* dismiss the fully eaten buffers, adjust the partial one */ tail = pipe->tail; while (ret) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (ret >= buf->len) { ret -= buf->len; buf->len = 0; pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd.need_wakeup = true; } else { buf->offset += ret; buf->len -= ret; ret = 0; } } } done: kfree(array); splice_from_pipe_end(pipe, &sd); pipe_unlock(pipe); if (sd.num_spliced) ret = sd.num_spliced; return ret; } EXPORT_SYMBOL(iter_file_splice_write); #ifdef CONFIG_NET /** * splice_to_socket - splice data from a pipe to a socket * @pipe: pipe to splice from * @out: socket to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will send @len bytes from the pipe to a network socket. No data copying * is involved. * */ ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct socket *sock = sock_from_file(out); struct bio_vec bvec[16]; struct msghdr msg = {}; ssize_t ret = 0; size_t spliced = 0; bool need_wakeup = false; pipe_lock(pipe); while (len > 0) { unsigned int head, tail, mask, bc = 0; size_t remain = len; /* * Check for signal early to make process killable when there * are always buffers available */ ret = -ERESTARTSYS; if (signal_pending(current)) break; while (pipe_empty(pipe->head, pipe->tail)) { ret = 0; if (!pipe->writers) goto out; if (spliced) goto out; ret = -EAGAIN; if (flags & SPLICE_F_NONBLOCK) goto out; ret = -ERESTARTSYS; if (signal_pending(current)) goto out; if (need_wakeup) { wakeup_pipe_writers(pipe); need_wakeup = false; } pipe_wait_readable(pipe); } head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t seg; if (!buf->len) { tail++; continue; } seg = min_t(size_t, remain, buf->len); ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; break; } bvec_set_page(&bvec[bc++], buf->page, seg, buf->offset); remain -= seg; if (remain == 0 || bc >= ARRAY_SIZE(bvec)) break; tail++; } if (!bc) break; msg.msg_flags = MSG_SPLICE_PAGES; if (flags & SPLICE_F_MORE) msg.msg_flags |= MSG_MORE; if (remain && pipe_occupancy(pipe->head, tail) > 0) msg.msg_flags |= MSG_MORE; if (out->f_flags & O_NONBLOCK) msg.msg_flags |= MSG_DONTWAIT; iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, bc, len - remain); ret = sock_sendmsg(sock, &msg); if (ret <= 0) break; spliced += ret; len -= ret; tail = pipe->tail; while (ret > 0) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t seg = min_t(size_t, ret, buf->len); buf->offset += seg; buf->len -= seg; ret -= seg; if (!buf->len) { pipe_buf_release(pipe, buf); tail++; } } if (tail != pipe->tail) { pipe->tail = tail; if (pipe->files) need_wakeup = true; } } out: pipe_unlock(pipe); if (need_wakeup) wakeup_pipe_writers(pipe); return spliced ?: ret; } #endif static int warn_unsupported(struct file *file, const char *op) { pr_debug_ratelimited( "splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } /* * Attempt to initiate a splice from pipe to file. */ static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { if (unlikely(!out->f_op->splice_write)) return warn_unsupported(out, "write"); return out->f_op->splice_write(pipe, out, ppos, len, flags); } /* * Indicate to the caller that there was a premature EOF when reading from the * source and the caller didn't indicate they would be sending more data after * this. */ static void do_splice_eof(struct splice_desc *sd) { if (sd->splice_eof) sd->splice_eof(sd); } /* * Callers already called rw_verify_area() on the entire range. * No need to call it for sub ranges. */ static ssize_t do_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { unsigned int p_space; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; if (!len) return 0; /* Don't try to read more the pipe has space for. */ p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); len = min_t(size_t, len, p_space << PAGE_SHIFT); if (unlikely(len > MAX_RW_COUNT)) len = MAX_RW_COUNT; if (unlikely(!in->f_op->splice_read)) return warn_unsupported(in, "read"); /* * O_DIRECT and DAX don't deal with the pagecache, so we allocate a * buffer, copy into it and splice that into the pipe. */ if ((in->f_flags & O_DIRECT) || IS_DAX(in->f_mapping->host)) return copy_splice_read(in, ppos, pipe, len, flags); return in->f_op->splice_read(in, ppos, pipe, len, flags); } /** * vfs_splice_read - Read data from a file and splice it into a pipe * @in: File to splice from * @ppos: Input file offset * @pipe: Pipe to splice to * @len: Number of bytes to splice * @flags: Splice modifier flags (SPLICE_F_*) * * Splice the requested amount of data from the input file to the pipe. This * is synchronous as the caller must hold the pipe lock across the entire * operation. * * If successful, it returns the amount of data spliced, 0 if it hit the EOF or * a hole and a negative error code otherwise. */ ssize_t vfs_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { ssize_t ret; ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; return do_splice_read(in, ppos, pipe, len, flags); } EXPORT_SYMBOL_GPL(vfs_splice_read); /** * splice_direct_to_actor - splices data directly between two non-pipes * @in: file to splice from * @sd: actor information on where to splice to * @actor: handles the data splicing * * Description: * This is a special case helper to splice directly between two * points, without requiring an explicit pipe. Internally an allocated * pipe is cached in the process, and reused during the lifetime of * that process. * */ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, splice_direct_actor *actor) { struct pipe_inode_info *pipe; ssize_t ret, bytes; size_t len; int i, flags, more; /* * We require the input to be seekable, as we don't want to randomly * drop data for eg socket -> socket splicing. Use the piped splicing * for that! */ if (unlikely(!(in->f_mode & FMODE_LSEEK))) return -EINVAL; /* * neither in nor out is a pipe, setup an internal pipe attached to * 'out' and transfer the wanted data from 'in' to 'out' through that */ pipe = current->splice_pipe; if (unlikely(!pipe)) { pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; /* * We don't have an immediate reader, but we'll read the stuff * out of the pipe right after the splice_to_pipe(). So set * PIPE_READERS appropriately. */ pipe->readers = 1; current->splice_pipe = pipe; } /* * Do the splice. */ bytes = 0; len = sd->total_len; /* Don't block on output, we have to drain the direct pipe. */ flags = sd->flags; sd->flags &= ~SPLICE_F_NONBLOCK; /* * We signal MORE until we've read sufficient data to fulfill the * request and we keep signalling it if the caller set it. */ more = sd->flags & SPLICE_F_MORE; sd->flags |= SPLICE_F_MORE; WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { size_t read_len; loff_t pos = sd->pos, prev_pos = pos; ret = do_splice_read(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto read_failure; read_len = ret; sd->total_len = read_len; /* * If we now have sufficient data to fulfill the request then * we clear SPLICE_F_MORE if it was not set initially. */ if (read_len >= len && !more) sd->flags &= ~SPLICE_F_MORE; /* * NOTE: nonblocking mode only applies to the input. We * must not do the output in nonblocking mode as then we * could get stuck data in the internal pipe: */ ret = actor(pipe, sd); if (unlikely(ret <= 0)) { sd->pos = prev_pos; goto out_release; } bytes += ret; len -= ret; sd->pos = pos; if (ret < read_len) { sd->pos = prev_pos + ret; goto out_release; } } done: pipe->tail = pipe->head = 0; file_accessed(in); return bytes; read_failure: /* * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a * "->splice_in()" that returned EOF (ie zero) *and* we have sent at * least 1 byte *then* we will also do the ->splice_eof() call. */ if (ret == 0 && !more && len > 0 && bytes) do_splice_eof(sd); out_release: /* * If we did an incomplete transfer we must release * the pipe buffers in question: */ for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = &pipe->bufs[i]; if (buf->ops) pipe_buf_release(pipe, buf); } if (!bytes) bytes = ret; goto done; } EXPORT_SYMBOL(splice_direct_to_actor); static int direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; long ret; file_start_write(file); ret = do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); file_end_write(file); return ret; } static int splice_file_range_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } static void direct_file_splice_eof(struct splice_desc *sd) { struct file *file = sd->u.file; if (file->f_op->splice_eof) file->f_op->splice_eof(file); } static ssize_t do_splice_direct_actor(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags, splice_direct_actor *actor) { struct splice_desc sd = { .len = len, .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, .splice_eof = direct_file_splice_eof, .opos = opos, }; ssize_t ret; if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = splice_direct_to_actor(in, &sd, actor); if (ret > 0) *ppos = sd.pos; return ret; } /** * do_splice_direct - splices data directly between two files * @in: file to splice from * @ppos: input file offset * @out: file to splice to * @opos: output file offset * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * For use by do_sendfile(). splice can easily emulate sendfile, but * doing it in the application would incur an extra system call * (splice in + splice out, as compared to just sendfile()). So this helper * can splice directly through a process-private pipe. * * Callers already called rw_verify_area() on the entire range. */ ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags) { return do_splice_direct_actor(in, ppos, out, opos, len, flags, direct_splice_actor); } EXPORT_SYMBOL(do_splice_direct); /** * splice_file_range - splices data between two files for copy_file_range() * @in: file to splice from * @ppos: input file offset * @out: file to splice to * @opos: output file offset * @len: number of bytes to splice * * Description: * For use by ->copy_file_range() methods. * Like do_splice_direct(), but vfs_copy_file_range() already holds * start_file_write() on @out file. * * Callers already called rw_verify_area() on the entire range. */ ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len) { lockdep_assert(file_write_started(out)); return do_splice_direct_actor(in, ppos, out, opos, min_t(size_t, len, MAX_RW_COUNT), 0, splice_file_range_actor); } EXPORT_SYMBOL(splice_file_range); static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) { for (;;) { if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); return -EPIPE; } if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; pipe_wait_writable(pipe); } } static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags) { ssize_t ret; pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) ret = do_splice_read(in, offset, opipe, len, flags); pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); return ret; } /* * Determine where to splice to/from. */ ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out, loff_t *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset; ssize_t ret; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) return -EBADF; ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); if (ipipe && opipe) { if (off_in || off_out) return -ESPIPE; /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; ret = splice_pipe_to_pipe(ipipe, opipe, len, flags); } else if (ipipe) { if (off_in) return -ESPIPE; if (off_out) { if (!(out->f_mode & FMODE_PWRITE)) return -EINVAL; offset = *off_out; } else { offset = out->f_pos; } if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = rw_verify_area(WRITE, out, &offset, len); if (unlikely(ret < 0)) return ret; if (in->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); if (!off_out) out->f_pos = offset; else *off_out = offset; } else if (opipe) { if (off_out) return -ESPIPE; if (off_in) { if (!(in->f_mode & FMODE_PREAD)) return -EINVAL; offset = *off_in; } else { offset = in->f_pos; } ret = rw_verify_area(READ, in, &offset, len); if (unlikely(ret < 0)) return ret; if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; ret = splice_file_to_pipe(in, opipe, &offset, len, flags); if (!off_in) in->f_pos = offset; else *off_in = offset; } else { ret = -EINVAL; } if (ret > 0) { /* * Generate modify out before access in: * do_splice_from() may've already sent modify out, * and this ensures the events get merged. */ fsnotify_modify(out); fsnotify_access(in); } return ret; } static ssize_t __do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset, *__off_in = NULL, *__off_out = NULL; ssize_t ret; ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); if (ipipe) { if (off_in) return -ESPIPE; pipe_clear_nowait(in); } if (opipe) { if (off_out) return -ESPIPE; pipe_clear_nowait(out); } if (off_out) { if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; __off_out = &offset; } if (off_in) { if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; __off_in = &offset; } ret = do_splice(in, __off_in, out, __off_out, len, flags); if (ret < 0) return ret; if (__off_out && copy_to_user(off_out, __off_out, sizeof(loff_t))) return -EFAULT; if (__off_in && copy_to_user(off_in, __off_in, sizeof(loff_t))) return -EFAULT; return ret; } static ssize_t iter_to_pipe(struct iov_iter *from, struct pipe_inode_info *pipe, unsigned int flags) { struct pipe_buffer buf = { .ops = &user_page_pipe_buf_ops, .flags = flags }; size_t total = 0; ssize_t ret = 0; while (iov_iter_count(from)) { struct page *pages[16]; ssize_t left; size_t start; int i, n; left = iov_iter_get_pages2(from, pages, ~0UL, 16, &start); if (left <= 0) { ret = left; break; } n = DIV_ROUND_UP(left + start, PAGE_SIZE); for (i = 0; i < n; i++) { int size = min_t(int, left, PAGE_SIZE - start); buf.page = pages[i]; buf.offset = start; buf.len = size; ret = add_to_pipe(pipe, &buf); if (unlikely(ret < 0)) { iov_iter_revert(from, left); // this one got dropped by add_to_pipe() while (++i < n) put_page(pages[i]); goto out; } total += ret; left -= size; start = 0; } } out: return total ? total : ret; } static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { int n = copy_page_to_iter(buf->page, buf->offset, sd->len, sd->u.data); return n == sd->len ? n : -EFAULT; } /* * For lack of a better implementation, implement vmsplice() to userspace * as a simple copy of the pipes pages to the user iov. */ static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe = get_pipe_info(file, true); struct splice_desc sd = { .total_len = iov_iter_count(iter), .flags = flags, .u.data = iter }; ssize_t ret = 0; if (!pipe) return -EBADF; pipe_clear_nowait(file); if (sd.total_len) { pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, pipe_to_user); pipe_unlock(pipe); } if (ret > 0) fsnotify_access(file); return ret; } /* * vmsplice splices a user address range into a pipe. It can be thought of * as splice-from-memory, where the regular splice is splice-from-file (or * to file). In both cases the output is a pipe, naturally. */ static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe; ssize_t ret = 0; unsigned buf_flag = 0; if (flags & SPLICE_F_GIFT) buf_flag = PIPE_BUF_FLAG_GIFT; pipe = get_pipe_info(file, true); if (!pipe) return -EBADF; pipe_clear_nowait(file); pipe_lock(pipe); ret = wait_for_space(pipe, flags); if (!ret) ret = iter_to_pipe(iter, pipe, buf_flag); pipe_unlock(pipe); if (ret > 0) { wakeup_pipe_readers(pipe); fsnotify_modify(file); } return ret; } static int vmsplice_type(struct fd f, int *type) { if (!f.file) return -EBADF; if (f.file->f_mode & FMODE_WRITE) { *type = ITER_SOURCE; } else if (f.file->f_mode & FMODE_READ) { *type = ITER_DEST; } else { fdput(f); return -EBADF; } return 0; } /* * Note that vmsplice only really supports true splicing _from_ user memory * to a pipe, not the other way around. Splicing from user memory is a simple * operation that can be supported without any funky alignment restrictions * or nasty vm tricks. We simply map in the user memory and fill them into * a pipe. The reverse isn't quite as easy, though. There are two possible * solutions for that: * * - memcpy() the data internally, at which point we might as well just * do a regular read() on the buffer anyway. * - Lots of nasty vm tricks, that are neither fast nor flexible (it * has restriction limitations on both ends of the pipe). * * Currently we punt and implement it as a normal copy, see pipe_to_user(). * */ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov, unsigned long, nr_segs, unsigned int, flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t error; struct fd f; int type; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; f = fdget(fd); error = vmsplice_type(f, &type); if (error) return error; error = import_iovec(type, uiov, nr_segs, ARRAY_SIZE(iovstack), &iov, &iter); if (error < 0) goto out_fdput; if (!iov_iter_count(&iter)) error = 0; else if (type == ITER_SOURCE) error = vmsplice_to_pipe(f.file, &iter, flags); else error = vmsplice_to_user(f.file, &iter, flags); kfree(iov); out_fdput: fdput(f); return error; } SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { struct fd in, out; ssize_t error; if (unlikely(!len)) return 0; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; error = -EBADF; in = fdget(fd_in); if (in.file) { out = fdget(fd_out); if (out.file) { error = __do_splice(in.file, off_in, out.file, off_out, len, flags); fdput(out); } fdput(in); } return error; } /* * Make sure there's data to read. Wait for input if we can, otherwise * return an appropriate error. */ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check the pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (!pipe_empty(pipe->head, pipe->tail)) return 0; ret = 0; pipe_lock(pipe); while (pipe_empty(pipe->head, pipe->tail)) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (!pipe->writers) break; if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } pipe_wait_readable(pipe); } pipe_unlock(pipe); return ret; } /* * Make sure there's writeable room. Wait for room if we can, otherwise * return an appropriate error. */ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; ret = 0; pipe_lock(pipe); while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; break; } if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } if (signal_pending(current)) { ret = -ERESTARTSYS; break; } pipe_wait_writable(pipe); } pipe_unlock(pipe); return ret; } /* * Splice contents of ipipe to opipe. */ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; int ret = 0; bool input_wakeup = false; retry: ret = ipipe_prep(ipipe, flags); if (ret) return ret; ret = opipe_prep(opipe, flags); if (ret) return ret; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { size_t o_len; if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; if (pipe_empty(i_head, i_tail) && !ipipe->writers) break; /* * Cannot make any progress, because either the input * pipe is empty or the output pipe is full. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) { /* Already processed some buffers, break */ if (ret) break; if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } /* * We raced with another reader/writer and haven't * managed to process any buffers. A zero return * value means EOF, so retry instead. */ pipe_unlock(ipipe); pipe_unlock(opipe); goto retry; } ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; if (len >= ibuf->len) { /* * Simply move the whole buffer from ipipe to opipe */ *obuf = *ibuf; ibuf->ops = NULL; i_tail++; ipipe->tail = i_tail; input_wakeup = true; o_len = obuf->len; o_head++; opipe->head = o_head; } else { /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift and merge flags, we need to * prevent multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE; obuf->len = len; ibuf->offset += len; ibuf->len -= len; o_len = len; o_head++; opipe->head = o_head; } ret += o_len; len -= o_len; } while (len); pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); if (input_wakeup) wakeup_pipe_writers(ipipe); return ret; } /* * Link contents of ipipe to opipe. */ static ssize_t link_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; ssize_t ret = 0; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; /* * If we have iterated all input buffers or run out of * output room, break. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) break; ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift and merge flag, we need to prevent * multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE; if (obuf->len > len) obuf->len = len; ret += obuf->len; len -= obuf->len; o_head++; opipe->head = o_head; i_tail++; } while (len); pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); return ret; } /* * This is a tee(1) implementation that works on pipes. It doesn't copy * any data, it simply references the 'in' pages on the 'out' pipe. * The 'flags' used are the SPLICE_F_* variants, currently the only * applicable one is SPLICE_F_NONBLOCK. */ ssize_t do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe = get_pipe_info(in, true); struct pipe_inode_info *opipe = get_pipe_info(out, true); ssize_t ret = -EINVAL; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) return -EBADF; /* * Duplicate the contents of ipipe to opipe without actually * copying the data. */ if (ipipe && opipe && ipipe != opipe) { if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. */ ret = ipipe_prep(ipipe, flags); if (!ret) { ret = opipe_prep(opipe, flags); if (!ret) ret = link_pipe(ipipe, opipe, len, flags); } } if (ret > 0) { fsnotify_access(in); fsnotify_modify(out); } return ret; } SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { struct fd in, out; ssize_t error; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; if (unlikely(!len)) return 0; error = -EBADF; in = fdget(fdin); if (in.file) { out = fdget(fdout); if (out.file) { error = do_tee(in.file, out.file, len, flags); fdput(out); } fdput(in); } return error; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** ** ******************************************************************************* ******************************************************************************/ #include <linux/module.h> #include "dlm_internal.h" #include "lockspace.h" #include "member.h" #include "recoverd.h" #include "dir.h" #include "midcomms.h" #include "config.h" #include "memory.h" #include "lock.h" #include "recover.h" #include "requestqueue.h" #include "user.h" #include "ast.h" static int ls_count; static struct mutex ls_lock; static struct list_head lslist; static spinlock_t lslist_lock; static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len) { ssize_t ret = len; int n; int rc = kstrtoint(buf, 0, &n); if (rc) return rc; ls = dlm_find_lockspace_local(ls->ls_local_handle); if (!ls) return -EINVAL; switch (n) { case 0: dlm_ls_stop(ls); break; case 1: dlm_ls_start(ls); break; default: ret = -EINVAL; } dlm_put_lockspace(ls); return ret; } static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len) { int rc = kstrtoint(buf, 0, &ls->ls_uevent_result); if (rc) return rc; set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags); wake_up(&ls->ls_uevent_wait); return len; } static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf) { return snprintf(buf, PAGE_SIZE, "%u\n", ls->ls_global_id); } static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len) { int rc = kstrtouint(buf, 0, &ls->ls_global_id); if (rc) return rc; return len; } static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf) { return snprintf(buf, PAGE_SIZE, "%u\n", dlm_no_directory(ls)); } static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len) { int val; int rc = kstrtoint(buf, 0, &val); if (rc) return rc; if (val == 1) set_bit(LSFL_NODIR, &ls->ls_flags); return len; } static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf) { uint32_t status = dlm_recover_status(ls); return snprintf(buf, PAGE_SIZE, "%x\n", status); } static ssize_t dlm_recover_nodeid_show(struct dlm_ls *ls, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", ls->ls_recover_nodeid); } struct dlm_attr { struct attribute attr; ssize_t (*show)(struct dlm_ls *, char *); ssize_t (*store)(struct dlm_ls *, const char *, size_t); }; static struct dlm_attr dlm_attr_control = { .attr = {.name = "control", .mode = S_IWUSR}, .store = dlm_control_store }; static struct dlm_attr dlm_attr_event = { .attr = {.name = "event_done", .mode = S_IWUSR}, .store = dlm_event_store }; static struct dlm_attr dlm_attr_id = { .attr = {.name = "id", .mode = S_IRUGO | S_IWUSR}, .show = dlm_id_show, .store = dlm_id_store }; static struct dlm_attr dlm_attr_nodir = { .attr = {.name = "nodir", .mode = S_IRUGO | S_IWUSR}, .show = dlm_nodir_show, .store = dlm_nodir_store }; static struct dlm_attr dlm_attr_recover_status = { .attr = {.name = "recover_status", .mode = S_IRUGO}, .show = dlm_recover_status_show }; static struct dlm_attr dlm_attr_recover_nodeid = { .attr = {.name = "recover_nodeid", .mode = S_IRUGO}, .show = dlm_recover_nodeid_show }; static struct attribute *dlm_attrs[] = { &dlm_attr_control.attr, &dlm_attr_event.attr, &dlm_attr_id.attr, &dlm_attr_nodir.attr, &dlm_attr_recover_status.attr, &dlm_attr_recover_nodeid.attr, NULL, }; ATTRIBUTE_GROUPS(dlm); static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); struct dlm_attr *a = container_of(attr, struct dlm_attr, attr); return a->show ? a->show(ls, buf) : 0; } static ssize_t dlm_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t len) { struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); struct dlm_attr *a = container_of(attr, struct dlm_attr, attr); return a->store ? a->store(ls, buf, len) : len; } static void lockspace_kobj_release(struct kobject *k) { struct dlm_ls *ls = container_of(k, struct dlm_ls, ls_kobj); kfree(ls); } static const struct sysfs_ops dlm_attr_ops = { .show = dlm_attr_show, .store = dlm_attr_store, }; static struct kobj_type dlm_ktype = { .default_groups = dlm_groups, .sysfs_ops = &dlm_attr_ops, .release = lockspace_kobj_release, }; static struct kset *dlm_kset; static int do_uevent(struct dlm_ls *ls, int in) { if (in) kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE); else kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE); log_rinfo(ls, "%s the lockspace group...", in ? "joining" : "leaving"); /* dlm_controld will see the uevent, do the necessary group management and then write to sysfs to wake us */ wait_event(ls->ls_uevent_wait, test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags)); log_rinfo(ls, "group event done %d", ls->ls_uevent_result); return ls->ls_uevent_result; } static int dlm_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); add_uevent_var(env, "LOCKSPACE=%s", ls->ls_name); return 0; } static const struct kset_uevent_ops dlm_uevent_ops = { .uevent = dlm_uevent, }; int __init dlm_lockspace_init(void) { ls_count = 0; mutex_init(&ls_lock); INIT_LIST_HEAD(&lslist); spin_lock_init(&lslist_lock); dlm_kset = kset_create_and_add("dlm", &dlm_uevent_ops, kernel_kobj); if (!dlm_kset) { printk(KERN_WARNING "%s: can not create kset\n", __func__); return -ENOMEM; } return 0; } void dlm_lockspace_exit(void) { kset_unregister(dlm_kset); } struct dlm_ls *dlm_find_lockspace_global(uint32_t id) { struct dlm_ls *ls; spin_lock_bh(&lslist_lock); list_for_each_entry(ls, &lslist, ls_list) { if (ls->ls_global_id == id) { atomic_inc(&ls->ls_count); goto out; } } ls = NULL; out: spin_unlock_bh(&lslist_lock); return ls; } struct dlm_ls *dlm_find_lockspace_local(dlm_lockspace_t *lockspace) { struct dlm_ls *ls; spin_lock_bh(&lslist_lock); list_for_each_entry(ls, &lslist, ls_list) { if (ls->ls_local_handle == lockspace) { atomic_inc(&ls->ls_count); goto out; } } ls = NULL; out: spin_unlock_bh(&lslist_lock); return ls; } struct dlm_ls *dlm_find_lockspace_device(int minor) { struct dlm_ls *ls; spin_lock_bh(&lslist_lock); list_for_each_entry(ls, &lslist, ls_list) { if (ls->ls_device.minor == minor) { atomic_inc(&ls->ls_count); goto out; } } ls = NULL; out: spin_unlock_bh(&lslist_lock); return ls; } void dlm_put_lockspace(struct dlm_ls *ls) { if (atomic_dec_and_test(&ls->ls_count)) wake_up(&ls->ls_count_wait); } static void remove_lockspace(struct dlm_ls *ls) { retry: wait_event(ls->ls_count_wait, atomic_read(&ls->ls_count) == 0); spin_lock_bh(&lslist_lock); if (atomic_read(&ls->ls_count) != 0) { spin_unlock_bh(&lslist_lock); goto retry; } WARN_ON(ls->ls_create_count != 0); list_del(&ls->ls_list); spin_unlock_bh(&lslist_lock); } static int threads_start(void) { int error; /* Thread for sending/receiving messages for all lockspace's */ error = dlm_midcomms_start(); if (error) log_print("cannot start dlm midcomms %d", error); return error; } static int new_lockspace(const char *name, const char *cluster, uint32_t flags, int lvblen, const struct dlm_lockspace_ops *ops, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { struct dlm_ls *ls; int do_unreg = 0; int namelen = strlen(name); int error; if (namelen > DLM_LOCKSPACE_LEN || namelen == 0) return -EINVAL; if (lvblen % 8) return -EINVAL; if (!try_module_get(THIS_MODULE)) return -EINVAL; if (!dlm_user_daemon_available()) { log_print("dlm user daemon not available"); error = -EUNATCH; goto out; } if (ops && ops_result) { if (!dlm_config.ci_recover_callbacks) *ops_result = -EOPNOTSUPP; else *ops_result = 0; } if (!cluster) log_print("dlm cluster name '%s' is being used without an application provided cluster name", dlm_config.ci_cluster_name); if (dlm_config.ci_recover_callbacks && cluster && strncmp(cluster, dlm_config.ci_cluster_name, DLM_LOCKSPACE_LEN)) { log_print("dlm cluster name '%s' does not match " "the application cluster name '%s'", dlm_config.ci_cluster_name, cluster); error = -EBADR; goto out; } error = 0; spin_lock_bh(&lslist_lock); list_for_each_entry(ls, &lslist, ls_list) { WARN_ON(ls->ls_create_count <= 0); if (ls->ls_namelen != namelen) continue; if (memcmp(ls->ls_name, name, namelen)) continue; if (flags & DLM_LSFL_NEWEXCL) { error = -EEXIST; break; } ls->ls_create_count++; *lockspace = ls; error = 1; break; } spin_unlock_bh(&lslist_lock); if (error) goto out; error = -ENOMEM; ls = kzalloc(sizeof(*ls), GFP_NOFS); if (!ls) goto out; memcpy(ls->ls_name, name, namelen); ls->ls_namelen = namelen; ls->ls_lvblen = lvblen; atomic_set(&ls->ls_count, 0); init_waitqueue_head(&ls->ls_count_wait); ls->ls_flags = 0; ls->ls_scan_time = jiffies; if (ops && dlm_config.ci_recover_callbacks) { ls->ls_ops = ops; ls->ls_ops_arg = ops_arg; } /* ls_exflags are forced to match among nodes, and we don't * need to require all nodes to have some flags set */ ls->ls_exflags = (flags & ~(DLM_LSFL_FS | DLM_LSFL_NEWEXCL)); INIT_LIST_HEAD(&ls->ls_toss); INIT_LIST_HEAD(&ls->ls_keep); rwlock_init(&ls->ls_rsbtbl_lock); error = rhashtable_init(&ls->ls_rsbtbl, &dlm_rhash_rsb_params); if (error) goto out_lsfree; idr_init(&ls->ls_lkbidr); rwlock_init(&ls->ls_lkbidr_lock); INIT_LIST_HEAD(&ls->ls_waiters); spin_lock_init(&ls->ls_waiters_lock); INIT_LIST_HEAD(&ls->ls_orphans); spin_lock_init(&ls->ls_orphans_lock); INIT_LIST_HEAD(&ls->ls_new_rsb); spin_lock_init(&ls->ls_new_rsb_spin); INIT_LIST_HEAD(&ls->ls_nodes); INIT_LIST_HEAD(&ls->ls_nodes_gone); ls->ls_num_nodes = 0; ls->ls_low_nodeid = 0; ls->ls_total_weight = 0; ls->ls_node_array = NULL; memset(&ls->ls_local_rsb, 0, sizeof(struct dlm_rsb)); ls->ls_local_rsb.res_ls = ls; ls->ls_debug_rsb_dentry = NULL; ls->ls_debug_waiters_dentry = NULL; init_waitqueue_head(&ls->ls_uevent_wait); ls->ls_uevent_result = 0; init_completion(&ls->ls_recovery_done); ls->ls_recovery_result = -1; spin_lock_init(&ls->ls_cb_lock); INIT_LIST_HEAD(&ls->ls_cb_delay); ls->ls_recoverd_task = NULL; mutex_init(&ls->ls_recoverd_active); spin_lock_init(&ls->ls_recover_lock); spin_lock_init(&ls->ls_rcom_spin); get_random_bytes(&ls->ls_rcom_seq, sizeof(uint64_t)); ls->ls_recover_status = 0; ls->ls_recover_seq = get_random_u64(); ls->ls_recover_args = NULL; init_rwsem(&ls->ls_in_recovery); rwlock_init(&ls->ls_recv_active); INIT_LIST_HEAD(&ls->ls_requestqueue); rwlock_init(&ls->ls_requestqueue_lock); spin_lock_init(&ls->ls_clear_proc_locks); /* Due backwards compatibility with 3.1 we need to use maximum * possible dlm message size to be sure the message will fit and * not having out of bounds issues. However on sending side 3.2 * might send less. */ ls->ls_recover_buf = kmalloc(DLM_MAX_SOCKET_BUFSIZE, GFP_NOFS); if (!ls->ls_recover_buf) { error = -ENOMEM; goto out_lkbidr; } ls->ls_slot = 0; ls->ls_num_slots = 0; ls->ls_slots_size = 0; ls->ls_slots = NULL; INIT_LIST_HEAD(&ls->ls_recover_list); spin_lock_init(&ls->ls_recover_list_lock); idr_init(&ls->ls_recover_idr); spin_lock_init(&ls->ls_recover_idr_lock); ls->ls_recover_list_count = 0; ls->ls_local_handle = ls; init_waitqueue_head(&ls->ls_wait_general); INIT_LIST_HEAD(&ls->ls_masters_list); rwlock_init(&ls->ls_masters_lock); INIT_LIST_HEAD(&ls->ls_dir_dump_list); rwlock_init(&ls->ls_dir_dump_lock); INIT_LIST_HEAD(&ls->ls_toss_q); spin_lock_init(&ls->ls_toss_q_lock); timer_setup(&ls->ls_timer, dlm_rsb_toss_timer, TIMER_DEFERRABLE); spin_lock_bh(&lslist_lock); ls->ls_create_count = 1; list_add(&ls->ls_list, &lslist); spin_unlock_bh(&lslist_lock); if (flags & DLM_LSFL_FS) { error = dlm_callback_start(ls); if (error) { log_error(ls, "can't start dlm_callback %d", error); goto out_delist; } } init_waitqueue_head(&ls->ls_recover_lock_wait); /* * Once started, dlm_recoverd first looks for ls in lslist, then * initializes ls_in_recovery as locked in "down" mode. We need * to wait for the wakeup from dlm_recoverd because in_recovery * has to start out in down mode. */ error = dlm_recoverd_start(ls); if (error) { log_error(ls, "can't start dlm_recoverd %d", error); goto out_callback; } wait_event(ls->ls_recover_lock_wait, test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags)); /* let kobject handle freeing of ls if there's an error */ do_unreg = 1; ls->ls_kobj.kset = dlm_kset; error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, "%s", ls->ls_name); if (error) goto out_recoverd; kobject_uevent(&ls->ls_kobj, KOBJ_ADD); /* This uevent triggers dlm_controld in userspace to add us to the group of nodes that are members of this lockspace (managed by the cluster infrastructure.) Once it's done that, it tells us who the current lockspace members are (via configfs) and then tells the lockspace to start running (via sysfs) in dlm_ls_start(). */ error = do_uevent(ls, 1); if (error) goto out_recoverd; /* wait until recovery is successful or failed */ wait_for_completion(&ls->ls_recovery_done); error = ls->ls_recovery_result; if (error) goto out_members; dlm_create_debug_file(ls); log_rinfo(ls, "join complete"); *lockspace = ls; return 0; out_members: do_uevent(ls, 0); dlm_clear_members(ls); kfree(ls->ls_node_array); out_recoverd: dlm_recoverd_stop(ls); out_callback: dlm_callback_stop(ls); out_delist: spin_lock_bh(&lslist_lock); list_del(&ls->ls_list); spin_unlock_bh(&lslist_lock); idr_destroy(&ls->ls_recover_idr); kfree(ls->ls_recover_buf); out_lkbidr: idr_destroy(&ls->ls_lkbidr); rhashtable_destroy(&ls->ls_rsbtbl); out_lsfree: if (do_unreg) kobject_put(&ls->ls_kobj); else kfree(ls); out: module_put(THIS_MODULE); return error; } static int __dlm_new_lockspace(const char *name, const char *cluster, uint32_t flags, int lvblen, const struct dlm_lockspace_ops *ops, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { int error = 0; mutex_lock(&ls_lock); if (!ls_count) error = threads_start(); if (error) goto out; error = new_lockspace(name, cluster, flags, lvblen, ops, ops_arg, ops_result, lockspace); if (!error) ls_count++; if (error > 0) error = 0; if (!ls_count) { dlm_midcomms_shutdown(); dlm_midcomms_stop(); } out: mutex_unlock(&ls_lock); return error; } int dlm_new_lockspace(const char *name, const char *cluster, uint32_t flags, int lvblen, const struct dlm_lockspace_ops *ops, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { return __dlm_new_lockspace(name, cluster, flags | DLM_LSFL_FS, lvblen, ops, ops_arg, ops_result, lockspace); } int dlm_new_user_lockspace(const char *name, const char *cluster, uint32_t flags, int lvblen, const struct dlm_lockspace_ops *ops, void *ops_arg, int *ops_result, dlm_lockspace_t **lockspace) { return __dlm_new_lockspace(name, cluster, flags, lvblen, ops, ops_arg, ops_result, lockspace); } static int lkb_idr_is_local(int id, void *p, void *data) { struct dlm_lkb *lkb = p; return lkb->lkb_nodeid == 0 && lkb->lkb_grmode != DLM_LOCK_IV; } static int lkb_idr_is_any(int id, void *p, void *data) { return 1; } static int lkb_idr_free(int id, void *p, void *data) { struct dlm_lkb *lkb = p; if (lkb->lkb_lvbptr && test_bit(DLM_IFL_MSTCPY_BIT, &lkb->lkb_iflags)) dlm_free_lvb(lkb->lkb_lvbptr); dlm_free_lkb(lkb); return 0; } /* NOTE: We check the lkbidr here rather than the resource table. This is because there may be LKBs queued as ASTs that have been unlinked from their RSBs and are pending deletion once the AST has been delivered */ static int lockspace_busy(struct dlm_ls *ls, int force) { int rv; read_lock_bh(&ls->ls_lkbidr_lock); if (force == 0) { rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_any, ls); } else if (force == 1) { rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_local, ls); } else { rv = 0; } read_unlock_bh(&ls->ls_lkbidr_lock); return rv; } static void rhash_free_rsb(void *ptr, void *arg) { struct dlm_rsb *rsb = ptr; dlm_free_rsb(rsb); } static int release_lockspace(struct dlm_ls *ls, int force) { struct dlm_rsb *rsb; int busy, rv; busy = lockspace_busy(ls, force); spin_lock_bh(&lslist_lock); if (ls->ls_create_count == 1) { if (busy) { rv = -EBUSY; } else { /* remove_lockspace takes ls off lslist */ ls->ls_create_count = 0; rv = 0; } } else if (ls->ls_create_count > 1) { rv = --ls->ls_create_count; } else { rv = -EINVAL; } spin_unlock_bh(&lslist_lock); if (rv) { log_debug(ls, "release_lockspace no remove %d", rv); return rv; } if (ls_count == 1) dlm_midcomms_version_wait(); dlm_device_deregister(ls); if (force < 3 && dlm_user_daemon_available()) do_uevent(ls, 0); dlm_recoverd_stop(ls); /* clear the LSFL_RUNNING flag to fast up * time_shutdown_sync(), we don't care anymore */ clear_bit(LSFL_RUNNING, &ls->ls_flags); timer_shutdown_sync(&ls->ls_timer); if (ls_count == 1) { dlm_clear_members(ls); dlm_midcomms_shutdown(); } dlm_callback_stop(ls); remove_lockspace(ls); dlm_delete_debug_file(ls); idr_destroy(&ls->ls_recover_idr); kfree(ls->ls_recover_buf); /* * Free all lkb's in idr */ idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls); idr_destroy(&ls->ls_lkbidr); /* * Free all rsb's on rsbtbl */ rhashtable_free_and_destroy(&ls->ls_rsbtbl, rhash_free_rsb, NULL); while (!list_empty(&ls->ls_new_rsb)) { rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb, res_hashchain); list_del(&rsb->res_hashchain); dlm_free_rsb(rsb); } /* * Free structures on any other lists */ dlm_purge_requestqueue(ls); kfree(ls->ls_recover_args); dlm_clear_members(ls); dlm_clear_members_gone(ls); kfree(ls->ls_node_array); log_rinfo(ls, "release_lockspace final free"); kobject_put(&ls->ls_kobj); /* The ls structure will be freed when the kobject is done with */ module_put(THIS_MODULE); return 0; } /* * Called when a system has released all its locks and is not going to use the * lockspace any longer. We free everything we're managing for this lockspace. * Remaining nodes will go through the recovery process as if we'd died. The * lockspace must continue to function as usual, participating in recoveries, * until this returns. * * Force has 4 possible values: * 0 - don't destroy lockspace if it has any LKBs * 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs * 2 - destroy lockspace regardless of LKBs * 3 - destroy lockspace as part of a forced shutdown */ int dlm_release_lockspace(void *lockspace, int force) { struct dlm_ls *ls; int error; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; dlm_put_lockspace(ls); mutex_lock(&ls_lock); error = release_lockspace(ls, force); if (!error) ls_count--; if (!ls_count) dlm_midcomms_stop(); mutex_unlock(&ls_lock); return error; } void dlm_stop_lockspaces(void) { struct dlm_ls *ls; int count; restart: count = 0; spin_lock_bh(&lslist_lock); list_for_each_entry(ls, &lslist, ls_list) { if (!test_bit(LSFL_RUNNING, &ls->ls_flags)) { count++; continue; } spin_unlock_bh(&lslist_lock); log_error(ls, "no userland control daemon, stopping lockspace"); dlm_ls_stop(ls); goto restart; } spin_unlock_bh(&lslist_lock); if (count) log_print("dlm user daemon left %d lockspaces", count); } |
| 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/compaction.c * * Memory compaction for the reduction of external fragmentation. Note that * this heavily depends upon page migration to do all the real heavy * lifting * * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie> */ #include <linux/cpu.h> #include <linux/swap.h> #include <linux/migrate.h> #include <linux/compaction.h> #include <linux/mm_inline.h> #include <linux/sched/signal.h> #include <linux/backing-dev.h> #include <linux/sysctl.h> #include <linux/sysfs.h> #include <linux/page-isolation.h> #include <linux/kasan.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/page_owner.h> #include <linux/psi.h> #include "internal.h" #ifdef CONFIG_COMPACTION /* * Fragmentation score check interval for proactive compaction purposes. */ #define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); } static inline void count_compact_events(enum vm_event_item item, long delta) { count_vm_events(item, delta); } /* * order == -1 is expected when compacting proactively via * 1. /proc/sys/vm/compact_memory * 2. /sys/devices/system/node/nodex/compact * 3. /proc/sys/vm/compaction_proactiveness */ static inline bool is_via_compact_memory(int order) { return order == -1; } #else #define count_compact_event(item) do { } while (0) #define count_compact_events(item, delta) do { } while (0) static inline bool is_via_compact_memory(int order) { return false; } #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> #define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order)) #define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order)) /* * Page order with-respect-to which proactive compaction * calculates external fragmentation, which is used as * the "fragmentation score" of a node/zone. */ #if defined CONFIG_TRANSPARENT_HUGEPAGE #define COMPACTION_HPAGE_ORDER HPAGE_PMD_ORDER #elif defined CONFIG_HUGETLBFS #define COMPACTION_HPAGE_ORDER HUGETLB_PAGE_ORDER #else #define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) #endif static void split_map_pages(struct list_head *freepages) { unsigned int i, order; struct page *page, *next; LIST_HEAD(tmp_list); for (order = 0; order < NR_PAGE_ORDERS; order++) { list_for_each_entry_safe(page, next, &freepages[order], lru) { unsigned int nr_pages; list_del(&page->lru); nr_pages = 1 << order; post_alloc_hook(page, order, __GFP_MOVABLE); if (order) split_page(page, order); for (i = 0; i < nr_pages; i++) { list_add(&page->lru, &tmp_list); page++; } } list_splice_init(&tmp_list, &freepages[0]); } } static unsigned long release_free_list(struct list_head *freepages) { int order; unsigned long high_pfn = 0; for (order = 0; order < NR_PAGE_ORDERS; order++) { struct page *page, *next; list_for_each_entry_safe(page, next, &freepages[order], lru) { unsigned long pfn = page_to_pfn(page); list_del(&page->lru); /* * Convert free pages into post allocation pages, so * that we can free them via __free_page. */ post_alloc_hook(page, order, __GFP_MOVABLE); __free_pages(page, order); if (pfn > high_pfn) high_pfn = pfn; } } return high_pfn; } #ifdef CONFIG_COMPACTION bool PageMovable(struct page *page) { const struct movable_operations *mops; VM_BUG_ON_PAGE(!PageLocked(page), page); if (!__PageMovable(page)) return false; mops = page_movable_ops(page); if (mops) return true; return false; } void __SetPageMovable(struct page *page, const struct movable_operations *mops) { VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page); page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE); } EXPORT_SYMBOL(__SetPageMovable); void __ClearPageMovable(struct page *page) { VM_BUG_ON_PAGE(!PageMovable(page), page); /* * This page still has the type of a movable page, but it's * actually not movable any more. */ page->mapping = (void *)PAGE_MAPPING_MOVABLE; } EXPORT_SYMBOL(__ClearPageMovable); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 /* * Compaction is deferred when compaction fails to result in a page * allocation success. 1 << compact_defer_shift, compactions are skipped up * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT */ static void defer_compaction(struct zone *zone, int order) { zone->compact_considered = 0; zone->compact_defer_shift++; if (order < zone->compact_order_failed) zone->compact_order_failed = order; if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; trace_mm_compaction_defer_compaction(zone, order); } /* Returns true if compaction should be skipped this time */ static bool compaction_deferred(struct zone *zone, int order) { unsigned long defer_limit = 1UL << zone->compact_defer_shift; if (order < zone->compact_order_failed) return false; /* Avoid possible overflow */ if (++zone->compact_considered >= defer_limit) { zone->compact_considered = defer_limit; return false; } trace_mm_compaction_deferred(zone, order); return true; } /* * Update defer tracking counters after successful compaction of given order, * which means an allocation either succeeded (alloc_success == true) or is * expected to succeed. */ void compaction_defer_reset(struct zone *zone, int order, bool alloc_success) { if (alloc_success) { zone->compact_considered = 0; zone->compact_defer_shift = 0; } if (order >= zone->compact_order_failed) zone->compact_order_failed = order + 1; trace_mm_compaction_defer_reset(zone, order); } /* Returns true if restarting compaction after many failures */ static bool compaction_restarting(struct zone *zone, int order) { if (order < zone->compact_order_failed) return false; return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && zone->compact_considered >= 1UL << zone->compact_defer_shift; } /* Returns true if the pageblock should be scanned for pages to isolate. */ static inline bool isolation_suitable(struct compact_control *cc, struct page *page) { if (cc->ignore_skip_hint) return true; return !get_pageblock_skip(page); } static void reset_cached_positions(struct zone *zone) { zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = pageblock_start_pfn(zone_end_pfn(zone) - 1); } #ifdef CONFIG_SPARSEMEM /* * If the PFN falls into an offline section, return the start PFN of the * next online section. If the PFN falls into an online section or if * there is no next online section, return 0. */ static unsigned long skip_offline_sections(unsigned long start_pfn) { unsigned long start_nr = pfn_to_section_nr(start_pfn); if (online_section_nr(start_nr)) return 0; while (++start_nr <= __highest_present_section_nr) { if (online_section_nr(start_nr)) return section_nr_to_pfn(start_nr); } return 0; } /* * If the PFN falls into an offline section, return the end PFN of the * next online section in reverse. If the PFN falls into an online section * or if there is no next online section in reverse, return 0. */ static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) { unsigned long start_nr = pfn_to_section_nr(start_pfn); if (!start_nr || online_section_nr(start_nr)) return 0; while (start_nr-- > 0) { if (online_section_nr(start_nr)) return section_nr_to_pfn(start_nr) + PAGES_PER_SECTION; } return 0; } #else static unsigned long skip_offline_sections(unsigned long start_pfn) { return 0; } static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) { return 0; } #endif /* * Compound pages of >= pageblock_order should consistently be skipped until * released. It is always pointless to compact pages of such order (if they are * migratable), and the pageblocks they occupy cannot contain any free pages. */ static bool pageblock_skip_persistent(struct page *page) { if (!PageCompound(page)) return false; page = compound_head(page); if (compound_order(page) >= pageblock_order) return true; return false; } static bool __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, bool check_target) { struct page *page = pfn_to_online_page(pfn); struct page *block_page; struct page *end_page; unsigned long block_pfn; if (!page) return false; if (zone != page_zone(page)) return false; if (pageblock_skip_persistent(page)) return false; /* * If skip is already cleared do no further checking once the * restart points have been set. */ if (check_source && check_target && !get_pageblock_skip(page)) return true; /* * If clearing skip for the target scanner, do not select a * non-movable pageblock as the starting point. */ if (!check_source && check_target && get_pageblock_migratetype(page) != MIGRATE_MOVABLE) return false; /* Ensure the start of the pageblock or zone is online and valid */ block_pfn = pageblock_start_pfn(pfn); block_pfn = max(block_pfn, zone->zone_start_pfn); block_page = pfn_to_online_page(block_pfn); if (block_page) { page = block_page; pfn = block_pfn; } /* Ensure the end of the pageblock or zone is online and valid */ block_pfn = pageblock_end_pfn(pfn) - 1; block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); end_page = pfn_to_online_page(block_pfn); if (!end_page) return false; /* * Only clear the hint if a sample indicates there is either a * free page or an LRU page in the block. One or other condition * is necessary for the block to be a migration source/target. */ do { if (check_source && PageLRU(page)) { clear_pageblock_skip(page); return true; } if (check_target && PageBuddy(page)) { clear_pageblock_skip(page); return true; } page += (1 << PAGE_ALLOC_COSTLY_ORDER); } while (page <= end_page); return false; } /* * This function is called to clear all cached information on pageblocks that * should be skipped for page isolation when the migrate and free page scanner * meet. */ static void __reset_isolation_suitable(struct zone *zone) { unsigned long migrate_pfn = zone->zone_start_pfn; unsigned long free_pfn = zone_end_pfn(zone) - 1; unsigned long reset_migrate = free_pfn; unsigned long reset_free = migrate_pfn; bool source_set = false; bool free_set = false; /* Only flush if a full compaction finished recently */ if (!zone->compact_blockskip_flush) return; zone->compact_blockskip_flush = false; /* * Walk the zone and update pageblock skip information. Source looks * for PageLRU while target looks for PageBuddy. When the scanner * is found, both PageBuddy and PageLRU are checked as the pageblock * is suitable as both source and target. */ for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages, free_pfn -= pageblock_nr_pages) { cond_resched(); /* Update the migrate PFN */ if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) && migrate_pfn < reset_migrate) { source_set = true; reset_migrate = migrate_pfn; zone->compact_init_migrate_pfn = reset_migrate; zone->compact_cached_migrate_pfn[0] = reset_migrate; zone->compact_cached_migrate_pfn[1] = reset_migrate; } /* Update the free PFN */ if (__reset_isolation_pfn(zone, free_pfn, free_set, true) && free_pfn > reset_free) { free_set = true; reset_free = free_pfn; zone->compact_init_free_pfn = reset_free; zone->compact_cached_free_pfn = reset_free; } } /* Leave no distance if no suitable block was reset */ if (reset_migrate >= reset_free) { zone->compact_cached_migrate_pfn[0] = migrate_pfn; zone->compact_cached_migrate_pfn[1] = migrate_pfn; zone->compact_cached_free_pfn = free_pfn; } } void reset_isolation_suitable(pg_data_t *pgdat) { int zoneid; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { struct zone *zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; __reset_isolation_suitable(zone); } } /* * Sets the pageblock skip bit if it was clear. Note that this is a hint as * locks are not required for read/writers. Returns true if it was already set. */ static bool test_and_set_skip(struct compact_control *cc, struct page *page) { bool skip; /* Do not update if skip hint is being ignored */ if (cc->ignore_skip_hint) return false; skip = get_pageblock_skip(page); if (!skip && !cc->no_set_skip_hint) set_pageblock_skip(page); return skip; } static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) { struct zone *zone = cc->zone; /* Set for isolation rather than compaction */ if (cc->no_set_skip_hint) return; pfn = pageblock_end_pfn(pfn); /* Update where async and sync compaction should restart */ if (pfn > zone->compact_cached_migrate_pfn[0]) zone->compact_cached_migrate_pfn[0] = pfn; if (cc->mode != MIGRATE_ASYNC && pfn > zone->compact_cached_migrate_pfn[1]) zone->compact_cached_migrate_pfn[1] = pfn; } /* * If no pages were isolated then mark this pageblock to be skipped in the * future. The information is later cleared by __reset_isolation_suitable(). */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long pfn) { struct zone *zone = cc->zone; if (cc->no_set_skip_hint) return; set_pageblock_skip(page); if (pfn < zone->compact_cached_free_pfn) zone->compact_cached_free_pfn = pfn; } #else static inline bool isolation_suitable(struct compact_control *cc, struct page *page) { return true; } static inline bool pageblock_skip_persistent(struct page *page) { return false; } static inline void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long pfn) { } static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) { } static bool test_and_set_skip(struct compact_control *cc, struct page *page) { return false; } #endif /* CONFIG_COMPACTION */ /* * Compaction requires the taking of some coarse locks that are potentially * very heavily contended. For async compaction, trylock and record if the * lock is contended. The lock will still be acquired but compaction will * abort when the current block is finished regardless of success rate. * Sync compaction acquires the lock. * * Always returns true which makes it easier to track lock state in callers. */ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags, struct compact_control *cc) __acquires(lock) { /* Track if the lock is contended in async mode */ if (cc->mode == MIGRATE_ASYNC && !cc->contended) { if (spin_trylock_irqsave(lock, *flags)) return true; cc->contended = true; } spin_lock_irqsave(lock, *flags); return true; } /* * Compaction requires the taking of some coarse locks that are potentially * very heavily contended. The lock should be periodically unlocked to avoid * having disabled IRQs for a long time, even when there is nobody waiting on * the lock. It might also be that allowing the IRQs will result in * need_resched() becoming true. If scheduling is needed, compaction schedules. * Either compaction type will also abort if a fatal signal is pending. * In either case if the lock was locked, it is dropped and not regained. * * Returns true if compaction should abort due to fatal signal pending. * Returns false when compaction can continue. */ static bool compact_unlock_should_abort(spinlock_t *lock, unsigned long flags, bool *locked, struct compact_control *cc) { if (*locked) { spin_unlock_irqrestore(lock, flags); *locked = false; } if (fatal_signal_pending(current)) { cc->contended = true; return true; } cond_resched(); return false; } /* * Isolate free pages onto a private freelist. If @strict is true, will abort * returning 0 on any invalid PFNs or non-free pages inside of the pageblock * (even though it may still end up isolating some pages). */ static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long *start_pfn, unsigned long end_pfn, struct list_head *freelist, unsigned int stride, bool strict) { int nr_scanned = 0, total_isolated = 0; struct page *page; unsigned long flags = 0; bool locked = false; unsigned long blockpfn = *start_pfn; unsigned int order; /* Strict mode is for isolation, speed is secondary */ if (strict) stride = 1; page = pfn_to_page(blockpfn); /* Isolate free pages. */ for (; blockpfn < end_pfn; blockpfn += stride, page += stride) { int isolated; /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort if fatal signal * pending. */ if (!(blockpfn % COMPACT_CLUSTER_MAX) && compact_unlock_should_abort(&cc->zone->lock, flags, &locked, cc)) break; nr_scanned++; /* * For compound pages such as THP and hugetlbfs, we can save * potentially a lot of iterations if we skip them at once. * The check is racy, but we can consider only valid values * and the only danger is skipping too much. */ if (PageCompound(page)) { const unsigned int order = compound_order(page); if (blockpfn + (1UL << order) <= end_pfn) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } if (!PageBuddy(page)) goto isolate_fail; /* If we already hold the lock, we can skip some rechecking. */ if (!locked) { locked = compact_lock_irqsave(&cc->zone->lock, &flags, cc); /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) goto isolate_fail; } /* Found a free page, will break it into order-0 pages */ order = buddy_order(page); isolated = __isolate_free_page(page, order); if (!isolated) break; set_page_private(page, order); nr_scanned += isolated - 1; total_isolated += isolated; cc->nr_freepages += isolated; list_add_tail(&page->lru, &freelist[order]); if (!strict && cc->nr_migratepages <= cc->nr_freepages) { blockpfn += isolated; break; } /* Advance to the end of split page */ blockpfn += isolated - 1; page += isolated - 1; continue; isolate_fail: if (strict) break; } if (locked) spin_unlock_irqrestore(&cc->zone->lock, flags); /* * Be careful to not go outside of the pageblock. */ if (unlikely(blockpfn > end_pfn)) blockpfn = end_pfn; trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn, nr_scanned, total_isolated); /* Record how far we have got within the block */ *start_pfn = blockpfn; /* * If strict isolation is requested by CMA then check that all the * pages requested were isolated. If there were any failures, 0 is * returned and CMA will fail. */ if (strict && blockpfn < end_pfn) total_isolated = 0; cc->total_free_scanned += nr_scanned; if (total_isolated) count_compact_events(COMPACTISOLATED, total_isolated); return total_isolated; } /** * isolate_freepages_range() - isolate free pages. * @cc: Compaction control structure. * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * * Non-free pages, invalid PFNs, or zone boundaries within the * [start_pfn, end_pfn) range are considered errors, cause function to * undo its actions and return zero. * * Otherwise, function returns one-past-the-last PFN of isolated page * (which may be greater then end_pfn if end fell in a middle of * a free page). */ unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long isolated, pfn, block_start_pfn, block_end_pfn; int order; struct list_head tmp_freepages[NR_PAGE_ORDERS]; for (order = 0; order < NR_PAGE_ORDERS; order++) INIT_LIST_HEAD(&tmp_freepages[order]); pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn += isolated, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* Protect pfn from changing by isolate_freepages_block */ unsigned long isolate_start_pfn = pfn; /* * pfn could pass the block_end_pfn if isolated freepage * is more than pageblock order. In this case, we adjust * scanning range to right one. */ if (pfn >= block_end_pfn) { block_start_pfn = pageblock_start_pfn(pfn); block_end_pfn = pageblock_end_pfn(pfn); } block_end_pfn = min(block_end_pfn, end_pfn); if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone)) break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, tmp_freepages, 0, true); /* * In strict mode, isolate_freepages_block() returns 0 if * there are any holes in the block (ie. invalid PFNs or * non-free pages). */ if (!isolated) break; /* * If we managed to isolate pages, it is always (1 << n) * * pageblock_nr_pages for some non-negative n. (Max order * page may span two pageblocks). */ } if (pfn < end_pfn) { /* Loop terminated early, cleanup. */ release_free_list(tmp_freepages); return 0; } /* __isolate_free_page() does not map the pages */ split_map_pages(tmp_freepages); /* We don't use freelists for anything. */ return pfn; } /* Similar to reclaim, but different enough that they don't share logic */ static bool too_many_isolated(struct compact_control *cc) { pg_data_t *pgdat = cc->zone->zone_pgdat; bool too_many; unsigned long active, inactive, isolated; inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_ANON); active = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + node_page_state(pgdat, NR_ISOLATED_ANON); /* * Allow GFP_NOFS to isolate past the limit set for regular * compaction runs. This prevents an ABBA deadlock when other * compactors have already isolated to the limit, but are * blocked on filesystem locks held by the GFP_NOFS thread. */ if (cc->gfp_mask & __GFP_FS) { inactive >>= 3; active >>= 3; } too_many = isolated > (inactive + active) / 2; if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /** * skip_isolation_on_order() - determine when to skip folio isolation based on * folio order and compaction target order * @order: to-be-isolated folio order * @target_order: compaction target order * * This avoids unnecessary folio isolations during compaction. */ static bool skip_isolation_on_order(int order, int target_order) { /* * Unless we are performing global compaction (i.e., * is_via_compact_memory), skip any folios that are larger than the * target order: we wouldn't be here if we'd have a free folio with * the desired target_order, so migrating this folio would likely fail * later. */ if (!is_via_compact_memory(target_order) && order >= target_order) return true; /* * We limit memory compaction to pageblocks and won't try * creating free blocks of memory that are larger than that. */ return order >= pageblock_order; } /** * isolate_migratepages_block() - isolate all migrate-able pages within * a single pageblock * @cc: Compaction control structure. * @low_pfn: The first PFN to isolate * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock * @mode: Isolation mode to be used. * * Isolate all pages that can be migrated from the range specified by * [low_pfn, end_pfn). The range is expected to be within same pageblock. * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion, * -ENOMEM in case we could not allocate a page, or 0. * cc->migrate_pfn will contain the next pfn to scan. * * The pages are isolated on cc->migratepages list (not required to be empty), * and cc->nr_migratepages is updated accordingly. */ static int isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn, isolate_mode_t mode) { pg_data_t *pgdat = cc->zone->zone_pgdat; unsigned long nr_scanned = 0, nr_isolated = 0; struct lruvec *lruvec; unsigned long flags = 0; struct lruvec *locked = NULL; struct folio *folio = NULL; struct page *page = NULL, *valid_page = NULL; struct address_space *mapping; unsigned long start_pfn = low_pfn; bool skip_on_failure = false; unsigned long next_skip_pfn = 0; bool skip_updated = false; int ret = 0; cc->migrate_pfn = low_pfn; /* * Ensure that there are not too many pages isolated from the LRU * list by either parallel reclaimers or compaction. If there are, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(cc))) { /* stop isolation if there are still pages not migrated */ if (cc->nr_migratepages) return -EAGAIN; /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); if (fatal_signal_pending(current)) return -EINTR; } cond_resched(); if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) { skip_on_failure = true; next_skip_pfn = block_end_pfn(low_pfn, cc->order); } /* Time to isolate some pages for migration */ for (; low_pfn < end_pfn; low_pfn++) { bool is_dirty, is_unevictable; if (skip_on_failure && low_pfn >= next_skip_pfn) { /* * We have isolated all migration candidates in the * previous order-aligned block, and did not skip it due * to failure. We should migrate the pages now and * hopefully succeed compaction. */ if (nr_isolated) break; /* * We failed to isolate in the previous order-aligned * block. Set the new boundary to the end of the * current block. Note we can't simply increase * next_skip_pfn by 1 << order, as low_pfn might have * been incremented by a higher number due to skipping * a compound or a high-order buddy page in the * previous loop iteration. */ next_skip_pfn = block_end_pfn(low_pfn, cc->order); } /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort completely if * a fatal signal is pending. */ if (!(low_pfn % COMPACT_CLUSTER_MAX)) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } if (fatal_signal_pending(current)) { cc->contended = true; ret = -EINTR; goto fatal_pending; } cond_resched(); } nr_scanned++; page = pfn_to_page(low_pfn); /* * Check if the pageblock has already been marked skipped. * Only the first PFN is checked as the caller isolates * COMPACT_CLUSTER_MAX at a time so the second call must * not falsely conclude that the block should be skipped. */ if (!valid_page && (pageblock_aligned(low_pfn) || low_pfn == cc->zone->zone_start_pfn)) { if (!isolation_suitable(cc, page)) { low_pfn = end_pfn; folio = NULL; goto isolate_abort; } valid_page = page; } if (PageHuge(page)) { /* * skip hugetlbfs if we are not compacting for pages * bigger than its order. THPs and other compound pages * are handled below. */ if (!cc->alloc_contig) { const unsigned int order = compound_order(page); if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } /* for alloc_contig case */ if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } ret = isolate_or_dissolve_huge_page(page, &cc->migratepages); /* * Fail isolation in case isolate_or_dissolve_huge_page() * reports an error. In case of -ENOMEM, abort right away. */ if (ret < 0) { /* Do not report -EBUSY down the chain */ if (ret == -EBUSY) ret = 0; low_pfn += compound_nr(page) - 1; nr_scanned += compound_nr(page) - 1; goto isolate_fail; } if (PageHuge(page)) { /* * Hugepage was successfully isolated and placed * on the cc->migratepages list. */ folio = page_folio(page); low_pfn += folio_nr_pages(folio) - 1; goto isolate_success_no_list; } /* * Ok, the hugepage was dissolved. Now these pages are * Buddy and cannot be re-allocated because they are * isolated. Fall-through as the check below handles * Buddy pages. */ } /* * Skip if free. We read page order here without zone lock * which is generally unsafe, but the race window is small and * the worst thing that can happen is that we skip some * potential isolation targets. */ if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); /* * Without lock, we cannot be sure that what we got is * a valid page order. Consider only values in the * valid order range to prevent low_pfn overflow. */ if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) { low_pfn += (1UL << freepage_order) - 1; nr_scanned += (1UL << freepage_order) - 1; } continue; } /* * Regardless of being on LRU, compound pages such as THP * (hugetlbfs is handled above) are not to be compacted unless * we are attempting an allocation larger than the compound * page size. We can potentially save a lot of iterations if we * skip them at once. The check is racy, but we can consider * only valid values and the only danger is skipping too much. */ if (PageCompound(page) && !cc->alloc_contig) { const unsigned int order = compound_order(page); /* Skip based on page order and compaction target order. */ if (skip_isolation_on_order(order, cc->order)) { if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } } /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU and non-lru movable pages. * Skip any other type of page */ if (!PageLRU(page)) { /* * __PageMovable can return false positive so we need * to verify it under page_lock. */ if (unlikely(__PageMovable(page)) && !PageIsolated(page)) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } if (isolate_movable_page(page, mode)) { folio = page_folio(page); goto isolate_success; } } goto isolate_fail; } /* * Be careful not to clear PageLRU until after we're * sure the page is not being freed elsewhere -- the * page release code relies on it. */ folio = folio_get_nontail_page(page); if (unlikely(!folio)) goto isolate_fail; /* * Migration will fail if an anonymous page is pinned in memory, * so avoid taking lru_lock and isolating it unnecessarily in an * admittedly racy check. */ mapping = folio_mapping(folio); if (!mapping && (folio_ref_count(folio) - 1) > folio_mapcount(folio)) goto isolate_fail_put; /* * Only allow to migrate anonymous pages in GFP_NOFS context * because those do not depend on fs locks. */ if (!(cc->gfp_mask & __GFP_FS) && mapping) goto isolate_fail_put; /* Only take pages on LRU: a check now makes later tests safe */ if (!folio_test_lru(folio)) goto isolate_fail_put; is_unevictable = folio_test_unevictable(folio); /* Compaction might skip unevictable pages but CMA takes them */ if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable) goto isolate_fail_put; /* * To minimise LRU disruption, the caller can indicate with * ISOLATE_ASYNC_MIGRATE that it only wants to isolate pages * it will be able to migrate without blocking - clean pages * for the most part. PageWriteback would require blocking. */ if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio)) goto isolate_fail_put; is_dirty = folio_test_dirty(folio); if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) || (mapping && is_unevictable)) { bool migrate_dirty = true; bool is_unmovable; /* * Only folios without mappings or that have * a ->migrate_folio callback are possible to migrate * without blocking. * * Folios from unmovable mappings are not migratable. * * However, we can be racing with truncation, which can * free the mapping that we need to check. Truncation * holds the folio lock until after the folio is removed * from the page so holding it ourselves is sufficient. * * To avoid locking the folio just to check unmovable, * assume every unmovable folio is also unevictable, * which is a cheaper test. If our assumption goes * wrong, it's not a correctness bug, just potentially * wasted cycles. */ if (!folio_trylock(folio)) goto isolate_fail_put; mapping = folio_mapping(folio); if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) { migrate_dirty = !mapping || mapping->a_ops->migrate_folio; } is_unmovable = mapping && mapping_unmovable(mapping); folio_unlock(folio); if (!migrate_dirty || is_unmovable) goto isolate_fail_put; } /* Try isolate the folio */ if (!folio_test_clear_lru(folio)) goto isolate_fail_put; lruvec = folio_lruvec(folio); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { if (locked) unlock_page_lruvec_irqrestore(locked, flags); compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); locked = lruvec; lruvec_memcg_debug(lruvec, folio); /* * Try get exclusive access under lock. If marked for * skip, the scan is aborted unless the current context * is a rescan to reach the end of the pageblock. */ if (!skip_updated && valid_page) { skip_updated = true; if (test_and_set_skip(cc, valid_page) && !cc->finish_pageblock) { low_pfn = end_pfn; goto isolate_abort; } } /* * Check LRU folio order under the lock */ if (unlikely(skip_isolation_on_order(folio_order(folio), cc->order) && !cc->alloc_contig)) { low_pfn += folio_nr_pages(folio) - 1; nr_scanned += folio_nr_pages(folio) - 1; folio_set_lru(folio); goto isolate_fail_put; } } /* The folio is taken off the LRU */ if (folio_test_large(folio)) low_pfn += folio_nr_pages(folio) - 1; /* Successfully isolated */ lruvec_del_folio(lruvec, folio); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); isolate_success: list_add(&folio->lru, &cc->migratepages); isolate_success_no_list: cc->nr_migratepages += folio_nr_pages(folio); nr_isolated += folio_nr_pages(folio); nr_scanned += folio_nr_pages(folio) - 1; /* * Avoid isolating too much unless this block is being * fully scanned (e.g. dirty/writeback pages, parallel allocation) * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && !cc->finish_pageblock && !cc->contended) { ++low_pfn; break; } continue; isolate_fail_put: /* Avoid potential deadlock in freeing page under lru_lock */ if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } folio_put(folio); isolate_fail: if (!skip_on_failure && ret != -ENOMEM) continue; /* * We have isolated some pages, but then failed. Release them * instead of migrating, as we cannot form the cc->order buddy * page anyway. */ if (nr_isolated) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; nr_isolated = 0; } if (low_pfn < next_skip_pfn) { low_pfn = next_skip_pfn - 1; /* * The check near the loop beginning would have updated * next_skip_pfn too, but this is a bit simpler. */ next_skip_pfn += 1UL << cc->order; } if (ret == -ENOMEM) break; } /* * The PageBuddy() check could have potentially brought us outside * the range to be scanned. */ if (unlikely(low_pfn > end_pfn)) low_pfn = end_pfn; folio = NULL; isolate_abort: if (locked) unlock_page_lruvec_irqrestore(locked, flags); if (folio) { folio_set_lru(folio); folio_put(folio); } /* * Update the cached scanner pfn once the pageblock has been scanned. * Pages will either be migrated in which case there is no point * scanning in the near future or migration failed in which case the * failure reason may persist. The block is marked for skipping if * there were no pages isolated in the block or if the block is * rescanned twice in a row. */ if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) { if (!cc->no_set_skip_hint && valid_page && !skip_updated) set_pageblock_skip(valid_page); update_cached_migrate(cc, low_pfn); } trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); cc->migrate_pfn = low_pfn; return ret; } /** * isolate_migratepages_range() - isolate migrate-able pages in a PFN range * @cc: Compaction control structure. * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * * Returns -EAGAIN when contented, -EINTR in case of a signal pending, -ENOMEM * in case we could not allocate a page, or 0. */ int isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn, block_start_pfn, block_end_pfn; int ret = 0; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { block_end_pfn = min(block_end_pfn, end_pfn); if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone)) continue; ret = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); if (ret) break; if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } return ret; } #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION static bool suitable_migration_source(struct compact_control *cc, struct page *page) { int block_mt; if (pageblock_skip_persistent(page)) return false; if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) return true; block_mt = get_pageblock_migratetype(page); if (cc->migratetype == MIGRATE_MOVABLE) return is_migrate_movable(block_mt); else return block_mt == cc->migratetype; } /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct compact_control *cc, struct page *page) { /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { int order = cc->order > 0 ? cc->order : pageblock_order; /* * We are checking page_order without zone->lock taken. But * the only small danger is that we skip a potentially suitable * pageblock, so it's not worth to check order for valid range. */ if (buddy_order_unsafe(page) >= order) return false; } if (cc->ignore_block_suitable) return true; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ if (is_migrate_movable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ return false; } static inline unsigned int freelist_scan_limit(struct compact_control *cc) { unsigned short shift = BITS_PER_LONG - 1; return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1; } /* * Test whether the free scanner has reached the same or lower pageblock than * the migration scanner, and compaction should thus terminate. */ static inline bool compact_scanners_met(struct compact_control *cc) { return (cc->free_pfn >> pageblock_order) <= (cc->migrate_pfn >> pageblock_order); } /* * Used when scanning for a suitable migration target which scans freelists * in reverse. Reorders the list such as the unscanned pages are scanned * first on the next iteration of the free scanner */ static void move_freelist_head(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); if (!list_is_first(&freepage->buddy_list, freelist)) { list_cut_before(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } /* * Similar to move_freelist_head except used by the migration scanner * when scanning forward. It's possible for these list operations to * move against each other if they search the free list exactly in * lockstep. */ static void move_freelist_tail(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); if (!list_is_last(&freepage->buddy_list, freelist)) { list_cut_position(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } static void fast_isolate_around(struct compact_control *cc, unsigned long pfn) { unsigned long start_pfn, end_pfn; struct page *page; /* Do not search around if there are enough pages already */ if (cc->nr_freepages >= cc->nr_migratepages) return; /* Minimise scanning during async compaction */ if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC) return; /* Pageblock boundaries */ start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn); end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)); page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone); if (!page) return; isolate_freepages_block(cc, &start_pfn, end_pfn, cc->freepages, 1, false); /* Skip this pageblock in the future as it's full or nearly full */ if (start_pfn == end_pfn && !cc->no_set_skip_hint) set_pageblock_skip(page); } /* Search orders in round-robin fashion */ static int next_search_order(struct compact_control *cc, int order) { order--; if (order < 0) order = cc->order - 1; /* Search wrapped around? */ if (order == cc->search_order) { cc->search_order--; if (cc->search_order < 0) cc->search_order = cc->order - 1; return -1; } return order; } static void fast_isolate_freepages(struct compact_control *cc) { unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1); unsigned int nr_scanned = 0, total_isolated = 0; unsigned long low_pfn, min_pfn, highest = 0; unsigned long nr_isolated = 0; unsigned long distance; struct page *page = NULL; bool scan_start = false; int order; /* Full compaction passes in a negative order */ if (cc->order <= 0) return; /* * If starting the scan, use a deeper search and use the highest * PFN found if a suitable one is not found. */ if (cc->free_pfn >= cc->zone->compact_init_free_pfn) { limit = pageblock_nr_pages >> 1; scan_start = true; } /* * Preferred point is in the top quarter of the scan space but take * a pfn from the top half if the search is problematic. */ distance = (cc->free_pfn - cc->migrate_pfn); low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2)); min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1)); if (WARN_ON_ONCE(min_pfn > low_pfn)) low_pfn = min_pfn; /* * Search starts from the last successful isolation order or the next * order to search after a previous failure */ cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order); for (order = cc->search_order; !page && order >= 0; order = next_search_order(cc, order)) { struct free_area *area = &cc->zone->free_area[order]; struct list_head *freelist; struct page *freepage; unsigned long flags; unsigned int order_scanned = 0; unsigned long high_pfn = 0; if (!area->nr_free) continue; spin_lock_irqsave(&cc->zone->lock, flags); freelist = &area->free_list[MIGRATE_MOVABLE]; list_for_each_entry_reverse(freepage, freelist, buddy_list) { unsigned long pfn; order_scanned++; nr_scanned++; pfn = page_to_pfn(freepage); if (pfn >= highest) highest = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn); if (pfn >= low_pfn) { cc->fast_search_fail = 0; cc->search_order = order; page = freepage; break; } if (pfn >= min_pfn && pfn > high_pfn) { high_pfn = pfn; /* Shorten the scan if a candidate is found */ limit >>= 1; } if (order_scanned >= limit) break; } /* Use a maximum candidate pfn if a preferred one was not found */ if (!page && high_pfn) { page = pfn_to_page(high_pfn); /* Update freepage for the list reorder below */ freepage = page; } /* Reorder to so a future search skips recent pages */ move_freelist_head(freelist, freepage); /* Isolate the page if available */ if (page) { if (__isolate_free_page(page, order)) { set_page_private(page, order); nr_isolated = 1 << order; nr_scanned += nr_isolated - 1; total_isolated += nr_isolated; cc->nr_freepages += nr_isolated; list_add_tail(&page->lru, &cc->freepages[order]); count_compact_events(COMPACTISOLATED, nr_isolated); } else { /* If isolation fails, abort the search */ order = cc->search_order + 1; page = NULL; } } spin_unlock_irqrestore(&cc->zone->lock, flags); /* Skip fast search if enough freepages isolated */ if (cc->nr_freepages >= cc->nr_migratepages) break; /* * Smaller scan on next order so the total scan is related * to freelist_scan_limit. */ if (order_scanned >= limit) limit = max(1U, limit >> 1); } trace_mm_compaction_fast_isolate_freepages(min_pfn, cc->free_pfn, nr_scanned, total_isolated); if (!page) { cc->fast_search_fail++; if (scan_start) { /* * Use the highest PFN found above min. If one was * not found, be pessimistic for direct compaction * and use the min mark. */ if (highest >= min_pfn) { page = pfn_to_page(highest); cc->free_pfn = highest; } else { if (cc->direct_compaction && pfn_valid(min_pfn)) { page = pageblock_pfn_to_page(min_pfn, min(pageblock_end_pfn(min_pfn), zone_end_pfn(cc->zone)), cc->zone); if (page && !suitable_migration_target(cc, page)) page = NULL; cc->free_pfn = min_pfn; } } } } if (highest && highest >= cc->zone->compact_cached_free_pfn) { highest -= pageblock_nr_pages; cc->zone->compact_cached_free_pfn = highest; } cc->total_free_scanned += nr_scanned; if (!page) return; low_pfn = page_to_pfn(page); fast_isolate_around(cc, low_pfn); } /* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. */ static void isolate_freepages(struct compact_control *cc) { struct zone *zone = cc->zone; struct page *page; unsigned long block_start_pfn; /* start of current pageblock */ unsigned long isolate_start_pfn; /* exact pfn we start at */ unsigned long block_end_pfn; /* end of current pageblock */ unsigned long low_pfn; /* lowest pfn scanner is able to scan */ unsigned int stride; /* Try a small search of the free lists for a candidate */ fast_isolate_freepages(cc); if (cc->nr_freepages) return; /* * Initialise the free scanner. The starting point is where we last * successfully isolated from, zone-cached value, or the end of the * zone when isolating for the first time. For looping we also need * this pfn aligned down to the pageblock boundary, because we do * block_start_pfn -= pageblock_nr_pages in the for loop. * For ending point, take care when isolating in last pageblock of a * zone which ends in the middle of a pageblock. * The low boundary is the end of the pageblock the migration scanner * is using. */ isolate_start_pfn = cc->free_pfn; block_start_pfn = pageblock_start_pfn(isolate_start_pfn); block_end_pfn = min(block_start_pfn + pageblock_nr_pages, zone_end_pfn(zone)); low_pfn = pageblock_end_pfn(cc->migrate_pfn); stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1; /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ for (; block_start_pfn >= low_pfn; block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { unsigned long nr_isolated; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check resched. */ if (!(block_start_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone); if (!page) { unsigned long next_pfn; next_pfn = skip_offline_sections_reverse(block_start_pfn); if (next_pfn) block_start_pfn = max(next_pfn, low_pfn); continue; } /* Check the block is suitable for migration */ if (!suitable_migration_target(cc, page)) continue; /* If isolation recently failed, do not retry */ if (!isolation_suitable(cc, page)) continue; /* Found a block suitable for isolating free pages from. */ nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, cc->freepages, stride, false); /* Update the skip hint if the full pageblock was scanned */ if (isolate_start_pfn == block_end_pfn) update_pageblock_skip(cc, page, block_start_pfn - pageblock_nr_pages); /* Are enough freepages isolated? */ if (cc->nr_freepages >= cc->nr_migratepages) { if (isolate_start_pfn >= block_end_pfn) { /* * Restart at previous pageblock if more * freepages can be isolated next time. */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; } break; } else if (isolate_start_pfn < block_end_pfn) { /* * If isolation failed early, do not continue * needlessly. */ break; } /* Adjust stride depending on isolation */ if (nr_isolated) { stride = 1; continue; } stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1); } /* * Record where the free scanner will restart next time. Either we * broke from the loop and set isolate_start_pfn based on the last * call to isolate_freepages_block(), or we met the migration scanner * and the loop terminated due to isolate_start_pfn < low_pfn */ cc->free_pfn = isolate_start_pfn; } /* * This is a migrate-callback that "allocates" freepages by taking pages * from the isolated freelists in the block we are migrating to. */ static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; struct folio *dst; int order = folio_order(src); bool has_isolated_pages = false; int start_order; struct page *freepage; unsigned long size; again: for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++) if (!list_empty(&cc->freepages[start_order])) break; /* no free pages in the list */ if (start_order == NR_PAGE_ORDERS) { if (has_isolated_pages) return NULL; isolate_freepages(cc); has_isolated_pages = true; goto again; } freepage = list_first_entry(&cc->freepages[start_order], struct page, lru); size = 1 << start_order; list_del(&freepage->lru); while (start_order > order) { start_order--; size >>= 1; list_add(&freepage[size].lru, &cc->freepages[start_order]); set_page_private(&freepage[size], start_order); } dst = (struct folio *)freepage; post_alloc_hook(&dst->page, order, __GFP_MOVABLE); if (order) prep_compound_page(&dst->page, order); cc->nr_freepages -= 1 << order; cc->nr_migratepages -= 1 << order; return page_rmappable_folio(&dst->page); } static struct folio *compaction_alloc(struct folio *src, unsigned long data) { return alloc_hooks(compaction_alloc_noprof(src, data)); } /* * This is a migrate-callback that "frees" freepages back to the isolated * freelist. All pages on the freelist are from the same zone, so there is no * special handling needed for NUMA. */ static void compaction_free(struct folio *dst, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; int order = folio_order(dst); struct page *page = &dst->page; if (folio_put_testzero(dst)) { free_pages_prepare(page, order); list_add(&dst->lru, &cc->freepages[order]); cc->nr_freepages += 1 << order; } cc->nr_migratepages += 1 << order; /* * someone else has referenced the page, we cannot take it back to our * free list. */ } /* possible outcome of isolate_migratepages */ typedef enum { ISOLATE_ABORT, /* Abort compaction now */ ISOLATE_NONE, /* No pages isolated, continue scanning */ ISOLATE_SUCCESS, /* Pages isolated, migrate */ } isolate_migrate_t; /* * Allow userspace to control policy on scanning the unevictable LRU for * compactable pages. */ static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; /* * Tunable for proactive compaction. It determines how * aggressively the kernel should compact memory in the * background. It takes values in the range [0, 100]. */ static unsigned int __read_mostly sysctl_compaction_proactiveness = 20; static int sysctl_extfrag_threshold = 500; static int __read_mostly sysctl_compact_memory; static inline void update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) { if (cc->fast_start_pfn == ULONG_MAX) return; if (!cc->fast_start_pfn) cc->fast_start_pfn = pfn; cc->fast_start_pfn = min(cc->fast_start_pfn, pfn); } static inline unsigned long reinit_migrate_pfn(struct compact_control *cc) { if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX) return cc->migrate_pfn; cc->migrate_pfn = cc->fast_start_pfn; cc->fast_start_pfn = ULONG_MAX; return cc->migrate_pfn; } /* * Briefly search the free lists for a migration source that already has * some free pages to reduce the number of pages that need migration * before a pageblock is free. */ static unsigned long fast_find_migrateblock(struct compact_control *cc) { unsigned int limit = freelist_scan_limit(cc); unsigned int nr_scanned = 0; unsigned long distance; unsigned long pfn = cc->migrate_pfn; unsigned long high_pfn; int order; bool found_block = false; /* Skip hints are relied on to avoid repeats on the fast search */ if (cc->ignore_skip_hint) return pfn; /* * If the pageblock should be finished then do not select a different * pageblock. */ if (cc->finish_pageblock) return pfn; /* * If the migrate_pfn is not at the start of a zone or the start * of a pageblock then assume this is a continuation of a previous * scan restarted due to COMPACT_CLUSTER_MAX. */ if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn)) return pfn; /* * For smaller orders, just linearly scan as the number of pages * to migrate should be relatively small and does not necessarily * justify freeing up a large block for a small allocation. */ if (cc->order <= PAGE_ALLOC_COSTLY_ORDER) return pfn; /* * Only allow kcompactd and direct requests for movable pages to * quickly clear out a MOVABLE pageblock for allocation. This * reduces the risk that a large movable pageblock is freed for * an unmovable/reclaimable small allocation. */ if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) return pfn; /* * When starting the migration scanner, pick any pageblock within the * first half of the search space. Otherwise try and pick a pageblock * within the first eighth to reduce the chances that a migration * target later becomes a source. */ distance = (cc->free_pfn - cc->migrate_pfn) >> 1; if (cc->migrate_pfn != cc->zone->zone_start_pfn) distance >>= 2; high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance); for (order = cc->order - 1; order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit; order--) { struct free_area *area = &cc->zone->free_area[order]; struct list_head *freelist; unsigned long flags; struct page *freepage; if (!area->nr_free) continue; spin_lock_irqsave(&cc->zone->lock, flags); freelist = &area->free_list[MIGRATE_MOVABLE]; list_for_each_entry(freepage, freelist, buddy_list) { unsigned long free_pfn; if (nr_scanned++ >= limit) { move_freelist_tail(freelist, freepage); break; } free_pfn = page_to_pfn(freepage); if (free_pfn < high_pfn) { /* * Avoid if skipped recently. Ideally it would * move to the tail but even safe iteration of * the list assumes an entry is deleted, not * reordered. */ if (get_pageblock_skip(freepage)) continue; /* Reorder to so a future search skips recent pages */ move_freelist_tail(freelist, freepage); update_fast_start_pfn(cc, free_pfn); pfn = pageblock_start_pfn(free_pfn); if (pfn < cc->zone->zone_start_pfn) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; break; } } spin_unlock_irqrestore(&cc->zone->lock, flags); } cc->total_migrate_scanned += nr_scanned; /* * If fast scanning failed then use a cached entry for a page block * that had free pages as the basis for starting a linear scan. */ if (!found_block) { cc->fast_search_fail++; pfn = reinit_migrate_pfn(cc); } return pfn; } /* * Isolate all pages that can be migrated from the first suitable block, * starting at the block pointed to by the migrate scanner pfn within * compact_control. */ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) { unsigned long block_start_pfn; unsigned long block_end_pfn; unsigned long low_pfn; struct page *page; const isolate_mode_t isolate_mode = (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | (cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0); bool fast_find_block; /* * Start at where we last stopped, or beginning of the zone as * initialized by compact_zone(). The first failure will use * the lowest PFN as the starting point for linear scanning. */ low_pfn = fast_find_migrateblock(cc); block_start_pfn = pageblock_start_pfn(low_pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; /* * fast_find_migrateblock() has already ensured the pageblock is not * set with a skipped flag, so to avoid the isolation_suitable check * below again, check whether the fast search was successful. */ fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail; /* Only scan within a pageblock boundary */ block_end_pfn = pageblock_end_pfn(low_pfn); /* * Iterate over whole pageblocks until we find the first suitable. * Do not cross the free scanner. */ for (; block_end_pfn <= cc->free_pfn; fast_find_block = false, cc->migrate_pfn = low_pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* * This can potentially iterate a massively long zone with * many pageblocks unsuitable, so periodically check if we * need to schedule. */ if (!(low_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone); if (!page) { unsigned long next_pfn; next_pfn = skip_offline_sections(block_start_pfn); if (next_pfn) block_end_pfn = min(next_pfn, cc->free_pfn); continue; } /* * If isolation recently failed, do not retry. Only check the * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock * to be visited multiple times. Assume skip was checked * before making it "skip" so other compaction instances do * not scan the same block. */ if ((pageblock_aligned(low_pfn) || low_pfn == cc->zone->zone_start_pfn) && !fast_find_block && !isolation_suitable(cc, page)) continue; /* * For async direct compaction, only scan the pageblocks of the * same migratetype without huge pages. Async direct compaction * is optimistic to see if the minimum amount of work satisfies * the allocation. The cached PFN is updated as it's possible * that all remaining blocks between source and target are * unsuitable and the compaction scanners fail to meet. */ if (!suitable_migration_source(cc, page)) { update_cached_migrate(cc, block_end_pfn); continue; } /* Perform the isolation */ if (isolate_migratepages_block(cc, low_pfn, block_end_pfn, isolate_mode)) return ISOLATE_ABORT; /* * Either we isolated something and proceed with migration. Or * we failed and compact_zone should decide if we should * continue or not. */ break; } return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } /* * Determine whether kswapd is (or recently was!) running on this node. * * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't * zero it. */ static bool kswapd_is_running(pg_data_t *pgdat) { bool running; pgdat_kswapd_lock(pgdat); running = pgdat->kswapd && task_is_running(pgdat->kswapd); pgdat_kswapd_unlock(pgdat); return running; } /* * A zone's fragmentation score is the external fragmentation wrt to the * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100]. */ static unsigned int fragmentation_score_zone(struct zone *zone) { return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER); } /* * A weighted zone's fragmentation score is the external fragmentation * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It * returns a value in the range [0, 100]. * * The scaling factor ensures that proactive compaction focuses on larger * zones like ZONE_NORMAL, rather than smaller, specialized zones like * ZONE_DMA32. For smaller zones, the score value remains close to zero, * and thus never exceeds the high threshold for proactive compaction. */ static unsigned int fragmentation_score_zone_weighted(struct zone *zone) { unsigned long score; score = zone->present_pages * fragmentation_score_zone(zone); return div64_ul(score, zone->zone_pgdat->node_present_pages + 1); } /* * The per-node proactive (background) compaction process is started by its * corresponding kcompactd thread when the node's fragmentation score * exceeds the high threshold. The compaction process remains active till * the node's score falls below the low threshold, or one of the back-off * conditions is met. */ static unsigned int fragmentation_score_node(pg_data_t *pgdat) { unsigned int score = 0; int zoneid; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { struct zone *zone; zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; score += fragmentation_score_zone_weighted(zone); } return score; } static unsigned int fragmentation_score_wmark(bool low) { unsigned int wmark_low; /* * Cap the low watermark to avoid excessive compaction * activity in case a user sets the proactiveness tunable * close to 100 (maximum). */ wmark_low = max(100U - sysctl_compaction_proactiveness, 5U); return low ? wmark_low : min(wmark_low + 10, 100U); } static bool should_proactive_compact_node(pg_data_t *pgdat) { int wmark_high; if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat)) return false; wmark_high = fragmentation_score_wmark(false); return fragmentation_score_node(pgdat) > wmark_high; } static enum compact_result __compact_finished(struct compact_control *cc) { unsigned int order; const int migratetype = cc->migratetype; int ret; /* Compaction run completes if the migrate and free scanner meet */ if (compact_scanners_met(cc)) { /* Let the next compaction start anew. */ reset_cached_positions(cc->zone); /* * Mark that the PG_migrate_skip information should be cleared * by kswapd when it goes to sleep. kcompactd does not set the * flag itself as the decision to be clear should be directly * based on an allocation request. */ if (cc->direct_compaction) cc->zone->compact_blockskip_flush = true; if (cc->whole_zone) return COMPACT_COMPLETE; else return COMPACT_PARTIAL_SKIPPED; } if (cc->proactive_compaction) { int score, wmark_low; pg_data_t *pgdat; pgdat = cc->zone->zone_pgdat; if (kswapd_is_running(pgdat)) return COMPACT_PARTIAL_SKIPPED; score = fragmentation_score_zone(cc->zone); wmark_low = fragmentation_score_wmark(true); if (score > wmark_low) ret = COMPACT_CONTINUE; else ret = COMPACT_SUCCESS; goto out; } if (is_via_compact_memory(cc->order)) return COMPACT_CONTINUE; /* * Always finish scanning a pageblock to reduce the possibility of * fallbacks in the future. This is particularly important when * migration source is unmovable/reclaimable but it's not worth * special casing. */ if (!pageblock_aligned(cc->migrate_pfn)) return COMPACT_CONTINUE; /* Direct compactor: Is a suitable page free? */ ret = COMPACT_NO_SUITABLE_PAGE; for (order = cc->order; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &cc->zone->free_area[order]; bool can_steal; /* Job done if page is free of the right migratetype */ if (!free_area_empty(area, migratetype)) return COMPACT_SUCCESS; #ifdef CONFIG_CMA /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ if (migratetype == MIGRATE_MOVABLE && !free_area_empty(area, MIGRATE_CMA)) return COMPACT_SUCCESS; #endif /* * Job done if allocation would steal freepages from * other migratetype buddy lists. */ if (find_suitable_fallback(area, order, migratetype, true, &can_steal) != -1) /* * Movable pages are OK in any pageblock. If we are * stealing for a non-movable allocation, make sure * we finish compacting the current pageblock first * (which is assured by the above migrate_pfn align * check) so it is as free as possible and we won't * have to steal another one soon. */ return COMPACT_SUCCESS; } out: if (cc->contended || fatal_signal_pending(current)) ret = COMPACT_CONTENDED; return ret; } static enum compact_result compact_finished(struct compact_control *cc) { int ret; ret = __compact_finished(cc); trace_mm_compaction_finished(cc->zone, cc->order, ret); if (ret == COMPACT_NO_SUITABLE_PAGE) ret = COMPACT_CONTINUE; return ret; } static bool __compaction_suitable(struct zone *zone, int order, int highest_zoneidx, unsigned long wmark_target) { unsigned long watermark; /* * Watermarks for order-0 must be met for compaction to be able to * isolate free pages for migration targets. This means that the * watermark and alloc_flags have to match, or be more pessimistic than * the check in __isolate_free_page(). We don't use the direct * compactor's alloc_flags, as they are not relevant for freepage * isolation. We however do use the direct compactor's highest_zoneidx * to skip over zones where lowmem reserves would prevent allocation * even if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. * ALLOC_CMA is used, as pages in CMA pageblocks are considered * suitable migration targets */ watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, ALLOC_CMA, wmark_target); } /* * compaction_suitable: Is this suitable to run compaction on this zone now? */ bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx) { enum compact_result compact_result; bool suitable; suitable = __compaction_suitable(zone, order, highest_zoneidx, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation * * index of -1000 would imply allocations might succeed depending on * watermarks, but we already failed the high-order watermark check * index towards 0 implies failure is due to lack of memory * index towards 1000 implies failure is due to fragmentation * * Only compact if a failure would be due to fragmentation. Also * ignore fragindex for non-costly orders where the alternative to * a successful reclaim/compaction is OOM. Fragindex and the * vm.extfrag_threshold sysctl is meant as a heuristic to prevent * excessive compaction for costly orders, but it should not be at the * expense of system stability. */ if (suitable) { compact_result = COMPACT_CONTINUE; if (order > PAGE_ALLOC_COSTLY_ORDER) { int fragindex = fragmentation_index(zone, order); if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) { suitable = false; compact_result = COMPACT_NOT_SUITABLE_ZONE; } } } else { compact_result = COMPACT_SKIPPED; } trace_mm_compaction_suitable(zone, order, compact_result); return suitable; } bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags) { struct zone *zone; struct zoneref *z; /* * Make sure at least one zone would pass __compaction_suitable if we continue * retrying the reclaim. */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->highest_zoneidx, ac->nodemask) { unsigned long available; /* * Do not consider all the reclaimable memory because we do not * want to trash just for a single high order allocation which * is even not guaranteed to appear even if __compaction_suitable * is happy about the watermark check. */ available = zone_reclaimable_pages(zone) / order; available += zone_page_state_snapshot(zone, NR_FREE_PAGES); if (__compaction_suitable(zone, order, ac->highest_zoneidx, available)) return true; } return false; } /* * Should we do compaction for target allocation order. * Return COMPACT_SUCCESS if allocation for target order can be already * satisfied * Return COMPACT_SKIPPED if compaction for target order is likely to fail * Return COMPACT_CONTINUE if compaction for target order should be ran */ static enum compact_result compaction_suit_allocation_order(struct zone *zone, unsigned int order, int highest_zoneidx, unsigned int alloc_flags) { unsigned long watermark; watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, alloc_flags)) return COMPACT_SUCCESS; if (!compaction_suitable(zone, order, highest_zoneidx)) return COMPACT_SKIPPED; return COMPACT_CONTINUE; } static enum compact_result compact_zone(struct compact_control *cc, struct capture_control *capc) { enum compact_result ret; unsigned long start_pfn = cc->zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(cc->zone); unsigned long last_migrated_pfn; const bool sync = cc->mode != MIGRATE_ASYNC; bool update_cached; unsigned int nr_succeeded = 0, nr_migratepages; int order; /* * These counters track activities during zone compaction. Initialize * them before compacting a new zone. */ cc->total_migrate_scanned = 0; cc->total_free_scanned = 0; cc->nr_migratepages = 0; cc->nr_freepages = 0; for (order = 0; order < NR_PAGE_ORDERS; order++) INIT_LIST_HEAD(&cc->freepages[order]); INIT_LIST_HEAD(&cc->migratepages); cc->migratetype = gfp_migratetype(cc->gfp_mask); if (!is_via_compact_memory(cc->order)) { ret = compaction_suit_allocation_order(cc->zone, cc->order, cc->highest_zoneidx, cc->alloc_flags); if (ret != COMPACT_CONTINUE) return ret; } /* * Clear pageblock skip if there were failures recently and compaction * is about to be retried after being deferred. */ if (compaction_restarting(cc->zone, cc->order)) __reset_isolation_suitable(cc->zone); /* * Setup to move all movable pages to the end of the zone. Used cached * information on where the scanners should start (unless we explicitly * want to compact the whole zone), but check that it is initialised * by ensuring the values are within zone boundaries. */ cc->fast_start_pfn = 0; if (cc->whole_zone) { cc->migrate_pfn = start_pfn; cc->free_pfn = pageblock_start_pfn(end_pfn - 1); } else { cc->migrate_pfn = cc->zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = cc->zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { cc->free_pfn = pageblock_start_pfn(end_pfn - 1); cc->zone->compact_cached_free_pfn = cc->free_pfn; } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { cc->migrate_pfn = start_pfn; cc->zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn) cc->whole_zone = true; } last_migrated_pfn = 0; /* * Migrate has separate cached PFNs for ASYNC and SYNC* migration on * the basis that some migrations will fail in ASYNC mode. However, * if the cached PFNs match and pageblocks are skipped due to having * no isolation candidates, then the sync state does not matter. * Until a pageblock with isolation candidates is found, keep the * cached PFNs in sync to avoid revisiting the same blocks. */ update_cached = !sync && cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1]; trace_mm_compaction_begin(cc, start_pfn, end_pfn, sync); /* lru_add_drain_all could be expensive with involving other CPUs */ lru_add_drain(); while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) { int err; unsigned long iteration_start_pfn = cc->migrate_pfn; /* * Avoid multiple rescans of the same pageblock which can * happen if a page cannot be isolated (dirty/writeback in * async mode) or if the migrated pages are being allocated * before the pageblock is cleared. The first rescan will * capture the entire pageblock for migration. If it fails, * it'll be marked skip and scanning will proceed as normal. */ cc->finish_pageblock = false; if (pageblock_start_pfn(last_migrated_pfn) == pageblock_start_pfn(iteration_start_pfn)) { cc->finish_pageblock = true; } rescan: switch (isolate_migratepages(cc)) { case ISOLATE_ABORT: ret = COMPACT_CONTENDED; putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; goto out; case ISOLATE_NONE: if (update_cached) { cc->zone->compact_cached_migrate_pfn[1] = cc->zone->compact_cached_migrate_pfn[0]; } /* * We haven't isolated and migrated anything, but * there might still be unflushed migrations from * previous cc->order aligned block. */ goto check_drain; case ISOLATE_SUCCESS: update_cached = false; last_migrated_pfn = max(cc->zone->zone_start_pfn, pageblock_start_pfn(cc->migrate_pfn - 1)); } /* * Record the number of pages to migrate since the * compaction_alloc/free() will update cc->nr_migratepages * properly. */ nr_migratepages = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION, &nr_succeeded); trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded); /* All pages were either migrated or will be released */ cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it */ if (err == -ENOMEM && !compact_scanners_met(cc)) { ret = COMPACT_CONTENDED; goto out; } /* * If an ASYNC or SYNC_LIGHT fails to migrate a page * within the pageblock_order-aligned block and * fast_find_migrateblock may be used then scan the * remainder of the pageblock. This will mark the * pageblock "skip" to avoid rescanning in the near * future. This will isolate more pages than necessary * for the request but avoid loops due to * fast_find_migrateblock revisiting blocks that were * recently partially scanned. */ if (!pageblock_aligned(cc->migrate_pfn) && !cc->ignore_skip_hint && !cc->finish_pageblock && (cc->mode < MIGRATE_SYNC)) { cc->finish_pageblock = true; /* * Draining pcplists does not help THP if * any page failed to migrate. Even after * drain, the pageblock will not be free. */ if (cc->order == COMPACTION_HPAGE_ORDER) last_migrated_pfn = 0; goto rescan; } } /* Stop if a page has been captured */ if (capc && capc->page) { ret = COMPACT_SUCCESS; break; } check_drain: /* * Has the migration scanner moved away from the previous * cc->order aligned block where we migrated from? If yes, * flush the pages that were freed, so that they can merge and * compact_finished() can detect immediately if allocation * would succeed. */ if (cc->order > 0 && last_migrated_pfn) { unsigned long current_block_start = block_start_pfn(cc->migrate_pfn, cc->order); if (last_migrated_pfn < current_block_start) { lru_add_drain_cpu_zone(cc->zone); /* No more flushing until we migrate again */ last_migrated_pfn = 0; } } } out: /* * Release free pages and update where the free scanner should restart, * so we don't leave any returned pages behind in the next attempt. */ if (cc->nr_freepages > 0) { unsigned long free_pfn = release_free_list(cc->freepages); cc->nr_freepages = 0; VM_BUG_ON(free_pfn == 0); /* The cached pfn is always the first in a pageblock */ free_pfn = pageblock_start_pfn(free_pfn); /* * Only go back, not forward. The cached pfn might have been * already reset to zone end in compact_finished() */ if (free_pfn > cc->zone->compact_cached_free_pfn) cc->zone->compact_cached_free_pfn = free_pfn; } count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned); count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned); trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret); VM_BUG_ON(!list_empty(&cc->migratepages)); return ret; } static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, unsigned int alloc_flags, int highest_zoneidx, struct page **capture) { enum compact_result ret; struct compact_control cc = { .order = order, .search_order = order, .gfp_mask = gfp_mask, .zone = zone, .mode = (prio == COMPACT_PRIO_ASYNC) ? MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT, .alloc_flags = alloc_flags, .highest_zoneidx = highest_zoneidx, .direct_compaction = true, .whole_zone = (prio == MIN_COMPACT_PRIORITY), .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; struct capture_control capc = { .cc = &cc, .page = NULL, }; /* * Make sure the structs are really initialized before we expose the * capture control, in case we are interrupted and the interrupt handler * frees a page. */ barrier(); WRITE_ONCE(current->capture_control, &capc); ret = compact_zone(&cc, &capc); /* * Make sure we hide capture control first before we read the captured * page pointer, otherwise an interrupt could free and capture a page * and we would leak it. */ WRITE_ONCE(current->capture_control, NULL); *capture = READ_ONCE(capc.page); /* * Technically, it is also possible that compaction is skipped but * the page is still captured out of luck(IRQ came and freed the page). * Returning COMPACT_SUCCESS in such cases helps in properly accounting * the COMPACT[STALL|FAIL] when compaction is skipped. */ if (*capture) ret = COMPACT_SUCCESS; return ret; } /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation * @order: The order of the current allocation * @alloc_flags: The allocation flags of the current allocation * @ac: The context of current allocation * @prio: Determines how hard direct compaction should try to succeed * @capture: Pointer to free page created by compaction will be stored here * * This is the main entry point for direct page compaction. */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->highest_zoneidx, ac->nodemask) { enum compact_result status; if (prio > MIN_COMPACT_PRIORITY && compaction_deferred(zone, order)) { rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); continue; } status = compact_zone_order(zone, order, gfp_mask, prio, alloc_flags, ac->highest_zoneidx, capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ if (status == COMPACT_SUCCESS) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller * will repeat this with true if allocation indeed * succeeds in this zone. */ compaction_defer_reset(zone, order, false); break; } if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE || status == COMPACT_PARTIAL_SKIPPED)) /* * We think that allocation won't succeed in this zone * so we defer compaction there. If it ends up * succeeding after all, it will be reset. */ defer_compaction(zone, order); /* * We might have stopped compacting due to need_resched() in * async compaction, or due to a fatal signal detected. In that * case do not try further zones */ if ((prio == COMPACT_PRIO_ASYNC && need_resched()) || fatal_signal_pending(current)) break; } return rc; } /* * compact_node() - compact all zones within a node * @pgdat: The node page data * @proactive: Whether the compaction is proactive * * For proactive compaction, compact till each zone's fragmentation score * reaches within proactive compaction thresholds (as determined by the * proactiveness tunable), it is possible that the function returns before * reaching score targets due to various back-off conditions, such as, * contention on per-node or per-zone locks. */ static int compact_node(pg_data_t *pgdat, bool proactive) { int zoneid; struct zone *zone; struct compact_control cc = { .order = -1, .mode = proactive ? MIGRATE_SYNC_LIGHT : MIGRATE_SYNC, .ignore_skip_hint = true, .whole_zone = true, .gfp_mask = GFP_KERNEL, .proactive_compaction = proactive, }; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; if (fatal_signal_pending(current)) return -EINTR; cc.zone = zone; compact_zone(&cc, NULL); if (proactive) { count_compact_events(KCOMPACTD_MIGRATE_SCANNED, cc.total_migrate_scanned); count_compact_events(KCOMPACTD_FREE_SCANNED, cc.total_free_scanned); } } return 0; } /* Compact all zones of all nodes in the system */ static int compact_nodes(void) { int ret, nid; /* Flush pending updates to the LRU lists */ lru_add_drain_all(); for_each_online_node(nid) { ret = compact_node(NODE_DATA(nid), false); if (ret) return ret; } return 0; } static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc, nid; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; if (write && sysctl_compaction_proactiveness) { for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); if (pgdat->proactive_compact_trigger) continue; pgdat->proactive_compact_trigger = true; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, -1, pgdat->nr_zones - 1); wake_up_interruptible(&pgdat->kcompactd_wait); } } return 0; } /* * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory */ static int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, length, ppos); if (ret) return ret; if (sysctl_compact_memory != 1) return -EINVAL; if (write) ret = compact_nodes(); return ret; } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) static ssize_t compact_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int nid = dev->id; if (nid >= 0 && nid < nr_node_ids && node_online(nid)) { /* Flush pending updates to the LRU lists */ lru_add_drain_all(); compact_node(NODE_DATA(nid), false); } return count; } static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { return device_create_file(&node->dev, &dev_attr_compact); } void compaction_unregister_node(struct node *node) { device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ static inline bool kcompactd_work_requested(pg_data_t *pgdat) { return pgdat->kcompactd_max_order > 0 || kthread_should_stop() || pgdat->proactive_compact_trigger; } static bool kcompactd_node_suitable(pg_data_t *pgdat) { int zoneid; struct zone *zone; enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; enum compact_result ret; for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; ret = compaction_suit_allocation_order(zone, pgdat->kcompactd_max_order, highest_zoneidx, ALLOC_WMARK_MIN); if (ret == COMPACT_CONTINUE) return true; } return false; } static void kcompactd_do_work(pg_data_t *pgdat) { /* * With no special task, compact all zones so that a page of requested * order is allocatable. */ int zoneid; struct zone *zone; struct compact_control cc = { .order = pgdat->kcompactd_max_order, .search_order = pgdat->kcompactd_max_order, .highest_zoneidx = pgdat->kcompactd_highest_zoneidx, .mode = MIGRATE_SYNC_LIGHT, .ignore_skip_hint = false, .gfp_mask = GFP_KERNEL, }; enum compact_result ret; trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.highest_zoneidx); count_compact_event(KCOMPACTD_WAKE); for (zoneid = 0; zoneid <= cc.highest_zoneidx; zoneid++) { int status; zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; if (compaction_deferred(zone, cc.order)) continue; ret = compaction_suit_allocation_order(zone, cc.order, zoneid, ALLOC_WMARK_MIN); if (ret != COMPACT_CONTINUE) continue; if (kthread_should_stop()) return; cc.zone = zone; status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); } else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) { /* * Buddy pages may become stranded on pcps that could * otherwise coalesce on the zone's free area for * order >= cc.order. This is ratelimited by the * upcoming deferral. */ drain_all_pages(zone); /* * We use sync migration mode here, so we defer like * sync direct compaction does. */ defer_compaction(zone, cc.order); } count_compact_events(KCOMPACTD_MIGRATE_SCANNED, cc.total_migrate_scanned); count_compact_events(KCOMPACTD_FREE_SCANNED, cc.total_free_scanned); } /* * Regardless of success, we are done until woken up next. But remember * the requested order/highest_zoneidx in case it was higher/tighter * than our current ones */ if (pgdat->kcompactd_max_order <= cc.order) pgdat->kcompactd_max_order = 0; if (pgdat->kcompactd_highest_zoneidx >= cc.highest_zoneidx) pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; } void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) { if (!order) return; if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx) pgdat->kcompactd_highest_zoneidx = highest_zoneidx; /* * Pairs with implicit barrier in wait_event_freezable() * such that wakeups are not missed. */ if (!wq_has_sleeper(&pgdat->kcompactd_wait)) return; if (!kcompactd_node_suitable(pgdat)) return; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order, highest_zoneidx); wake_up_interruptible(&pgdat->kcompactd_wait); } /* * The background compaction daemon, started as a kernel thread * from the init process. */ static int kcompactd(void *p) { pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); set_freezable(); pgdat->kcompactd_max_order = 0; pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { unsigned long pflags; /* * Avoid the unnecessary wakeup for proactive compaction * when it is disabled. */ if (!sysctl_compaction_proactiveness) timeout = MAX_SCHEDULE_TIMEOUT; trace_mm_compaction_kcompactd_sleep(pgdat->node_id); if (wait_event_freezable_timeout(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat), timeout) && !pgdat->proactive_compact_trigger) { psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); psi_memstall_leave(&pflags); /* * Reset the timeout value. The defer timeout from * proactive compaction is lost here but that is fine * as the condition of the zone changing substantionally * then carrying on with the previous defer interval is * not useful. */ timeout = default_timeout; continue; } /* * Start the proactive work with default timeout. Based * on the fragmentation score, this timeout is updated. */ timeout = default_timeout; if (should_proactive_compact_node(pgdat)) { unsigned int prev_score, score; prev_score = fragmentation_score_node(pgdat); compact_node(pgdat, true); score = fragmentation_score_node(pgdat); /* * Defer proactive compaction if the fragmentation * score did not go down i.e. no progress made. */ if (unlikely(score >= prev_score)) timeout = default_timeout << COMPACT_MAX_DEFER_SHIFT; } if (unlikely(pgdat->proactive_compact_trigger)) pgdat->proactive_compact_trigger = false; } return 0; } /* * This kcompactd start function will be called by init and node-hot-add. * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added. */ void __meminit kcompactd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); if (pgdat->kcompactd) return; pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid); if (IS_ERR(pgdat->kcompactd)) { pr_err("Failed to start kcompactd on node %d\n", nid); pgdat->kcompactd = NULL; } } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kcompactd_stop(int nid) { struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd; if (kcompactd) { kthread_stop(kcompactd); NODE_DATA(nid)->kcompactd = NULL; } } /* * It's optimal to keep kcompactd on the same CPUs as their memory, but * not required for correctness. So if the last cpu in a node goes * away, we get changed to run anywhere: as the first one comes back, * restore their cpu bindings. */ static int kcompactd_cpu_online(unsigned int cpu) { int nid; for_each_node_state(nid, N_MEMORY) { pg_data_t *pgdat = NODE_DATA(nid); const struct cpumask *mask; mask = cpumask_of_node(pgdat->node_id); if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ if (pgdat->kcompactd) set_cpus_allowed_ptr(pgdat->kcompactd, mask); } return 0; } static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, old; if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) return proc_dointvec_minmax(table, write, buffer, lenp, ppos); old = *(int *)table->data; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret) return ret; if (old != *(int *)table->data) pr_warn_once("sysctl attribute %s changed by %s[%d]\n", table->procname, current->comm, task_pid_nr(current)); return ret; } static struct ctl_table vm_compaction[] = { { .procname = "compact_memory", .data = &sysctl_compact_memory, .maxlen = sizeof(int), .mode = 0200, .proc_handler = sysctl_compaction_handler, }, { .procname = "compaction_proactiveness", .data = &sysctl_compaction_proactiveness, .maxlen = sizeof(sysctl_compaction_proactiveness), .mode = 0644, .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", .data = &sysctl_extfrag_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "compact_unevictable_allowed", .data = &sysctl_compact_unevictable_allowed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_warn_RT_change, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static int __init kcompactd_init(void) { int nid; int ret; ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "mm/compaction:online", kcompactd_cpu_online, NULL); if (ret < 0) { pr_err("kcompactd: failed to register hotplug callbacks.\n"); return ret; } for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); register_sysctl_init("vm", vm_compaction); return 0; } subsys_initcall(kcompactd_init) #endif /* CONFIG_COMPACTION */ |
| 314 311 42 273 276 311 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 564 558 558 11 10 10 560 565 563 279 280 280 651 268 270 268 646 648 648 646 496 643 650 636 635 634 637 | 1 2 3 4 5 6 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/util.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/slab.h> #include <linux/rculist.h> #include "common.h" /* Lock for protecting policy. */ DEFINE_MUTEX(tomoyo_policy_lock); /* Has /sbin/init started? */ bool tomoyo_policy_loaded; /* * Mapping table from "enum tomoyo_mac_index" to * "enum tomoyo_mac_category_index". */ const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_OPEN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CREATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UNLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_GETATTR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RMDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKFIFO] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKSOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_TRUNCATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_SYMLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKBLOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKCHAR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_LINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RENAME] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHMOD] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHOWN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHGRP] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_IOCTL] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHROOT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UMOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE, /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = TOMOYO_MAC_CATEGORY_MISC, }; /** * tomoyo_convert_time - Convert time_t to YYYY/MM/DD hh/mm/ss. * * @time64: Seconds since 1970/01/01 00:00:00. * @stamp: Pointer to "struct tomoyo_time". * * Returns nothing. */ void tomoyo_convert_time(time64_t time64, struct tomoyo_time *stamp) { struct tm tm; time64_to_tm(time64, 0, &tm); stamp->sec = tm.tm_sec; stamp->min = tm.tm_min; stamp->hour = tm.tm_hour; stamp->day = tm.tm_mday; stamp->month = tm.tm_mon + 1; stamp->year = tm.tm_year + 1900; } /** * tomoyo_permstr - Find permission keywords. * * @string: String representation for permissions in foo/bar/buz format. * @keyword: Keyword to find from @string/ * * Returns true if @keyword was found in @string, false otherwise. * * This function assumes that strncmp(w1, w2, strlen(w1)) != 0 if w1 != w2. */ bool tomoyo_permstr(const char *string, const char *keyword) { const char *cp = strstr(string, keyword); if (cp) return cp == string || *(cp - 1) == '/'; return false; } /** * tomoyo_read_token - Read a word from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a word on success, "" otherwise. * * To allow the caller to skip NULL check, this function returns "" rather than * NULL if there is no more words to read. */ char *tomoyo_read_token(struct tomoyo_acl_param *param) { char *pos = param->data; char *del = strchr(pos, ' '); if (del) *del++ = '\0'; else del = pos + strlen(pos); param->data = del; return pos; } static bool tomoyo_correct_path2(const char *filename, const size_t len); /** * tomoyo_get_domainname - Read a domainname from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a domainname on success, NULL otherwise. */ const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param) { char *start = param->data; char *pos = start; while (*pos) { if (*pos++ != ' ' || tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos)) continue; *(pos - 1) = '\0'; break; } param->data = pos; if (tomoyo_correct_domain(start)) return tomoyo_get_name(start); return NULL; } /** * tomoyo_parse_ulong - Parse an "unsigned long" value. * * @result: Pointer to "unsigned long". * @str: Pointer to string to parse. * * Returns one of values in "enum tomoyo_value_type". * * The @src is updated to point the first character after the value * on success. */ u8 tomoyo_parse_ulong(unsigned long *result, char **str) { const char *cp = *str; char *ep; int base = 10; if (*cp == '0') { char c = *(cp + 1); if (c == 'x' || c == 'X') { base = 16; cp += 2; } else if (c >= '0' && c <= '7') { base = 8; cp++; } } *result = simple_strtoul(cp, &ep, base); if (cp == ep) return TOMOYO_VALUE_TYPE_INVALID; *str = ep; switch (base) { case 16: return TOMOYO_VALUE_TYPE_HEXADECIMAL; case 8: return TOMOYO_VALUE_TYPE_OCTAL; default: return TOMOYO_VALUE_TYPE_DECIMAL; } } /** * tomoyo_print_ulong - Print an "unsigned long" value. * * @buffer: Pointer to buffer. * @buffer_len: Size of @buffer. * @value: An "unsigned long" value. * @type: Type of @value. * * Returns nothing. */ void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type) { if (type == TOMOYO_VALUE_TYPE_DECIMAL) snprintf(buffer, buffer_len, "%lu", value); else if (type == TOMOYO_VALUE_TYPE_OCTAL) snprintf(buffer, buffer_len, "0%lo", value); else if (type == TOMOYO_VALUE_TYPE_HEXADECIMAL) snprintf(buffer, buffer_len, "0x%lX", value); else snprintf(buffer, buffer_len, "type(%u)", type); } /** * tomoyo_parse_name_union - Parse a tomoyo_name_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr) { char *filename; if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_PATH_GROUP); return ptr->group != NULL; } filename = tomoyo_read_token(param); if (!tomoyo_correct_word(filename)) return false; ptr->filename = tomoyo_get_name(filename); return ptr->filename != NULL; } /** * tomoyo_parse_number_union - Parse a tomoyo_number_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr) { char *data; u8 type; unsigned long v; memset(ptr, 0, sizeof(*ptr)); if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_NUMBER_GROUP); return ptr->group != NULL; } data = tomoyo_read_token(param); type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID) return false; ptr->values[0] = v; ptr->value_type[0] = type; if (!*data) { ptr->values[1] = v; ptr->value_type[1] = type; return true; } if (*data++ != '-') return false; type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID || *data || ptr->values[0] > v) return false; ptr->values[1] = v; ptr->value_type[1] = type; return true; } /** * tomoyo_byte_range - Check whether the string is a \ooo style octal value. * * @str: Pointer to the string. * * Returns true if @str is a \ooo style octal value, false otherwise. * * TOMOYO uses \ooo style representation for 0x01 - 0x20 and 0x7F - 0xFF. * This function verifies that \ooo is in valid range. */ static inline bool tomoyo_byte_range(const char *str) { return *str >= '0' && *str++ <= '3' && *str >= '0' && *str++ <= '7' && *str >= '0' && *str <= '7'; } /** * tomoyo_alphabet_char - Check whether the character is an alphabet. * * @c: The character to check. * * Returns true if @c is an alphabet character, false otherwise. */ static inline bool tomoyo_alphabet_char(const char c) { return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); } /** * tomoyo_make_byte - Make byte value from three octal characters. * * @c1: The first character. * @c2: The second character. * @c3: The third character. * * Returns byte value. */ static inline u8 tomoyo_make_byte(const u8 c1, const u8 c2, const u8 c3) { return ((c1 - '0') << 6) + ((c2 - '0') << 3) + (c3 - '0'); } /** * tomoyo_valid - Check whether the character is a valid char. * * @c: The character to check. * * Returns true if @c is a valid character, false otherwise. */ static inline bool tomoyo_valid(const unsigned char c) { return c > ' ' && c < 127; } /** * tomoyo_invalid - Check whether the character is an invalid char. * * @c: The character to check. * * Returns true if @c is an invalid character, false otherwise. */ static inline bool tomoyo_invalid(const unsigned char c) { return c && (c <= ' ' || c >= 127); } /** * tomoyo_str_starts - Check whether the given string starts with the given keyword. * * @src: Pointer to pointer to the string. * @find: Pointer to the keyword. * * Returns true if @src starts with @find, false otherwise. * * The @src is updated to point the first character after the @find * if @src starts with @find. */ bool tomoyo_str_starts(char **src, const char *find) { const int len = strlen(find); char *tmp = *src; if (strncmp(tmp, find, len)) return false; tmp += len; *src = tmp; return true; } /** * tomoyo_normalize_line - Format string. * * @buffer: The line to normalize. * * Leading and trailing whitespaces are removed. * Multiple whitespaces are packed into single space. * * Returns nothing. */ void tomoyo_normalize_line(unsigned char *buffer) { unsigned char *sp = buffer; unsigned char *dp = buffer; bool first = true; while (tomoyo_invalid(*sp)) sp++; while (*sp) { if (!first) *dp++ = ' '; first = false; while (tomoyo_valid(*sp)) *dp++ = *sp++; while (tomoyo_invalid(*sp)) sp++; } *dp = '\0'; } /** * tomoyo_correct_word2 - Validate a string. * * @string: The string to check. Maybe non-'\0'-terminated. * @len: Length of @string. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ static bool tomoyo_correct_word2(const char *string, size_t len) { u8 recursion = 20; const char *const start = string; bool in_repetition = false; if (!len) goto out; while (len--) { unsigned char c = *string++; if (c == '\\') { if (!len--) goto out; c = *string++; if (c >= '0' && c <= '3') { unsigned char d; unsigned char e; if (!len-- || !len--) goto out; d = *string++; e = *string++; if (d < '0' || d > '7' || e < '0' || e > '7') goto out; c = tomoyo_make_byte(c, d, e); if (c <= ' ' || c >= 127) continue; goto out; } switch (c) { case '\\': /* "\\" */ case '+': /* "\+" */ case '?': /* "\?" */ case 'x': /* "\x" */ case 'a': /* "\a" */ case '-': /* "\-" */ continue; } if (!recursion--) goto out; switch (c) { case '*': /* "\*" */ case '@': /* "\@" */ case '$': /* "\$" */ case 'X': /* "\X" */ case 'A': /* "\A" */ continue; case '{': /* "/\{" */ if (string - 3 < start || *(string - 3) != '/') goto out; in_repetition = true; continue; case '}': /* "\}/" */ if (*string != '/') goto out; if (!in_repetition) goto out; in_repetition = false; continue; } goto out; } else if (in_repetition && c == '/') { goto out; } else if (c <= ' ' || c >= 127) { goto out; } } if (in_repetition) goto out; return true; out: return false; } /** * tomoyo_correct_word - Validate a string. * * @string: The string to check. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ bool tomoyo_correct_word(const char *string) { return tomoyo_correct_word2(string, strlen(string)); } /** * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules. * * @filename: The pathname to check. * @len: Length of @filename. * * Returns true if @filename follows the naming rules, false otherwise. */ static bool tomoyo_correct_path2(const char *filename, const size_t len) { const char *cp1 = memchr(filename, '/', len); const char *cp2 = memchr(filename, '.', len); return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len); } /** * tomoyo_correct_path - Validate a pathname. * * @filename: The pathname to check. * * Check whether the given pathname follows the naming rules. * Returns true if @filename follows the naming rules, false otherwise. */ bool tomoyo_correct_path(const char *filename) { return tomoyo_correct_path2(filename, strlen(filename)); } /** * tomoyo_correct_domain - Check whether the given domainname follows the naming rules. * * @domainname: The domainname to check. * * Returns true if @domainname follows the naming rules, false otherwise. */ bool tomoyo_correct_domain(const unsigned char *domainname) { if (!domainname || !tomoyo_domain_def(domainname)) return false; domainname = strchr(domainname, ' '); if (!domainname++) return true; while (1) { const unsigned char *cp = strchr(domainname, ' '); if (!cp) break; if (!tomoyo_correct_path2(domainname, cp - domainname)) return false; domainname = cp + 1; } return tomoyo_correct_path(domainname); } /** * tomoyo_domain_def - Check whether the given token can be a domainname. * * @buffer: The token to check. * * Returns true if @buffer possibly be a domainname, false otherwise. */ bool tomoyo_domain_def(const unsigned char *buffer) { const unsigned char *cp; int len; if (*buffer != '<') return false; cp = strchr(buffer, ' '); if (!cp) len = strlen(buffer); else len = cp - buffer; if (buffer[len - 1] != '>' || !tomoyo_correct_word2(buffer + 1, len - 2)) return false; return true; } /** * tomoyo_find_domain - Find a domain by the given name. * * @domainname: The domainname to find. * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; } return NULL; } /** * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token. * * @filename: The string to evaluate. * * Returns the initial length without a pattern in @filename. */ static int tomoyo_const_part_length(const char *filename) { char c; int len = 0; if (!filename) return 0; while ((c = *filename++) != '\0') { if (c != '\\') { len++; continue; } c = *filename++; switch (c) { case '\\': /* "\\" */ len += 2; continue; case '0': /* "\ooo" */ case '1': case '2': case '3': c = *filename++; if (c < '0' || c > '7') break; c = *filename++; if (c < '0' || c > '7') break; len += 4; continue; } break; } return len; } /** * tomoyo_fill_path_info - Fill in "struct tomoyo_path_info" members. * * @ptr: Pointer to "struct tomoyo_path_info" to fill in. * * The caller sets "struct tomoyo_path_info"->name. */ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) { const char *name = ptr->name; const int len = strlen(name); ptr->const_len = tomoyo_const_part_length(name); ptr->is_dir = len && (name[len - 1] == '/'); ptr->is_patterned = (ptr->const_len < len); ptr->hash = full_name_hash(NULL, name, len); } /** * tomoyo_file_matches_pattern2 - Pattern matching without '/' character and "\-" pattern. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern2(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { while (filename < filename_end && pattern < pattern_end) { char c; int i; int j; if (*pattern != '\\') { if (*filename++ != *pattern++) return false; continue; } c = *filename; pattern++; switch (*pattern) { case '?': if (c == '/') { return false; } else if (c == '\\') { if (filename[1] == '\\') filename++; else if (tomoyo_byte_range(filename + 1)) filename += 3; else return false; } break; case '\\': if (c != '\\') return false; if (*++filename != '\\') return false; break; case '+': if (!isdigit(c)) return false; break; case 'x': if (!isxdigit(c)) return false; break; case 'a': if (!tomoyo_alphabet_char(c)) return false; break; case '0': case '1': case '2': case '3': if (c == '\\' && tomoyo_byte_range(filename + 1) && strncmp(filename + 1, pattern, 3) == 0) { filename += 3; pattern += 2; break; } return false; /* Not matched. */ case '*': case '@': for (i = 0; i <= filename_end - filename; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; c = filename[i]; if (c == '.' && *pattern == '@') break; if (c != '\\') continue; if (filename[i + 1] == '\\') i++; else if (tomoyo_byte_range(filename + i + 1)) i += 3; else break; /* Bad pattern. */ } return false; /* Not matched. */ default: j = 0; c = *pattern; if (c == '$') { while (isdigit(filename[j])) j++; } else if (c == 'X') { while (isxdigit(filename[j])) j++; } else if (c == 'A') { while (tomoyo_alphabet_char(filename[j])) j++; } for (i = 1; i <= j; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; } return false; /* Not matched or bad pattern. */ } filename++; pattern++; } while (*pattern == '\\' && (*(pattern + 1) == '*' || *(pattern + 1) == '@')) pattern += 2; return filename == filename_end && pattern == pattern_end; } /** * tomoyo_file_matches_pattern - Pattern matching without '/' character. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { const char *pattern_start = pattern; bool first = true; bool result; while (pattern < pattern_end - 1) { /* Split at "\-" pattern. */ if (*pattern++ != '\\' || *pattern++ != '-') continue; result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern - 2); if (first) result = !result; if (result) return false; first = false; pattern_start = pattern; } result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern_end); return first ? result : !result; } /** * tomoyo_path_matches_pattern2 - Do pathname pattern matching. * * @f: The start of string to check. * @p: The start of pattern to compare. * * Returns true if @f matches @p, false otherwise. */ static bool tomoyo_path_matches_pattern2(const char *f, const char *p) { const char *f_delimiter; const char *p_delimiter; while (*f && *p) { f_delimiter = strchr(f, '/'); if (!f_delimiter) f_delimiter = f + strlen(f); p_delimiter = strchr(p, '/'); if (!p_delimiter) p_delimiter = p + strlen(p); if (*p == '\\' && *(p + 1) == '{') goto recursive; if (!tomoyo_file_matches_pattern(f, f_delimiter, p, p_delimiter)) return false; f = f_delimiter; if (*f) f++; p = p_delimiter; if (*p) p++; } /* Ignore trailing "\*" and "\@" in @pattern. */ while (*p == '\\' && (*(p + 1) == '*' || *(p + 1) == '@')) p += 2; return !*f && !*p; recursive: /* * The "\{" pattern is permitted only after '/' character. * This guarantees that below "*(p - 1)" is safe. * Also, the "\}" pattern is permitted only before '/' character * so that "\{" + "\}" pair will not break the "\-" operator. */ if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' || *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\') return false; /* Bad pattern. */ do { /* Compare current component with pattern. */ if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2, p_delimiter - 2)) break; /* Proceed to next component. */ f = f_delimiter; if (!*f) break; f++; /* Continue comparison. */ if (tomoyo_path_matches_pattern2(f, p_delimiter + 1)) return true; f_delimiter = strchr(f, '/'); } while (f_delimiter); return false; /* Not matched. */ } /** * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern. * * @filename: The filename to check. * @pattern: The pattern to compare. * * Returns true if matches, false otherwise. * * The following patterns are available. * \\ \ itself. * \ooo Octal representation of a byte. * \* Zero or more repetitions of characters other than '/'. * \@ Zero or more repetitions of characters other than '/' or '.'. * \? 1 byte character other than '/'. * \$ One or more repetitions of decimal digits. * \+ 1 decimal digit. * \X One or more repetitions of hexadecimal digits. * \x 1 hexadecimal digit. * \A One or more repetitions of alphabet characters. * \a 1 alphabet character. * * \- Subtraction operator. * * /\{dir\}/ '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/ * /dir/dir/dir/ ). */ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern) { const char *f = filename->name; const char *p = pattern->name; const int len = pattern->const_len; /* If @pattern doesn't contain pattern, I can use strcmp(). */ if (!pattern->is_patterned) return !tomoyo_pathcmp(filename, pattern); /* Don't compare directory and non-directory. */ if (filename->is_dir != pattern->is_dir) return false; /* Compare the initial length without patterns. */ if (strncmp(f, p, len)) return false; f += len; p += len; return tomoyo_path_matches_pattern2(f, p); } /** * tomoyo_get_exe - Get tomoyo_realpath() of current process. * * Returns the tomoyo_realpath() of current process on success, NULL otherwise. * * This function uses kzalloc(), so the caller must call kfree() * if this function didn't return NULL. */ const char *tomoyo_get_exe(void) { struct file *exe_file; const char *cp; struct mm_struct *mm = current->mm; if (!mm) return NULL; exe_file = get_mm_exe_file(mm); if (!exe_file) return NULL; cp = tomoyo_realpath_from_path(&exe_file->f_path); fput(exe_file); return cp; } /** * tomoyo_get_mode - Get MAC mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * * Returns mode. */ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index) { u8 mode; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return TOMOYO_CONFIG_DISABLED; p = tomoyo_profile(ns, profile); mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; return mode & 3; } /** * tomoyo_init_request_info - Initialize "struct tomoyo_request_info" members. * * @r: Pointer to "struct tomoyo_request_info" to initialize. * @domain: Pointer to "struct tomoyo_domain_info". NULL for tomoyo_domain(). * @index: Index number of functionality. * * Returns mode. */ int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index) { u8 profile; memset(r, 0, sizeof(*r)); if (!domain) domain = tomoyo_domain(); r->domain = domain; profile = domain->profile; r->profile = profile; r->type = index; r->mode = tomoyo_get_mode(domain->ns, profile, index); return r->mode; } /** * tomoyo_domain_quota_is_ok - Check for domain's quota. * * @r: Pointer to "struct tomoyo_request_info". * * Returns true if the domain is not exceeded quota, false otherwise. * * Caller holds tomoyo_read_lock(). */ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) { unsigned int count = 0; struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; if (r->mode != TOMOYO_CONFIG_LEARNING) return false; if (!domain) return true; if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED])) return false; list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, srcu_read_lock_held(&tomoyo_ss)) { u16 perm; if (ptr->is_deleted) continue; /* * Reading perm bitmap might race with tomoyo_merge_*() because * caller does not hold tomoyo_policy_lock mutex. But exceeding * max_learning_entry parameter by a few entries does not harm. */ switch (ptr->type) { case TOMOYO_TYPE_PATH_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm); break; case TOMOYO_TYPE_PATH2_ACL: perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm); break; case TOMOYO_TYPE_PATH_NUMBER_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head) ->perm); break; case TOMOYO_TYPE_MKDEV_ACL: perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm); break; case TOMOYO_TYPE_INET_ACL: perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm); break; case TOMOYO_TYPE_UNIX_ACL: perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm); break; case TOMOYO_TYPE_MANUAL_TASK_ACL: perm = 0; break; default: perm = 1; } count += hweight16(perm); } if (count < tomoyo_profile(domain->ns, domain->profile)-> pref[TOMOYO_PREF_MAX_LEARNING_ENTRY]) return true; WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true); /* r->granted = false; */ tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]); #ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n", domain->domainname->name); #endif return false; } |
| 2 86 9 1 1 1 1 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/rcupdate.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) #define INIT_PASID 0 struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * If your page will not be mapped to userspace, you can also use the four * bytes in the mapcount union, but you must call page_mapcount_reset() * before freeing it. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and counters. * That requires that freelist & counters in struct slab be adjacent and * double-word aligned. Because struct slab currently just reinterprets the * bits of struct page, we align all struct pages to double-word boundaries, * and ensure that 'freelist' is aligned within struct slab. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) #else #define _struct_page_alignment __aligned(sizeof(unsigned long)) #endif struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. * WARNING: bit 0 of the first word is used for PageTail(). That * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ union { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ union { struct list_head lru; /* Or, for the Unevictable "LRU list" slot */ struct { /* Always even, to negate PageTail */ void *__filler; /* Count page's or folio's mlocks */ unsigned int mlock_count; }; /* Or, free page */ struct list_head buddy_list; struct list_head pcp_list; }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; union { pgoff_t index; /* Our offset within mapping. */ unsigned long share; /* share count for fsdax */ }; /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if PageSwapCache. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; }; struct { /* page_pool used by netstack */ /** * @pp_magic: magic value to avoid recycling non * page_pool allocated pages. */ unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being * mapped so the next 3 words hold the mapping, index, * and private fields from the source anonymous or * page cache page while the page is migrated to device * private memory. * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also * use the mapping, index, and private fields when * pmem backed DAX files are mapped. */ }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; }; union { /* This union is 4 bytes in size. */ /* * If the page can be mapped to userspace, encodes the number * of times this page is referenced by a page table. */ atomic_t _mapcount; /* * If the page is neither PageSlab nor mappable to userspace, * the value stored here may help determine what this page * is used for. See page-flags.h for a list of page types * which are currently stored here. */ unsigned int page_type; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with * highmem some memory is mapped into kernel virtual memory * dynamically, so we need a place to store that address. * Note that this field could be 16 bits on x86 ... ;) * * Architectures with slow multiplication can define * WANT_PAGE_VIRTUAL in asm/page.h */ #if defined(WANT_PAGE_VIRTUAL) void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif #ifdef CONFIG_KMSAN /* * KMSAN metadata for this page: * - shadow page: every bit indicates whether the corresponding * bit of the original page is initialized (0) or not (1); * - origin page: every 4 bytes contain an id of the stack trace * where the uninitialized value was created. */ struct page *kmsan_shadow; struct page *kmsan_origin; #endif } _struct_page_alignment; /* * struct encoded_page - a nonexistent type marking this pointer * * An 'encoded_page' pointer is a pointer to a regular 'struct page', but * with the low bits of the pointer indicating extra context-dependent * information. Only used in mmu_gather handling, and this acts as a type * system check on that use. * * We only really have two guaranteed bits in general, although you could * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE) * for more. * * Use the supplied helper functions to endcode/decode the pointer and bits. */ struct encoded_page; #define ENCODED_PAGE_BITS 3ul /* Perform rmap removal after we have flushed the TLB. */ #define ENCODED_PAGE_BIT_DELAY_RMAP 1ul /* * The next item in an encoded_page array is the "nr_pages" argument, specifying * the number of consecutive pages starting from this page, that all belong to * the same folio. For example, "nr_pages" corresponds to the number of folio * references that must be dropped. If this bit is not set, "nr_pages" is * implicitly 1. */ #define ENCODED_PAGE_BIT_NR_PAGES_NEXT 2ul static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags) { BUILD_BUG_ON(flags > ENCODED_PAGE_BITS); return (struct encoded_page *)(flags | (unsigned long)page); } static inline unsigned long encoded_page_flags(struct encoded_page *page) { return ENCODED_PAGE_BITS & (unsigned long)page; } static inline struct page *encoded_page_ptr(struct encoded_page *page) { return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page); } static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr) { VM_WARN_ON_ONCE((nr << 2) >> 2 != nr); return (struct encoded_page *)(nr << 2); } static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page) { return ((unsigned long)page) >> 2; } /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ typedef struct { unsigned long val; } swp_entry_t; /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, * this is the index from the beginning of the mmap. * @private: Filesystem per-folio data (see folio_attach_private()). * @swap: Used for swp_entry_t if folio_test_swapcache(). * @_mapcount: Do not access this member directly. Use folio_mapcount() to * find out how many times this folio is mapped by userspace. * @_refcount: Do not access this member directly. Use folio_ref_count() * to find how many references there are to this folio. * @memcg_data: Memory Control Group data. * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). * @_large_mapcount: Do not use directly, call folio_mapcount(). * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head(). * @_deferred_list: Folios to be split under memory pressure. * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that * same power-of-two. It is at least as large as %PAGE_SIZE. If it is * in the page cache, it is at a file offset which is a multiple of that * power-of-two. It may be mapped into userspace at an address which is * at an arbitrary page offset, but its kernel virtual address is aligned * to its size. */ struct folio { /* private: don't document the anon union */ union { struct { /* public: */ unsigned long flags; union { struct list_head lru; /* private: avoid cluttering the output */ struct { void *__filler; /* public: */ unsigned int mlock_count; /* private: */ }; /* public: */ }; struct address_space *mapping; pgoff_t index; union { void *private; swp_entry_t swap; }; atomic_t _mapcount; atomic_t _refcount; #ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif #if defined(WANT_PAGE_VIRTUAL) void *virtual; #endif #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif /* private: the union with struct page is transitional */ }; struct page page; }; union { struct { unsigned long _flags_1; unsigned long _head_1; /* public: */ atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; #ifdef CONFIG_64BIT unsigned int _folio_nr_pages; #endif /* private: the union with struct page is transitional */ }; struct page __page_1; }; union { struct { unsigned long _flags_2; unsigned long _head_2; /* public: */ void *_hugetlb_subpool; void *_hugetlb_cgroup; void *_hugetlb_cgroup_rsvd; void *_hugetlb_hwpoison; /* private: the union with struct page is transitional */ }; struct { unsigned long _flags_2a; unsigned long _head_2a; /* public: */ struct list_head _deferred_list; /* private: the union with struct page is transitional */ }; struct page __page_2; }; }; #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); FOLIO_MATCH(_mapcount, _mapcount); FOLIO_MATCH(_refcount, _refcount); #ifdef CONFIG_MEMCG FOLIO_MATCH(memcg_data, memcg_data); #endif #if defined(WANT_PAGE_VIRTUAL) FOLIO_MATCH(virtual, virtual); #endif #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS FOLIO_MATCH(_last_cpupid, _last_cpupid); #endif #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ offsetof(struct page, pg) + sizeof(struct page)) FOLIO_MATCH(flags, _flags_1); FOLIO_MATCH(compound_head, _head_1); #undef FOLIO_MATCH #define FOLIO_MATCH(pg, fl) \ static_assert(offsetof(struct folio, fl) == \ offsetof(struct page, pg) + 2 * sizeof(struct page)) FOLIO_MATCH(flags, _flags_2); FOLIO_MATCH(compound_head, _head_2); FOLIO_MATCH(flags, _flags_2a); FOLIO_MATCH(compound_head, _head_2a); #undef FOLIO_MATCH /** * struct ptdesc - Memory descriptor for page tables. * @__page_flags: Same as page flags. Powerpc only. * @pt_rcu_head: For freeing page table pages. * @pt_list: List of used page tables. Used for s390 and x86. * @_pt_pad_1: Padding that aliases with page's compound head. * @pmd_huge_pte: Protected by ptdesc->ptl, used for THPs. * @__page_mapping: Aliases with page->mapping. Unused for page tables. * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. * @__page_refcount: Same as page refcount. * @pt_memcg_data: Memcg data. Tracked for page tables here. * * This struct overlays struct page for now. Do not modify without a good * understanding of the issues. */ struct ptdesc { unsigned long __page_flags; union { struct rcu_head pt_rcu_head; struct list_head pt_list; struct { unsigned long _pt_pad_1; pgtable_t pmd_huge_pte; }; }; unsigned long __page_mapping; union { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; }; union { unsigned long _pt_pad_2; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; #endif }; unsigned int __page_type; atomic_t __page_refcount; #ifdef CONFIG_MEMCG unsigned long pt_memcg_data; #endif }; #define TABLE_MATCH(pg, pt) \ static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt)) TABLE_MATCH(flags, __page_flags); TABLE_MATCH(compound_head, pt_list); TABLE_MATCH(compound_head, _pt_pad_1); TABLE_MATCH(mapping, __page_mapping); TABLE_MATCH(index, pt_index); TABLE_MATCH(rcu_head, pt_rcu_head); TABLE_MATCH(page_type, __page_type); TABLE_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG TABLE_MATCH(memcg_data, pt_memcg_data); #endif #undef TABLE_MATCH static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); #define ptdesc_page(pt) (_Generic((pt), \ const struct ptdesc *: (const struct page *)(pt), \ struct ptdesc *: (struct page *)(pt))) #define ptdesc_folio(pt) (_Generic((pt), \ const struct ptdesc *: (const struct folio *)(pt), \ struct ptdesc *: (struct folio *)(pt))) #define page_ptdesc(p) (_Generic((p), \ const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages * should be used for data that's ancillary to the head page (eg attaching * buffer heads to tail pages after attaching buffer heads to the head page) */ #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) { page->private = private; } static inline void *folio_get_private(struct folio *folio) { return folio->private; } struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) __u16 offset; __u16 size; #else __u32 offset; #endif /* we maintain a pagecount bias, so that we dont dirty cache line * containing page->_refcount every time we allocate a fragment. */ unsigned int pagecnt_bias; bool pfmemalloc; }; typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { struct rb_node vm_rb; /* link in global region tree */ vm_flags_t vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for * this region */ }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) struct vm_userfaultfd_ctx { struct userfaultfd_ctx *ctx; }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ struct anon_vma_name { struct kref kref; /* The name needs to be at the end because it is dynamically sized. */ char name[]; }; #ifdef CONFIG_ANON_VMA_NAME /* * mmap_lock should be read-locked when calling anon_vma_name(). Caller should * either keep holding the lock while using the returned pointer or it should * raise anon_vma_name refcount before releasing the lock. */ struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); struct anon_vma_name *anon_vma_name_alloc(const char *name); void anon_vma_name_free(struct kref *kref); #else /* CONFIG_ANON_VMA_NAME */ static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { return NULL; } static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) { return NULL; } #endif struct vma_lock { struct rw_semaphore lock; }; struct vma_numab_state { /* * Initialised as time in 'jiffies' after which VMA * should be scanned. Delays first scan of new VMA by at * least sysctl_numa_balancing_scan_delay: */ unsigned long next_scan; /* * Time in jiffies when pids_active[] is reset to * detect phase change behaviour: */ unsigned long pids_active_reset; /* * Approximate tracking of PIDs that trapped a NUMA hinting * fault. May produce false positives due to hash collisions. * * [0] Previous PID tracking * [1] Current PID tracking * * Window moves after next_pid_reset has expired approximately * every VMA_PID_RESET_PERIOD jiffies: */ unsigned long pids_active[2]; /* MM scan sequence ID when scan first started after VMA creation */ int start_scan_seq; /* * MM scan sequence ID when the VMA was last completely scanned. * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq */ int prev_scan_seq; }; /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ union { struct { /* VMA covers [vm_start; vm_end) addresses within mm */ unsigned long vm_start; unsigned long vm_end; }; #ifdef CONFIG_PER_VMA_LOCK struct rcu_head vm_rcu; /* Used for deferred freeing. */ #endif }; struct mm_struct *vm_mm; /* The address space we belong to. */ pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. * To modify use vm_flags_{init|reset|set|clear|mod} functions. */ union { const vm_flags_t vm_flags; vm_flags_t __private __vm_flags; }; #ifdef CONFIG_PER_VMA_LOCK /* Flag to indicate areas detached from the mm->mm_mt tree */ bool detached; /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) * - vm_lock->lock (in write mode) * Can be read reliably while holding one of: * - mmap_lock (in read or write mode) * - vm_lock->lock (in read or write mode) * Can be read unreliably (using READ_ONCE()) for pessimistic bailout * while holding nothing (except RCU to keep the VMA struct allocated). * * This sequence counter is explicitly allowed to overflow; sequence * counter reuse can only lead to occasional unnecessary use of the * slowpath. */ int vm_lock_seq; struct vma_lock *vm_lock; #endif /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. * */ struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_ANON_VMA_NAME /* * For private and shared anonymous mappings, a pointer to a null * terminated string containing the name given to the vma, or NULL if * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. */ struct anon_vma_name *anon_name; #endif #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif #ifdef CONFIG_NUMA_BALANCING struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; #ifdef CONFIG_NUMA #define vma_policy(vma) ((vma)->vm_policy) #else #define vma_policy(vma) NULL #endif #ifdef CONFIG_SCHED_MM_CID struct mm_cid { u64 time; int cid; }; #endif struct kioctx_table; struct iommu_mm_data; struct mm_struct { struct { /* * Fields which are often written to are placed in a separate * cache line. */ struct { /** * @mm_count: The number of references to &struct * mm_struct (@mm_users count as 1). * * Use mmgrab()/mmdrop() to modify. When this drops to * 0, the &struct mm_struct is freed. */ atomic_t mm_count; } ____cacheline_aligned_in_smp; struct maple_tree mm_mt; unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* Base addresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER /** * @membarrier_state: Flags controlling membarrier behavior. * * This field is close to @pgd to hopefully fit in the same * cache-line, which needs to be touched by switch_mm(). */ atomic_t membarrier_state; #endif /** * @mm_users: The number of users including userspace. * * Use mmget()/mmget_not_zero()/mmput() to modify. When this * drops to 0 (i.e. when the task exits and there are no other * temporary reference holders), we also release a reference on * @mm_count (which may then free the &struct mm_struct if * @mm_count also drops to 0). */ atomic_t mm_users; #ifdef CONFIG_SCHED_MM_CID /** * @pcpu_cid: Per-cpu current cid. * * Keep track of the currently allocated mm_cid for each cpu. * The per-cpu mm_cid values are serialized by their respective * runqueue locks. */ struct mm_cid __percpu *pcpu_cid; /* * @mm_cid_next_scan: Next mm_cid scan (in jiffies). * * When the next mm_cid scan is due (in jiffies). */ unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ #endif int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some * counters */ /* * With some kernel config, the current mmap_lock's offset * inside 'mm_struct' is at 0x120, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * * So please be careful with adding new fields before * mmap_lock, which can easily push the 2 fields into one * cacheline. */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off * init_mm.mmlist, and are protected * by mmlist_lock */ #ifdef CONFIG_PER_VMA_LOCK /* * This field has lock-like semantics, meaning it is sometimes * accessed with ACQUIRE/RELEASE semantics. * Roughly speaking, incrementing the sequence number is * equivalent to releasing locks on VMAs; reading the sequence * number can be part of taking a read lock on a VMA. * * Can be modified under write mmap_lock using RELEASE * semantics. * Can be read with no other protection when holding write * mmap_lock. * Can be read with ACQUIRE semantics if not holding write * mmap_lock. */ int mm_lock_seq; #endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ atomic64_t pinned_vm; /* Refcount permanently increased */ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; /** * @write_protect_seq: Locked when any thread is write * protecting pages mapped by this mm to enforce a later COW, * for instance during page table copying for fork(). */ seqcount_t write_protect_seq; spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ struct percpu_counter rss_stat[NR_MM_COUNTERS]; struct linux_binfmt *binfmt; /* Architecture-specific MM context */ mm_context_t context; unsigned long flags; /* Must use atomic bitops to access */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */ struct task_struct __rcu *owner; #endif struct user_namespace *user_ns; /* store ref to file /proc/<pid>/exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING /* * numa_next_scan is the next time that PTEs will be remapped * PROT_NONE to trigger NUMA hinting faults; such faults gather * statistics and migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; /* Restart point for scanning and remapping PTEs. */ unsigned long numa_scan_offset; /* numa_scan_seq prevents two threads remapping PTEs. */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when * moving a PROT_NONE mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT struct rcu_head delayed_drop; #endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; #ifdef CONFIG_IOMMU_MM_DATA struct iommu_mm_data *iommu_mm; #endif #ifdef CONFIG_KSM /* * Represent how many pages of this process are involved in KSM * merging (not including ksm_zero_pages). */ unsigned long ksm_merging_pages; /* * Represent how many pages are checked for ksm merging * including merged and not merged. */ unsigned long ksm_rmap_items; /* * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ unsigned long ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { /* this mm_struct is on lru_gen_mm_list */ struct list_head list; /* * Set when switching to this mm_struct, as a hint of * whether it has been used since the last time per-node * page table walkers cleared the corresponding bits. */ unsigned long bitmap; #ifdef CONFIG_MEMCG /* points to the memcg of "owner" above */ struct mem_cgroup *memcg; #endif } lru_gen; #endif /* CONFIG_LRU_GEN_WALKS_MMU */ } __randomize_layout; /* * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ unsigned long cpu_bitmap[]; }; #define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { return (struct cpumask *)&mm->cpu_bitmap; } #ifdef CONFIG_LRU_GEN struct lru_gen_mm_list { /* mm_struct list for page table walkers */ struct list_head fifo; /* protects the list above */ spinlock_t lock; }; #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_LRU_GEN_WALKS_MMU void lru_gen_add_mm(struct mm_struct *mm); void lru_gen_del_mm(struct mm_struct *mm); void lru_gen_migrate_mm(struct mm_struct *mm); static inline void lru_gen_init_mm(struct mm_struct *mm) { INIT_LIST_HEAD(&mm->lru_gen.list); mm->lru_gen.bitmap = 0; #ifdef CONFIG_MEMCG mm->lru_gen.memcg = NULL; #endif } static inline void lru_gen_use_mm(struct mm_struct *mm) { /* * When the bitmap is set, page reclaim knows this mm_struct has been * used since the last time it cleared the bitmap. So it might be worth * walking the page tables of this mm_struct to clear the accessed bit. */ WRITE_ONCE(mm->lru_gen.bitmap, -1); } #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static inline void lru_gen_add_mm(struct mm_struct *mm) { } static inline void lru_gen_del_mm(struct mm_struct *mm) { } static inline void lru_gen_migrate_mm(struct mm_struct *mm) { } static inline void lru_gen_init_mm(struct mm_struct *mm) { } static inline void lru_gen_use_mm(struct mm_struct *mm) { } #endif /* CONFIG_LRU_GEN_WALKS_MMU */ struct vma_iterator { struct ma_state mas; }; #define VMA_ITERATOR(name, __mm, __addr) \ struct vma_iterator name = { \ .mas = { \ .tree = &(__mm)->mm_mt, \ .index = __addr, \ .node = NULL, \ .status = ma_start, \ }, \ } static inline void vma_iter_init(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long addr) { mas_init(&vmi->mas, &mm->mm_mt, addr); } #ifdef CONFIG_SCHED_MM_CID enum mm_cid_state { MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ MM_CID_LAZY_PUT = (1U << 31), }; static inline bool mm_cid_is_unset(int cid) { return cid == MM_CID_UNSET; } static inline bool mm_cid_is_lazy_put(int cid) { return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); } static inline bool mm_cid_is_valid(int cid) { return !(cid & MM_CID_LAZY_PUT); } static inline int mm_cid_set_lazy_put(int cid) { return cid | MM_CID_LAZY_PUT; } static inline int mm_cid_clear_lazy_put(int cid) { return cid & ~MM_CID_LAZY_PUT; } /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { unsigned long cid_bitmap = (unsigned long)mm; cid_bitmap += offsetof(struct mm_struct, cpu_bitmap); /* Skip cpu_bitmap */ cid_bitmap += cpumask_size(); return (struct cpumask *)cid_bitmap; } static inline void mm_init_cid(struct mm_struct *mm) { int i; for_each_possible_cpu(i) { struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); pcpu_cid->cid = MM_CID_UNSET; pcpu_cid->time = 0; } cpumask_clear(mm_cidmask(mm)); } static inline int mm_alloc_cid_noprof(struct mm_struct *mm) { mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm); return 0; } #define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { free_percpu(mm->pcpu_cid); mm->pcpu_cid = NULL; } static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ typedef __bitwise unsigned int vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100, VM_FAULT_LOCKED = (__force vm_fault_t)0x000200, VM_FAULT_RETRY = (__force vm_fault_t)0x000400, VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) #define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ { VM_FAULT_COMPLETED, "COMPLETED" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ /* * If .fault is not provided, this points to a * NULL-terminated array of pages that back the special mapping. * * This must not be NULL unless .fault is provided. */ struct page **pages; /* * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ vm_fault_t (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; /** * enum fault_flag - Fault flag definitions. * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to break COW in a * COW mapping, making sure that an exclusive anon page is * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. * * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when * applied to mappings that are not COW mappings. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, FAULT_FLAG_MKWRITE = 1 << 1, FAULT_FLAG_ALLOW_RETRY = 1 << 2, FAULT_FLAG_RETRY_NOWAIT = 1 << 3, FAULT_FLAG_KILLABLE = 1 << 4, FAULT_FLAG_TRIED = 1 << 5, FAULT_FLAG_USER = 1 << 6, FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; /* Flags for clear_young_dirty_ptes(). */ typedef int __bitwise cydp_t; /* Clear the access bit */ #define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) /* Clear the dirty bit */ #define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ enum { /* check pte is writable */ FOLL_WRITE = 1 << 0, /* do get_page on page */ FOLL_GET = 1 << 1, /* give error on hole if it would be zero */ FOLL_DUMP = 1 << 2, /* get_user_pages read/write w/o permission */ FOLL_FORCE = 1 << 3, /* * if a disk transfer is needed, start the IO and return without waiting * upon it */ FOLL_NOWAIT = 1 << 4, /* do not fault in pages */ FOLL_NOFAULT = 1 << 5, /* check page is hwpoisoned */ FOLL_HWPOISON = 1 << 6, /* don't do file mappings */ FOLL_ANON = 1 << 7, /* * FOLL_LONGTERM indicates that the page will be held for an indefinite * time period _often_ under userspace control. This is in contrast to * iov_iter_get_pages(), whose usages are transient. */ FOLL_LONGTERM = 1 << 8, /* split huge pmd before returning */ FOLL_SPLIT_PMD = 1 << 9, /* allow returning PCI P2PDMA pages */ FOLL_PCI_P2PDMA = 1 << 10, /* allow interrupts from generic signals */ FOLL_INTERRUPTIBLE = 1 << 11, /* * Always honor (trigger) NUMA hinting faults. * * FOLL_WRITE implicitly honors NUMA hinting faults because a * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE * apply). get_user_pages_fast_only() always implicitly honors NUMA * hinting faults. */ FOLL_HONOR_NUMA_FAULT = 1 << 12, /* See also internal only FOLL flags in mm/internal.h */ }; #endif /* _LINUX_MM_TYPES_H */ |
| 63 64 64 25 63 64 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/symlink.c - kernfs symlink 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/fs.h> #include <linux/gfp.h> #include <linux/namei.h> #include "kernfs-internal.h" /** * kernfs_create_link - create a symlink * @parent: directory to create the symlink in * @name: name of the symlink * @target: target node for the symlink to point to * * Return: the created node on success, ERR_PTR() value on error. * Ownership of the link matches ownership of the target. */ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { struct kernfs_node *kn; int error; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; if (target->iattr) { uid = target->iattr->ia_uid; gid = target->iattr->ia_gid; } kn = kernfs_new_node(parent, name, S_IFLNK|0777, uid, gid, KERNFS_LINK); if (!kn) return ERR_PTR(-ENOMEM); if (kernfs_ns_enabled(parent)) kn->ns = target->ns; kn->symlink.target_kn = target; kernfs_get(target); /* ref owned by symlink */ error = kernfs_add_one(kn); if (!error) return kn; kernfs_put(kn); return ERR_PTR(error); } static int kernfs_get_target_path(struct kernfs_node *parent, struct kernfs_node *target, char *path) { struct kernfs_node *base, *kn; char *s = path; int len = 0; /* go up to the root, stop at the base */ base = parent; while (base->parent) { kn = target->parent; while (kn->parent && base != kn) kn = kn->parent; if (base == kn) break; if ((s - path) + 3 >= PATH_MAX) return -ENAMETOOLONG; strcpy(s, "../"); s += 3; base = base->parent; } /* determine end of target string for reverse fillup */ kn = target; while (kn->parent && kn != base) { len += strlen(kn->name) + 1; kn = kn->parent; } /* check limits */ if (len < 2) return -EINVAL; len--; if ((s - path) + len >= PATH_MAX) return -ENAMETOOLONG; /* reverse fillup of target string from target to base */ kn = target; while (kn->parent && kn != base) { int slen = strlen(kn->name); len -= slen; memcpy(s + len, kn->name, slen); if (len) s[--len] = '/'; kn = kn->parent; } return 0; } static int kernfs_getlink(struct inode *inode, char *path) { struct kernfs_node *kn = inode->i_private; struct kernfs_node *parent = kn->parent; struct kernfs_node *target = kn->symlink.target_kn; struct kernfs_root *root = kernfs_root(parent); int error; down_read(&root->kernfs_rwsem); error = kernfs_get_target_path(parent, target, path); up_read(&root->kernfs_rwsem); return error; } static const char *kernfs_iop_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { char *body; int error; if (!dentry) return ERR_PTR(-ECHILD); body = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!body) return ERR_PTR(-ENOMEM); error = kernfs_getlink(inode, body); if (unlikely(error < 0)) { kfree(body); return ERR_PTR(error); } set_delayed_call(done, kfree_link, body); return body; } const struct inode_operations kernfs_symlink_iops = { .listxattr = kernfs_iop_listxattr, .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, }; |
| 8 8 8 8 8 8 8 8 6 8 8 8 8 8 8 8 5 4 3 5 4 3 3 3 3 3 3 3 3 1 3 3 8 8 8 8 8 8 8 8 8 8 1 8 1 8 8 4 4 8 8 1 8 8 8 8 8 8 8 8 8 8 1 8 8 5 3 5 1 2 2 1 1 4 4 4 4 4 4 4 1 4 1 4 4 4 1 2 8 8 8 8 8 8 8 7 8 8 4 4 4 4 4 4 1 1 1 1 1 1 1 1 8 8 8 8 8 6 8 1 4 4 4 3 1 3 4 4 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * This module provides the abstraction for an SCTP association. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ryan Layer <rmlayer@us.ibm.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/in.h> #include <net/ipv6.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* Forward declarations for internal functions. */ static void sctp_select_active_and_retran_path(struct sctp_association *asoc); static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc); /* 1st Level Abstractions. */ /* Initialize a new association from provided memory. */ static struct sctp_association *sctp_association_init( struct sctp_association *asoc, const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_sock *sp; struct sctp_paramhdr *p; int i; /* Retrieve the SCTP per socket area. */ sp = sctp_sk((struct sock *)sk); /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; asoc->base.sk = (struct sock *)sk; asoc->base.net = sock_net(sk); sctp_endpoint_hold(asoc->ep); sock_hold(asoc->base.sk); /* Initialize the common base substructure. */ asoc->base.type = SCTP_EP_TYPE_ASSOCIATION; /* Initialize the object handling fields. */ refcount_set(&asoc->base.refcnt, 1); /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); asoc->state = SCTP_STATE_CLOSED; asoc->cookie_life = ms_to_ktime(sp->assocparams.sasoc_cookie_life); asoc->user_frag = sp->user_frag; /* Set the association max_retrans and RTO values from the * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; asoc->pf_retrans = sp->pf_retrans; asoc->ps_retrans = sp->ps_retrans; asoc->pf_expose = sp->pf_expose; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); asoc->rto_min = msecs_to_jiffies(sp->rtoinfo.srto_min); /* Initialize the association's heartbeat interval based on the * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; asoc->flowlabel = sp->flowlabel; asoc->dscp = sp->dscp; /* Set association default SACK delay */ asoc->sackdelay = msecs_to_jiffies(sp->sackdelay); asoc->sackfreq = sp->sackfreq; /* Set the association default flags controlling * Heartbeat, SACK delay, and Path MTU Discovery. */ asoc->param_flags = sp->param_flags; /* Initialize the maximum number of new data packets that can be sent * in a burst. */ asoc->max_burst = sp->max_burst; asoc->subscribe = sp->subscribe; /* initialize association timers */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = asoc->rto_initial; /* sctpimpguide Section 2.12.2 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the * recommended value of 5 times 'RTO.Max'. */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) timer_setup(&asoc->timers[i], sctp_timer_events[i], 0); /* Pull default initialization values from the sock options. * Note: This assumes that the values have already been * validated in the sock. */ asoc->c.sinit_max_instreams = sp->initmsg.sinit_max_instreams; asoc->c.sinit_num_ostreams = sp->initmsg.sinit_num_ostreams; asoc->max_init_attempts = sp->initmsg.sinit_max_attempts; asoc->max_init_timeo = msecs_to_jiffies(sp->initmsg.sinit_max_init_timeo); /* Set the local window size for receive. * This is also the rcvbuf space per association. * RFC 6 - A SCTP receiver MUST be able to receive a minimum of * 1500 bytes in one SCTP packet. */ if ((sk->sk_rcvbuf/2) < SCTP_DEFAULT_MINWINDOW) asoc->rwnd = SCTP_DEFAULT_MINWINDOW; else asoc->rwnd = sk->sk_rcvbuf/2; asoc->a_rwnd = asoc->rwnd; /* Use my own max window until I learn something better. */ asoc->peer.rwnd = SCTP_DEFAULT_MAXWINDOW; /* Initialize the receive memory counter */ atomic_set(&asoc->rmem_alloc, 0); init_waitqueue_head(&asoc->wait); asoc->c.my_vtag = sctp_generate_tag(ep); asoc->c.my_port = ep->base.bind_addr.port; asoc->c.initial_tsn = sctp_generate_tsn(ep); asoc->next_tsn = asoc->c.initial_tsn; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; asoc->highest_sacked = asoc->ctsn_ack_point; asoc->last_cwr_tsn = asoc->ctsn_ack_point; /* ADDIP Section 4.1 Asconf Chunk Procedures * * When an endpoint has an ASCONF signaled change to be sent to the * remote endpoint it should do the following: * ... * A2) a serial number should be assigned to the chunk. The serial * number SHOULD be a monotonically increasing number. The serial * numbers SHOULD be initialized at the start of the * association to the same value as the initial TSN. */ asoc->addip_serial = asoc->c.initial_tsn; asoc->strreset_outseq = asoc->c.initial_tsn; INIT_LIST_HEAD(&asoc->addip_chunk_list); INIT_LIST_HEAD(&asoc->asconf_ack_list); /* Make an empty list of remote transport addresses. */ INIT_LIST_HEAD(&asoc->peer.transport_addr_list); /* RFC 2960 5.1 Normal Establishment of an Association * * After the reception of the first data chunk in an * association the endpoint must immediately respond with a * sack to acknowledge the data chunk. Subsequent * acknowledgements should be done as described in Section * 6.2. * * [We implement this by telling a new association that it * already received one packet.] */ asoc->peer.sack_needed = 1; asoc->peer.sack_generation = 1; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); sctp_inq_set_th_handler(&asoc->base.inqueue, sctp_assoc_bh_rcv); /* Create an output queue. */ sctp_outq_init(asoc, &asoc->outqueue); sctp_ulpq_init(&asoc->ulpq, asoc); if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) goto stream_free; /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; sctp_assoc_update_frag_point(asoc); /* Assume that peer would support both address types unless we are * told otherwise. */ asoc->peer.ipv4_address = 1; if (asoc->base.sk->sk_family == PF_INET6) asoc->peer.ipv6_address = 1; INIT_LIST_HEAD(&asoc->asocs); asoc->default_stream = sp->default_stream; asoc->default_ppid = sp->default_ppid; asoc->default_flags = sp->default_flags; asoc->default_context = sp->default_context; asoc->default_timetolive = sp->default_timetolive; asoc->default_rcv_context = sp->default_rcv_context; /* AUTH related initializations */ INIT_LIST_HEAD(&asoc->endpoint_shared_keys); if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp)) goto stream_free; asoc->active_key_id = ep->active_key_id; asoc->strreset_enable = ep->strreset_enable; /* Save the hmacs and chunks list into this association */ if (ep->auth_hmacs_list) memcpy(asoc->c.auth_hmacs, ep->auth_hmacs_list, ntohs(ep->auth_hmacs_list->param_hdr.length)); if (ep->auth_chunk_list) memcpy(asoc->c.auth_chunks, ep->auth_chunk_list, ntohs(ep->auth_chunk_list->param_hdr.length)); /* Get the AUTH random number for this association */ p = (struct sctp_paramhdr *)asoc->c.auth_random; p->type = SCTP_PARAM_RANDOM; p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH); get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH); return asoc; stream_free: sctp_stream_free(&asoc->stream); sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); return NULL; } /* Allocate and initialize a new association */ struct sctp_association *sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp) { struct sctp_association *asoc; asoc = kzalloc(sizeof(*asoc), gfp); if (!asoc) goto fail; if (!sctp_association_init(asoc, ep, sk, scope, gfp)) goto fail_init; SCTP_DBG_OBJCNT_INC(assoc); pr_debug("Created asoc %p\n", asoc); return asoc; fail_init: kfree(asoc); fail: return NULL; } /* Free this association if possible. There may still be users, so * the actual deallocation may be delayed. */ void sctp_association_free(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; struct sctp_transport *transport; struct list_head *pos, *temp; int i; /* Only real associations count against the endpoint, so * don't bother for if this is a temporary association. */ if (!list_empty(&asoc->asocs)) { list_del(&asoc->asocs); /* Decrement the backlog value for a TCP-style listening * socket. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) sk_acceptq_removed(sk); } /* Mark as dead, so other users can know this structure is * going away. */ asoc->base.dead = true; /* Dispose of any data lying around in the outqueue. */ sctp_outq_free(&asoc->outqueue); /* Dispose of any pending messages for the upper layer. */ sctp_ulpq_free(&asoc->ulpq); /* Dispose of any pending chunks on the inqueue. */ sctp_inq_free(&asoc->base.inqueue); sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); /* Clean up the bound address list. */ sctp_bind_addr_free(&asoc->base.bind_addr); /* Do we need to go through all of our timers and * delete them? To be safe we will try to delete all, but we * should be able to go through and make a guess based * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { if (del_timer(&asoc->timers[i])) sctp_association_put(asoc); } /* Free peer's cached cookie. */ kfree(asoc->peer.cookie); kfree(asoc->peer.peer_random); kfree(asoc->peer.peer_chunks); kfree(asoc->peer.peer_hmacs); /* Release the transport structures. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); list_del_rcu(pos); sctp_unhash_transport(transport); sctp_transport_free(transport); } asoc->peer.transport_count = 0; sctp_asconf_queue_teardown(asoc); /* Free pending address space being deleted */ kfree(asoc->asconf_addr_del_pending); /* AUTH - Free the endpoint shared keys */ sctp_auth_destroy_keys(&asoc->endpoint_shared_keys); /* AUTH - Free the association shared key */ sctp_auth_key_put(asoc->asoc_shared_key); sctp_association_put(asoc); } /* Cleanup and free up an association. */ static void sctp_association_destroy(struct sctp_association *asoc) { if (unlikely(!asoc->base.dead)) { WARN(1, "Attempt to destroy undead association %p!\n", asoc); return; } sctp_endpoint_put(asoc->ep); sock_put(asoc->base.sk); if (asoc->assoc_id != 0) { spin_lock_bh(&sctp_assocs_id_lock); idr_remove(&sctp_assocs_id, asoc->assoc_id); spin_unlock_bh(&sctp_assocs_id_lock); } WARN_ON(atomic_read(&asoc->rmem_alloc)); kfree_rcu(asoc, rcu); SCTP_DBG_OBJCNT_DEC(assoc); } /* Change the primary destination address for the peer. */ void sctp_assoc_set_primary(struct sctp_association *asoc, struct sctp_transport *transport) { int changeover = 0; /* it's a changeover only if we already have a primary path * that we are changing */ if (asoc->peer.primary_path != NULL && asoc->peer.primary_path != transport) changeover = 1 ; asoc->peer.primary_path = transport; sctp_ulpevent_notify_peer_addr_change(transport, SCTP_ADDR_MADE_PRIM, 0); /* Set a default msg_name for events. */ memcpy(&asoc->peer.primary_addr, &transport->ipaddr, sizeof(union sctp_addr)); /* If the primary path is changing, assume that the * user wants to use this new path. */ if ((transport->state == SCTP_ACTIVE) || (transport->state == SCTP_UNKNOWN)) asoc->peer.active_path = transport; /* * SFR-CACC algorithm: * Upon the receipt of a request to change the primary * destination address, on the data structure for the new * primary destination, the sender MUST do the following: * * 1) If CHANGEOVER_ACTIVE is set, then there was a switch * to this destination address earlier. The sender MUST set * CYCLING_CHANGEOVER to indicate that this switch is a * double switch to the same destination address. * * Really, only bother is we have data queued or outstanding on * the association. */ if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen) return; if (transport->cacc.changeover_active) transport->cacc.cycling_changeover = changeover; /* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that * a changeover has occurred. */ transport->cacc.changeover_active = changeover; /* 3) The sender MUST store the next TSN to be sent in * next_tsn_at_change. */ transport->cacc.next_tsn_at_change = asoc->next_tsn; } /* Remove a transport from an association. */ void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer) { struct sctp_transport *transport; struct list_head *pos; struct sctp_chunk *ch; pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, &peer->ipaddr.sa); /* If we are to remove the current retran_path, update it * to the next peer before removing this peer from the list. */ if (asoc->peer.retran_path == peer) sctp_assoc_update_retran_path(asoc); /* Remove this peer from the list. */ list_del_rcu(&peer->transports); /* Remove this peer from the transport hashtable */ sctp_unhash_transport(peer); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; transport = list_entry(pos, struct sctp_transport, transports); /* Update any entries that match the peer to be deleted. */ if (asoc->peer.primary_path == peer) sctp_assoc_set_primary(asoc, transport); if (asoc->peer.active_path == peer) asoc->peer.active_path = transport; if (asoc->peer.retran_path == peer) asoc->peer.retran_path = transport; if (asoc->peer.last_data_from == peer) asoc->peer.last_data_from = transport; if (asoc->strreset_chunk && asoc->strreset_chunk->transport == peer) { asoc->strreset_chunk->transport = transport; sctp_transport_reset_reconf_timer(transport); } /* If we remove the transport an INIT was last sent to, set it to * NULL. Combined with the update of the retran path above, this * will cause the next INIT to be sent to the next available * transport, maintaining the cycle. */ if (asoc->init_last_sent_to == peer) asoc->init_last_sent_to = NULL; /* If we remove the transport an SHUTDOWN was last sent to, set it * to NULL. Combined with the update of the retran path above, this * will cause the next SHUTDOWN to be sent to the next available * transport, maintaining the cycle. */ if (asoc->shutdown_last_sent_to == peer) asoc->shutdown_last_sent_to = NULL; /* If we remove the transport an ASCONF was last sent to, set it to * NULL. */ if (asoc->addip_last_asconf && asoc->addip_last_asconf->transport == peer) asoc->addip_last_asconf->transport = NULL; /* If we have something on the transmitted list, we have to * save it off. The best place is the active path. */ if (!list_empty(&peer->transmitted)) { struct sctp_transport *active = asoc->peer.active_path; /* Reset the transport of each chunk on this list */ list_for_each_entry(ch, &peer->transmitted, transmitted_list) { ch->transport = NULL; ch->rtt_in_progress = 0; } list_splice_tail_init(&peer->transmitted, &active->transmitted); /* Start a T3 timer here in case it wasn't running so * that these migrated packets have a chance to get * retransmitted. */ if (!timer_pending(&active->T3_rtx_timer)) if (!mod_timer(&active->T3_rtx_timer, jiffies + active->rto)) sctp_transport_hold(active); } list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) if (ch->transport == peer) ch->transport = NULL; asoc->peer.transport_count--; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_REMOVED, 0); sctp_transport_free(peer); } /* Add a transport address to an association. */ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, const union sctp_addr *addr, const gfp_t gfp, const int peer_state) { struct sctp_transport *peer; struct sctp_sock *sp; unsigned short port; sp = sctp_sk(asoc->base.sk); /* AF_INET and AF_INET6 share common port field. */ port = ntohs(addr->v4.sin_port); pr_debug("%s: association:%p addr:%pISpc state:%d\n", __func__, asoc, &addr->sa, peer_state); /* Set the port if it has not been set yet. */ if (0 == asoc->peer.port) asoc->peer.port = port; /* Check to see if this is a duplicate. */ peer = sctp_assoc_lookup_paddr(asoc, addr); if (peer) { /* An UNKNOWN state is only set on transports added by * user in sctp_connectx() call. Such transports should be * considered CONFIRMED per RFC 4960, Section 5.4. */ if (peer->state == SCTP_UNKNOWN) { peer->state = SCTP_ACTIVE; } return peer; } peer = sctp_transport_new(asoc->base.net, addr, gfp); if (!peer) return NULL; sctp_transport_set_owner(peer, asoc); /* Initialize the peer's heartbeat interval based on the * association configured value. */ peer->hbinterval = asoc->hbinterval; peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; /* And the partial failure retrans threshold */ peer->pf_retrans = asoc->pf_retrans; /* And the primary path switchover retrans threshold */ peer->ps_retrans = asoc->ps_retrans; /* Initialize the peer's SACK delay timeout based on the * association configured value. */ peer->sackdelay = asoc->sackdelay; peer->sackfreq = asoc->sackfreq; if (addr->sa.sa_family == AF_INET6) { __be32 info = addr->v6.sin6_flowinfo; if (info) { peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK); peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } else { peer->flowlabel = asoc->flowlabel; } } peer->dscp = asoc->dscp; /* Enable/disable heartbeat, SACK delay, and path MTU discovery * based on association setting. */ peer->param_flags = asoc->param_flags; /* Initialize the pmtu of the transport. */ sctp_transport_route(peer, NULL, sp); /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. * If not and the current association PMTU is higher than the new * peer's PMTU, reset the association PMTU to the new peer's PMTU. */ sctp_assoc_set_pmtu(asoc, asoc->pathmtu ? min_t(int, peer->pathmtu, asoc->pathmtu) : peer->pathmtu); peer->pmtu_pending = 0; /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. */ sctp_packet_init(&peer->packet, peer, asoc->base.bind_addr.port, asoc->peer.port); /* 7.2.1 Slow-Start * * o The initial cwnd before DATA transmission or after a sufficiently * long idle period MUST be set to * min(4*MTU, max(2*MTU, 4380 bytes)) * * o The initial value of ssthresh MAY be arbitrarily high * (for example, implementations MAY use the size of the * receiver advertised window). */ peer->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); /* At this point, we may not have the receiver's advertised window, * so initialize ssthresh to the default value and it will be set * later when we process the INIT. */ peer->ssthresh = SCTP_DEFAULT_MAXWINDOW; peer->partial_bytes_acked = 0; peer->flight_size = 0; peer->burst_limited = 0; /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; sctp_max_rto(asoc, peer); /* Set the peer's active state. */ peer->state = peer_state; /* Add this peer into the transport hashtable */ if (sctp_hash_transport(peer)) { sctp_transport_free(peer); return NULL; } sctp_transport_pl_reset(peer); /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; sctp_ulpevent_notify_peer_addr_change(peer, SCTP_ADDR_ADDED, 0); /* If we do not yet have a primary path, set one. */ if (!asoc->peer.primary_path) { sctp_assoc_set_primary(asoc, peer); asoc->peer.retran_path = peer; } if (asoc->peer.active_path == asoc->peer.retran_path && peer->state != SCTP_UNCONFIRMED) { asoc->peer.retran_path = peer; } return peer; } /* Delete a transport address from an association. */ void sctp_assoc_del_peer(struct sctp_association *asoc, const union sctp_addr *addr) { struct list_head *pos; struct list_head *temp; struct sctp_transport *transport; list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); if (sctp_cmp_addr_exact(addr, &transport->ipaddr)) { /* Do book keeping for removing the peer and free it. */ sctp_assoc_rm_peer(asoc, transport); break; } } } /* Lookup a transport by address. */ struct sctp_transport *sctp_assoc_lookup_paddr( const struct sctp_association *asoc, const union sctp_addr *address) { struct sctp_transport *t; /* Cycle through all transports searching for a peer address. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (sctp_cmp_addr_exact(address, &t->ipaddr)) return t; } return NULL; } /* Remove all transports except a give one */ void sctp_assoc_del_nonprimary_peers(struct sctp_association *asoc, struct sctp_transport *primary) { struct sctp_transport *temp; struct sctp_transport *t; list_for_each_entry_safe(t, temp, &asoc->peer.transport_addr_list, transports) { /* if the current transport is not the primary one, delete it */ if (t != primary) sctp_assoc_rm_peer(asoc, t); } } /* Engage in transport control operations. * Mark the transport up or down and send a notification to the user. * Select and update the new active and retran paths. */ void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_transport *transport, enum sctp_transport_cmd command, sctp_sn_error_t error) { int spc_state = SCTP_ADDR_AVAILABLE; bool ulp_notify = true; /* Record the transition on the transport. */ switch (command) { case SCTP_TRANSPORT_UP: /* If we are moving from UNCONFIRMED state due * to heartbeat success, report the SCTP_ADDR_CONFIRMED * state to the user, otherwise report SCTP_ADDR_AVAILABLE. */ if (transport->state == SCTP_PF && asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else if (transport->state == SCTP_UNCONFIRMED && error == SCTP_HEARTBEAT_SUCCESS) spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: /* If the transport was never confirmed, do not transition it * to inactive state. Also, release the cached route since * there may be a better route next time. */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); ulp_notify = false; } break; case SCTP_TRANSPORT_PF: transport->state = SCTP_PF; if (asoc->pf_expose != SCTP_PF_EXPOSE_ENABLE) ulp_notify = false; else spc_state = SCTP_ADDR_POTENTIALLY_FAILED; break; default: return; } /* Generate and send a SCTP_PEER_ADDR_CHANGE notification * to the user. */ if (ulp_notify) sctp_ulpevent_notify_peer_addr_change(transport, spc_state, error); /* Select new active and retran paths. */ sctp_select_active_and_retran_path(asoc); } /* Hold a reference to an association. */ void sctp_association_hold(struct sctp_association *asoc) { refcount_inc(&asoc->base.refcnt); } /* Release a reference to an association and cleanup * if there are no more references. */ void sctp_association_put(struct sctp_association *asoc) { if (refcount_dec_and_test(&asoc->base.refcnt)) sctp_association_destroy(asoc); } /* Allocate the next TSN, Transmission Sequence Number, for the given * association. */ __u32 sctp_association_get_next_tsn(struct sctp_association *asoc) { /* From Section 1.6 Serial Number Arithmetic: * Transmission Sequence Numbers wrap around when they reach * 2**32 - 1. That is, the next TSN a DATA chunk MUST use * after transmitting TSN = 2*32 - 1 is TSN = 0. */ __u32 retval = asoc->next_tsn; asoc->next_tsn++; asoc->unack_data++; return retval; } /* Compare two addresses to see if they match. Wildcard addresses * only match themselves. */ int sctp_cmp_addr_exact(const union sctp_addr *ss1, const union sctp_addr *ss2) { struct sctp_af *af; af = sctp_get_af_specific(ss1->sa.sa_family); if (unlikely(!af)) return 0; return af->cmp_addr(ss1, ss2); } /* Return an ecne chunk to get prepended to a packet. * Note: We are sly and return a shared, prealloced chunk. FIXME: * No we don't, but we could/should. */ struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc) { if (!asoc->need_ecne) return NULL; /* Send ECNE if needed. * Not being able to allocate a chunk here is not deadly. */ return sctp_make_ecne(asoc, asoc->last_ecne_tsn); } /* * Find which transport this TSN was sent on. */ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc, __u32 tsn) { struct sctp_transport *active; struct sctp_transport *match; struct sctp_transport *transport; struct sctp_chunk *chunk; __be32 key = htonl(tsn); match = NULL; /* * FIXME: In general, find a more efficient data structure for * searching. */ /* * The general strategy is to search each transport's transmitted * list. Return which transport this TSN lives on. * * Let's be hopeful and check the active_path first. * Another optimization would be to know if there is only one * outbound path and not have to look for the TSN at all. * */ active = asoc->peer.active_path; list_for_each_entry(chunk, &active->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = active; goto out; } } /* If not found, go search all the other transports. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { if (transport == active) continue; list_for_each_entry(chunk, &transport->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { match = transport; goto out; } } } out: return match; } /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { struct sctp_association *asoc = container_of(work, struct sctp_association, base.inqueue.immediate); struct net *net = asoc->base.net; union sctp_subtype subtype; struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; int first_time = 1; /* is this the first time through the loop */ int error = 0; int state; /* The association should be held so we should be safe. */ ep = asoc->ep; inqueue = &asoc->base.inqueue; sctp_association_hold(asoc); while (NULL != (chunk = sctp_inq_pop(inqueue))) { state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); /* If the first chunk in the packet is AUTH, do special * processing specified in Section 6.3 of SCTP-AUTH spec */ if (first_time && subtype.chunk == SCTP_CID_AUTH) { struct sctp_chunkhdr *next_hdr; next_hdr = sctp_inq_peek(inqueue); if (!next_hdr) goto normal; /* If the next chunk is COOKIE-ECHO, skip the AUTH * chunk while saving a pointer to it so we can do * Authentication later (during cookie-echo * processing). */ if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { chunk->auth_chunk = skb_clone(chunk->skb, GFP_ATOMIC); chunk->auth = 1; continue; } } normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has * been sent to the peer during the association setup. It * MUST silently discard these chunks if they are not placed * after an AUTH chunk in the packet. */ if (sctp_auth_recv_cid(subtype.chunk, asoc) && !chunk->auth) continue; /* Remember where the last DATA chunk came from so we * know where to send the SACK. */ if (sctp_chunk_is_data(chunk)) asoc->peer.last_data_from = chunk->transport; else { SCTP_INC_STATS(net, SCTP_MIB_INCTRLCHUNKS); asoc->stats.ictrlchunks++; if (chunk->chunk_hdr->type == SCTP_CID_SACK) asoc->stats.isacks++; } if (chunk->transport) chunk->transport->last_time_heard = ktime_get(); /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state, ep, asoc, chunk, GFP_ATOMIC); /* Check to see if the association is freed in response to * the incoming chunk. If so, get out of the while loop. */ if (asoc->base.dead) break; /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; if (first_time) first_time = 0; } sctp_association_put(asoc); } /* This routine moves an association from its old sk to a new sk. */ void sctp_assoc_migrate(struct sctp_association *assoc, struct sock *newsk) { struct sctp_sock *newsp = sctp_sk(newsk); struct sock *oldsk = assoc->base.sk; /* Delete the association from the old endpoint's list of * associations. */ list_del_init(&assoc->asocs); /* Decrement the backlog value for a TCP-style socket. */ if (sctp_style(oldsk, TCP)) sk_acceptq_removed(oldsk); /* Release references to the old endpoint and the sock. */ sctp_endpoint_put(assoc->ep); sock_put(assoc->base.sk); /* Get a reference to the new endpoint. */ assoc->ep = newsp->ep; sctp_endpoint_hold(assoc->ep); /* Get a reference to the new sock. */ assoc->base.sk = newsk; sock_hold(assoc->base.sk); /* Add the association to the new endpoint's list of associations. */ sctp_endpoint_add_asoc(newsp->ep, assoc); } /* Update an association (possibly from unexpected COOKIE-ECHO processing). */ int sctp_assoc_update(struct sctp_association *asoc, struct sctp_association *new) { struct sctp_transport *trans; struct list_head *pos, *temp; /* Copy in new parameters of peer. */ asoc->c = new->c; asoc->peer.rwnd = new->peer.rwnd; asoc->peer.sack_needed = new->peer.sack_needed; asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, asoc->peer.i.initial_tsn, GFP_ATOMIC)) return -ENOMEM; /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { trans = list_entry(pos, struct sctp_transport, transports); if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) { sctp_assoc_rm_peer(asoc, trans); continue; } if (asoc->state >= SCTP_STATE_ESTABLISHED) sctp_transport_reset(trans); } /* If the case is A (association restart), use * initial_tsn as next_tsn. If the case is B, use * current next_tsn in case data sent to peer * has been discarded and needs retransmission. */ if (asoc->state >= SCTP_STATE_ESTABLISHED) { asoc->next_tsn = new->next_tsn; asoc->ctsn_ack_point = new->ctsn_ack_point; asoc->adv_peer_ack_point = new->adv_peer_ack_point; /* Reinitialize SSN for both local streams * and peer's streams. */ sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will * cause problems. */ sctp_ulpq_flush(&asoc->ulpq); /* reset the overall association error count so * that the restarted association doesn't get torn * down on the next retransmission timer. */ asoc->overall_error_count = 0; } else { /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; if (sctp_state(asoc, COOKIE_WAIT)) sctp_stream_update(&asoc->stream, &new->stream); /* get a new assoc id if we don't have one yet. */ if (sctp_assoc_set_id(asoc, GFP_ATOMIC)) return -ENOMEM; } /* SCTP-AUTH: Save the peer parameters from the new associations * and also move the association shared keys over */ kfree(asoc->peer.peer_random); asoc->peer.peer_random = new->peer.peer_random; new->peer.peer_random = NULL; kfree(asoc->peer.peer_chunks); asoc->peer.peer_chunks = new->peer.peer_chunks; new->peer.peer_chunks = NULL; kfree(asoc->peer.peer_hmacs); asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; return sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } /* Update the retran path for sending a retransmitted packet. * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: * * When there is outbound data to send and the primary path * becomes inactive (e.g., due to failures), or where the * SCTP user explicitly requests to send data to an * inactive destination transport address, before reporting * an error to its ULP, the SCTP endpoint should try to send * the data to an alternate active destination transport * address if one exists. * * When retransmitting data that timed out, if the endpoint * is multihomed, it should consider each source-destination * address pair in its retransmission selection policy. * When retransmitting timed-out data, the endpoint should * attempt to pick the most divergent source-destination * pair from the original source-destination pair to which * the packet was transmitted. * * Note: Rules for picking the most divergent source-destination * pair are an implementation decision and are not specified * within this document. * * Our basic strategy is to round-robin transports in priorities * according to sctp_trans_score() e.g., if no such * transport with state SCTP_ACTIVE exists, round-robin through * SCTP_UNKNOWN, etc. You get the picture. */ static u8 sctp_trans_score(const struct sctp_transport *trans) { switch (trans->state) { case SCTP_ACTIVE: return 3; /* best case */ case SCTP_UNKNOWN: return 2; case SCTP_PF: return 1; default: /* case SCTP_INACTIVE */ return 0; /* worst case */ } } static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1, struct sctp_transport *trans2) { if (trans1->error_count > trans2->error_count) { return trans2; } else if (trans1->error_count == trans2->error_count && ktime_after(trans2->last_time_heard, trans1->last_time_heard)) { return trans2; } else { return trans1; } } static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, struct sctp_transport *best) { u8 score_curr, score_best; if (best == NULL || curr == best) return curr; score_curr = sctp_trans_score(curr); score_best = sctp_trans_score(best); /* First, try a score-based selection if both transport states * differ. If we're in a tie, lets try to make a more clever * decision here based on error counts and last time heard. */ if (score_curr > score_best) return curr; else if (score_curr == score_best) return sctp_trans_elect_tie(best, curr); else return best; } void sctp_assoc_update_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans = asoc->peer.retran_path; struct sctp_transport *trans_next = NULL; /* We're done as we only have the one and only path. */ if (asoc->peer.transport_count == 1) return; /* If active_path and retran_path are the same and active, * then this is the only active path. Use it. */ if (asoc->peer.active_path == asoc->peer.retran_path && asoc->peer.active_path->state == SCTP_ACTIVE) return; /* Iterate from retran_path's successor back to retran_path. */ for (trans = list_next_entry(trans, transports); 1; trans = list_next_entry(trans, transports)) { /* Manually skip the head element. */ if (&trans->transports == &asoc->peer.transport_addr_list) continue; if (trans->state == SCTP_UNCONFIRMED) continue; trans_next = sctp_trans_elect_best(trans, trans_next); /* Active is good enough for immediate return. */ if (trans_next->state == SCTP_ACTIVE) break; /* We've reached the end, time to update path. */ if (trans == asoc->peer.retran_path) break; } asoc->peer.retran_path = trans_next; pr_debug("%s: association:%p updated new path to addr:%pISpc\n", __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } static void sctp_select_active_and_retran_path(struct sctp_association *asoc) { struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL; struct sctp_transport *trans_pf = NULL; /* Look for the two most recently used active transports. */ list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { /* Skip uninteresting transports. */ if (trans->state == SCTP_INACTIVE || trans->state == SCTP_UNCONFIRMED) continue; /* Keep track of the best PF transport from our * list in case we don't find an active one. */ if (trans->state == SCTP_PF) { trans_pf = sctp_trans_elect_best(trans, trans_pf); continue; } /* For active transports, pick the most recent ones. */ if (trans_pri == NULL || ktime_after(trans->last_time_heard, trans_pri->last_time_heard)) { trans_sec = trans_pri; trans_pri = trans; } else if (trans_sec == NULL || ktime_after(trans->last_time_heard, trans_sec->last_time_heard)) { trans_sec = trans; } } /* RFC 2960 6.4 Multi-Homed SCTP Endpoints * * By default, an endpoint should always transmit to the primary * path, unless the SCTP user explicitly specifies the * destination transport address (and possibly source transport * address) to use. [If the primary is active but not most recent, * bump the most recently used transport.] */ if ((asoc->peer.primary_path->state == SCTP_ACTIVE || asoc->peer.primary_path->state == SCTP_UNKNOWN) && asoc->peer.primary_path != trans_pri) { trans_sec = trans_pri; trans_pri = asoc->peer.primary_path; } /* We did not find anything useful for a possible retransmission * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) trans_sec = trans_pri; /* If we failed to find a usable transport, just camp on the * active or pick a PF iff it's the better choice. */ if (trans_pri == NULL) { trans_pri = sctp_trans_elect_best(asoc->peer.active_path, trans_pf); trans_sec = trans_pri; } /* Set the active and retran transports. */ asoc->peer.active_path = trans_pri; asoc->peer.retran_path = trans_sec; } struct sctp_transport * sctp_assoc_choose_alter_transport(struct sctp_association *asoc, struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ if (last_sent_to == NULL) { return asoc->peer.active_path; } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); return asoc->peer.retran_path; } } void sctp_assoc_update_frag_point(struct sctp_association *asoc) { int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu, sctp_datachk_len(&asoc->stream)); if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN - sctp_datachk_len(&asoc->stream)); asoc->frag_point = SCTP_TRUNC4(frag); } void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu) { if (asoc->pathmtu != pmtu) { asoc->pathmtu = pmtu; sctp_assoc_update_frag_point(asoc); } pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, asoc->pathmtu, asoc->frag_point); } /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) { struct sctp_transport *t; __u32 pmtu = 0; if (!asoc) return; /* Get the lowest pmtu of all the transports. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { sctp_transport_update_pmtu(t, atomic_read(&t->mtu_info)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) pmtu = t->pathmtu; } sctp_assoc_set_pmtu(asoc, pmtu); } /* Should we send a SACK to update our peer? */ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) { struct net *net = asoc->base.net; switch (asoc->state) { case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: case SCTP_STATE_SHUTDOWN_SENT: if ((asoc->rwnd > asoc->a_rwnd) && ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, (asoc->base.sk->sk_rcvbuf >> net->sctp.rwnd_upd_shift), asoc->pathmtu))) return true; break; default: break; } return false; } /* Increase asoc's rwnd by len and send any window update SACK if needed. */ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) { struct sctp_chunk *sack; struct timer_list *timer; if (asoc->rwnd_over) { if (asoc->rwnd_over >= len) { asoc->rwnd_over -= len; } else { asoc->rwnd += (len - asoc->rwnd_over); asoc->rwnd_over = 0; } } else { asoc->rwnd += len; } /* If we had window pressure, start recovering it * once our rwnd had reached the accumulated pressure * threshold. The idea is to recover slowly, but up * to the initial advertised window. */ if (asoc->rwnd_press) { int change = min(asoc->pathmtu, asoc->rwnd_press); asoc->rwnd += change; asoc->rwnd_press -= change; } pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->a_rwnd); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ if (sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " "a_rwnd:%u\n", __func__, asoc, asoc->rwnd, asoc->a_rwnd); sack = sctp_make_sack(asoc); if (!sack) return; asoc->peer.sack_needed = 0; sctp_outq_tail(&asoc->outqueue, sack, GFP_ATOMIC); /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; if (del_timer(timer)) sctp_association_put(asoc); } } /* Decrease asoc's rwnd by len. */ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) { int rx_count; int over = 0; if (unlikely(!asoc->rwnd || asoc->rwnd_over)) pr_debug("%s: association:%p has asoc->rwnd:%u, " "asoc->rwnd_over:%u!\n", __func__, asoc, asoc->rwnd, asoc->rwnd_over); if (asoc->ep->rcvbuf_policy) rx_count = atomic_read(&asoc->rmem_alloc); else rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) over = 1; if (asoc->rwnd >= len) { asoc->rwnd -= len; if (over) { asoc->rwnd_press += asoc->rwnd; asoc->rwnd = 0; } } else { asoc->rwnd_over += len - asoc->rwnd; asoc->rwnd = 0; } pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, asoc->rwnd_press); } /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. */ int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; if (!inet_v6_ipv6only(sk)) flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) flags |= SCTP_ADDR6_PEERSUPP; return sctp_bind_addr_copy(asoc->base.net, &asoc->base.bind_addr, &asoc->ep->base.bind_addr, scope, gfp, flags); } /* Build the association's bind address list from the cookie. */ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc, struct sctp_cookie *cookie, gfp_t gfp) { struct sctp_init_chunk *peer_init = (struct sctp_init_chunk *)(cookie + 1); int var_size2 = ntohs(peer_init->chunk_hdr.length); int var_size3 = cookie->raw_addr_list_len; __u8 *raw = (__u8 *)peer_init + var_size2; return sctp_raw_to_bind_addrs(&asoc->base.bind_addr, raw, var_size3, asoc->ep->base.bind_addr.port, gfp); } /* Lookup laddr in the bind address list of an association. */ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, const union sctp_addr *laddr) { int found = 0; if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) && sctp_bind_addr_match(&asoc->base.bind_addr, laddr, sctp_sk(asoc->base.sk))) found = 1; return found; } /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { bool preload = gfpflags_allow_blocking(gfp); int ret; /* If the id is already assigned, keep it. */ if (asoc->assoc_id) return 0; if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. */ ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); if (ret < 0) return ret; asoc->assoc_id = (sctp_assoc_t)ret; return 0; } /* Free the ASCONF queue */ static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc) { struct sctp_chunk *asconf; struct sctp_chunk *tmp; list_for_each_entry_safe(asconf, tmp, &asoc->addip_chunk_list, list) { list_del_init(&asconf->list); sctp_chunk_free(asconf); } } /* Free asconf_ack cache */ static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Clean up the ASCONF_ACK queue */ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc) { struct sctp_chunk *ack; struct sctp_chunk *tmp; /* We can remove all the entries from the queue up to * the "Peer-Sequence-Number". */ list_for_each_entry_safe(ack, tmp, &asoc->asconf_ack_list, transmitted_list) { if (ack->subh.addip_hdr->serial == htonl(asoc->peer.addip_serial)) break; list_del_init(&ack->transmitted_list); sctp_chunk_free(ack); } } /* Find the ASCONF_ACK whose serial number matches ASCONF */ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( const struct sctp_association *asoc, __be32 serial) { struct sctp_chunk *ack; /* Walk through the list of cached ASCONF-ACKs and find the * ack chunk whose serial number matches that of the request. */ list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) { if (sctp_chunk_pending(ack)) continue; if (ack->subh.addip_hdr->serial == serial) { sctp_chunk_hold(ack); return ack; } } return NULL; } void sctp_asconf_queue_teardown(struct sctp_association *asoc) { /* Free any cached ASCONF_ACK chunk. */ sctp_assoc_free_asconf_acks(asoc); /* Free the ASCONF queue. */ sctp_assoc_free_asconf_queue(asoc); /* Free any cached ASCONF chunk. */ if (asoc->addip_last_asconf) sctp_chunk_free(asoc->addip_last_asconf); } |
| 940 2 940 821 819 831 944 806 944 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor label definitions * * Copyright 2017 Canonical Ltd. */ #ifndef __AA_LABEL_H #define __AA_LABEL_H #include <linux/atomic.h> #include <linux/audit.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include "apparmor.h" #include "lib.h" struct aa_ns; #define LOCAL_VEC_ENTRIES 8 #define DEFINE_VEC(T, V) \ struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES]; \ struct aa_ ## T **(V) #define vec_setup(T, V, N, GFP) \ ({ \ if ((N) <= LOCAL_VEC_ENTRIES) { \ typeof(N) i; \ (V) = (_ ## V ## _localtmp); \ for (i = 0; i < (N); i++) \ (V)[i] = NULL; \ } else \ (V) = kzalloc(sizeof(struct aa_ ## T *) * (N), (GFP)); \ (V) ? 0 : -ENOMEM; \ }) #define vec_cleanup(T, V, N) \ do { \ int i; \ for (i = 0; i < (N); i++) { \ if (!IS_ERR_OR_NULL((V)[i])) \ aa_put_ ## T((V)[i]); \ } \ if ((V) != _ ## V ## _localtmp) \ kfree(V); \ } while (0) #define vec_last(VEC, SIZE) ((VEC)[(SIZE) - 1]) #define vec_ns(VEC, SIZE) (vec_last((VEC), (SIZE))->ns) #define vec_labelset(VEC, SIZE) (&vec_ns((VEC), (SIZE))->labels) #define cleanup_domain_vec(V, L) cleanup_label_vec((V), (L)->size) struct aa_profile; #define VEC_FLAG_TERMINATE 1 int aa_vec_unique(struct aa_profile **vec, int n, int flags); struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len, gfp_t gfp); #define aa_sort_and_merge_vec(N, V) \ aa_sort_and_merge_profiles((N), (struct aa_profile **)(V)) /* struct aa_labelset - set of labels for a namespace * * Labels are reference counted; aa_labelset does not contribute to label * reference counts. Once a label's last refcount is put it is removed from * the set. */ struct aa_labelset { rwlock_t lock; struct rb_root root; }; #define __labelset_for_each(LS, N) \ for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N)) enum label_flags { FLAG_HAT = 1, /* profile is a hat */ FLAG_UNCONFINED = 2, /* label unconfined only if all */ FLAG_NULL = 4, /* profile is null learning profile */ FLAG_IX_ON_NAME_ERROR = 8, /* fallback to ix on name lookup fail */ FLAG_IMMUTIBLE = 0x10, /* don't allow changes/replacement */ FLAG_USER_DEFINED = 0x20, /* user based profile - lower privs */ FLAG_NO_LIST_REF = 0x40, /* list doesn't keep profile ref */ FLAG_NS_COUNT = 0x80, /* carries NS ref count */ FLAG_IN_TREE = 0x100, /* label is in tree */ FLAG_PROFILE = 0x200, /* label is a profile */ FLAG_EXPLICIT = 0x400, /* explicit static label */ FLAG_STALE = 0x800, /* replaced/removed */ FLAG_RENAMED = 0x1000, /* label has renaming in it */ FLAG_REVOKED = 0x2000, /* label has revocation in it */ FLAG_DEBUG1 = 0x4000, FLAG_DEBUG2 = 0x8000, /* These flags must correspond with PATH_flags */ /* TODO: add new path flags */ }; struct aa_label; struct aa_proxy { struct kref count; struct aa_label __rcu *label; }; struct label_it { int i, j; }; /* struct aa_label - lazy labeling struct * @count: ref count of active users * @node: rbtree position * @rcu: rcu callback struct * @proxy: is set to the label that replaced this label * @hname: text representation of the label (MAYBE_NULL) * @flags: stale and other flags - values may change under label set lock * @secid: secid that references this label * @size: number of entries in @ent[] * @ent: set of profiles for label, actual size determined by @size */ struct aa_label { struct kref count; struct rb_node node; struct rcu_head rcu; struct aa_proxy *proxy; __counted char *hname; long flags; u32 secid; int size; struct aa_profile *vec[]; }; #define last_error(E, FN) \ do { \ int __subE = (FN); \ if (__subE) \ (E) = __subE; \ } while (0) #define label_isprofile(X) ((X)->flags & FLAG_PROFILE) #define label_unconfined(X) ((X)->flags & FLAG_UNCONFINED) #define unconfined(X) label_unconfined(X) #define label_is_stale(X) ((X)->flags & FLAG_STALE) #define __label_make_stale(X) ((X)->flags |= FLAG_STALE) #define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size)) #define labels_set(X) (&labels_ns(X)->labels) #define labels_view(X) labels_ns(X) #define labels_profile(X) ((X)->vec[(X)->size - 1]) int aa_label_next_confined(struct aa_label *l, int i); /* for each profile in a label */ #define label_for_each(I, L, P) \ for ((I).i = 0; ((P) = (L)->vec[(I).i]); ++((I).i)) /* assumes break/goto ended label_for_each */ #define label_for_each_cont(I, L, P) \ for (++((I).i); ((P) = (L)->vec[(I).i]); ++((I).i)) #define next_comb(I, L1, L2) \ do { \ (I).j++; \ if ((I).j >= (L2)->size) { \ (I).i++; \ (I).j = 0; \ } \ } while (0) /* for each combination of P1 in L1, and P2 in L2 */ #define label_for_each_comb(I, L1, L2, P1, P2) \ for ((I).i = (I).j = 0; \ ((P1) = (L1)->vec[(I).i]) && ((P2) = (L2)->vec[(I).j]); \ (I) = next_comb(I, L1, L2)) #define fn_for_each_comb(L1, L2, P1, P2, FN) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each_comb(i, (L1), (L2), (P1), (P2)) { \ last_error(__E, (FN)); \ } \ __E; \ }) /* for each profile that is enforcing confinement in a label */ #define label_for_each_confined(I, L, P) \ for ((I).i = aa_label_next_confined((L), 0); \ ((P) = (L)->vec[(I).i]); \ (I).i = aa_label_next_confined((L), (I).i + 1)) #define label_for_each_in_merge(I, A, B, P) \ for ((I).i = (I).j = 0; \ ((P) = aa_label_next_in_merge(&(I), (A), (B))); \ ) #define label_for_each_not_in_set(I, SET, SUB, P) \ for ((I).i = (I).j = 0; \ ((P) = __aa_label_next_not_in_set(&(I), (SET), (SUB))); \ ) #define next_in_ns(i, NS, L) \ ({ \ typeof(i) ___i = (i); \ while ((L)->vec[___i] && (L)->vec[___i]->ns != (NS)) \ (___i)++; \ (___i); \ }) #define label_for_each_in_ns(I, NS, L, P) \ for ((I).i = next_in_ns(0, (NS), (L)); \ ((P) = (L)->vec[(I).i]); \ (I).i = next_in_ns((I).i + 1, (NS), (L))) #define fn_for_each_in_ns(L, P, FN) \ ({ \ struct label_it __i; \ struct aa_ns *__ns = labels_ns(L); \ int __E = 0; \ label_for_each_in_ns(__i, __ns, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_XXX(L, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each(L, P, FN) fn_for_each_XXX(L, P, FN) #define fn_for_each_confined(L, P, FN) fn_for_each_XXX(L, P, FN, _confined) #define fn_for_each2_XXX(L1, L2, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L1), (L2), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_in_merge(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _in_merge) #define fn_for_each_not_in_set(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set) #define LABEL_MEDIATES(L, C) \ ({ \ struct aa_profile *profile; \ struct label_it i; \ int ret = 0; \ label_for_each(i, (L), profile) { \ if (RULE_MEDIATES(&profile->rules, (C))) { \ ret = 1; \ break; \ } \ } \ ret; \ }) void aa_labelset_destroy(struct aa_labelset *ls); void aa_labelset_init(struct aa_labelset *ls); void __aa_labelset_update_subtree(struct aa_ns *ns); void aa_label_destroy(struct aa_label *label); void aa_label_free(struct aa_label *label); void aa_label_kref(struct kref *kref); bool aa_label_init(struct aa_label *label, int size, gfp_t gfp); struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp); bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub); bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub); struct aa_profile *__aa_label_next_not_in_set(struct label_it *I, struct aa_label *set, struct aa_label *sub); bool aa_label_remove(struct aa_label *label); struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *l); bool aa_label_replace(struct aa_label *old, struct aa_label *new); bool aa_label_make_newest(struct aa_labelset *ls, struct aa_label *old, struct aa_label *new); struct aa_label *aa_label_find(struct aa_label *l); struct aa_profile *aa_label_next_in_merge(struct label_it *I, struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b, gfp_t gfp); bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp); #define FLAGS_NONE 0 #define FLAG_SHOW_MODE 1 #define FLAG_VIEW_SUBNS 2 #define FLAG_HIDDEN_UNCONFINED 4 #define FLAG_ABS_ROOT 8 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_label *label, int flags); int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_audit(struct audit_buffer *ab, struct aa_label *label, gfp_t gfp); void aa_label_seq_print(struct seq_file *f, struct aa_label *label, gfp_t gfp); void aa_label_printk(struct aa_label *label, gfp_t gfp); struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, size_t n, gfp_t gfp, bool create, bool force_stack); struct aa_label *aa_label_parse(struct aa_label *base, const char *str, gfp_t gfp, bool create, bool force_stack); static inline const char *aa_label_strn_split(const char *str, int n) { const char *pos; aa_state_t state; state = aa_dfa_matchn_until(stacksplitdfa, DFA_START, str, n, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } static inline const char *aa_label_str_split(const char *str) { const char *pos; aa_state_t state; state = aa_dfa_match_until(stacksplitdfa, DFA_START, str, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } struct aa_perms; struct aa_ruleset; int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms); /** * __aa_get_label - get a reference count to uncounted label reference * @l: reference to get a count on * * Returns: pointer to reference OR NULL if race is lost and reference is * being repeated. * Requires: lock held, and the return code MUST be checked */ static inline struct aa_label *__aa_get_label(struct aa_label *l) { if (l && kref_get_unless_zero(&l->count)) return l; return NULL; } static inline struct aa_label *aa_get_label(struct aa_label *l) { if (l) kref_get(&(l->count)); return l; } /** * aa_get_label_rcu - increment refcount on a label that can be replaced * @l: pointer to label that can be replaced (NOT NULL) * * Returns: pointer to a refcounted label. * else NULL if no label */ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l) { struct aa_label *c; rcu_read_lock(); do { c = rcu_dereference(*l); } while (c && !kref_get_unless_zero(&c->count)); rcu_read_unlock(); return c; } /** * aa_get_newest_label - find the newest version of @l * @l: the label to check for newer versions of * * Returns: refcounted newest version of @l taking into account * replacement, renames and removals * return @l. */ static inline struct aa_label *aa_get_newest_label(struct aa_label *l) { if (!l) return NULL; if (label_is_stale(l)) { struct aa_label *tmp; AA_BUG(!l->proxy); AA_BUG(!l->proxy->label); /* BUG: only way this can happen is @l ref count and its * replacement count have gone to 0 and are on their way * to destruction. ie. we have a refcounting error */ tmp = aa_get_label_rcu(&l->proxy->label); AA_BUG(!tmp); return tmp; } return aa_get_label(l); } static inline void aa_put_label(struct aa_label *l) { if (l) kref_put(&l->count, aa_label_kref); } struct aa_proxy *aa_alloc_proxy(struct aa_label *l, gfp_t gfp); void aa_proxy_kref(struct kref *kref); static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) { if (proxy) kref_get(&(proxy->count)); return proxy; } static inline void aa_put_proxy(struct aa_proxy *proxy) { if (proxy) kref_put(&proxy->count, aa_proxy_kref); } void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new); #endif /* __AA_LABEL_H */ |
| 5 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_PKT_CLS_H #define __NET_PKT_CLS_H #include <linux/pkt_cls.h> #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> #include <net/net_namespace.h> /* TC action not accessible from user space */ #define TC_ACT_CONSUMED (TC_ACT_VALUE_MAX + 1) /* Basic packet classifier frontend definitions. */ struct tcf_walker { int stop; int skip; int count; bool nonempty; unsigned long cookie; int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *); }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); void unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #define NET_CLS_ALIAS_PREFIX "net-cls-" #define MODULE_ALIAS_NET_CLS(kind) MODULE_ALIAS(NET_CLS_ALIAS_PREFIX kind) struct tcf_block_ext_info { enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; u32 block_index; }; struct tcf_qevent { struct tcf_block *block; struct tcf_block_ext_info info; struct tcf_proto __rcu *filter_chain; }; struct tcf_block_cb; bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index); void tcf_chain_put_by_act(struct tcf_chain *chain); struct tcf_chain *tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain); struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack); int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack); void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, int police, struct tcf_proto *tp, u32 handle, bool used_action_miss); static inline bool tcf_block_shared(struct tcf_block *block) { return block->index; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return block && block->index; } #ifdef CONFIG_NET_CLS_ACT DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); static inline bool tcf_block_bypass_sw(struct tcf_block *block) { return block && block->bypass_wanted; } #endif static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { WARN_ON(tcf_block_shared(block)); return block->q; } int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); static inline bool tc_cls_stats_dump(struct tcf_proto *tp, struct tcf_walker *arg, void *filter) { if (arg->count >= arg->skip && arg->fn(tp, filter, arg) < 0) { arg->stop = 1; return false; } arg->count++; return true; } #else static inline bool tcf_block_shared(struct tcf_block *block) { return false; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return false; } static inline int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack) { return 0; } static inline int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_block_put(struct tcf_block *block) { } static inline void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { } static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; } static inline int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { return TC_ACT_UNSPEC; } #endif static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) { return xchg(clp, cl); } static inline void __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base) { unsigned long cl; cl = q->ops->cl_ops->bind_tcf(q, base, r->classid); cl = __cls_set_class(&r->class, cl); if (cl) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base) { struct Qdisc *q = tp->chain->block->q; /* Check q as it is not set for shared blocks. In that case, * setting class is not supported. */ if (!q) return; sch_tree_lock(q); __tcf_bind_filter(q, r, base); sch_tree_unlock(q); } static inline void __tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r) { unsigned long cl; if ((cl = __cls_set_class(&r->class, 0)) != 0) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) { struct Qdisc *q = tp->chain->block->q; if (!q) return; __tcf_unbind_filter(q, r); } static inline void tc_cls_bind_class(u32 classid, unsigned long cl, void *q, struct tcf_result *res, unsigned long base) { if (res->classid == classid) { if (cl) __tcf_bind_filter(q, res, base); else __tcf_unbind_filter(q, res); } } struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ int nr_actions; struct tc_action **actions; struct net *net; netns_tracker ns_tracker; struct tcf_exts_miss_cookie_node *miss_cookie_node; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. */ int action; int police; }; static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net, int action, int police) { #ifdef CONFIG_NET_CLS return tcf_exts_init_ex(exts, net, action, police, NULL, 0, false); #else return -EOPNOTSUPP; #endif } /* Return false if the netns is being destroyed in cleanup_net(). Callers * need to do cleanup synchronously in this case, otherwise may race with * tc_action_net_exit(). Return true for other cases. */ static inline bool tcf_exts_get_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT exts->net = maybe_get_net(exts->net); if (exts->net) netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL); return exts->net != NULL; #else return true; #endif } static inline void tcf_exts_put_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT if (exts->net) put_net_track(exts->net, &exts->ns_tracker); #endif } #ifdef CONFIG_NET_CLS_ACT #define tcf_exts_for_each_action(i, a, exts) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = (exts)->actions[i]); i++) #else #define tcf_exts_for_each_action(i, a, exts) \ for (; 0; (void)(i), (void)(a), (void)(exts)) #endif #define tcf_act_for_each_action(i, a, actions) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++) static inline bool tc_act_in_hw(struct tc_action *act) { return !!act->in_hw_count; } static inline void tcf_exts_hw_stats_update(const struct tcf_exts *exts, struct flow_stats *stats, bool use_act_stats) { #ifdef CONFIG_NET_CLS_ACT int i; for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; if (use_act_stats || tc_act_in_hw(a)) { if (!tcf_action_update_hw_stats(a)) continue; } preempt_disable(); tcf_action_stats_update(a, stats->bytes, stats->pkts, stats->drops, stats->lastused, true); preempt_enable(); a->used_hw_stats = stats->used_hw_stats; a->used_hw_stats_valid = stats->used_hw_stats_valid; } #endif } /** * tcf_exts_has_actions - check if at least one action is present * @exts: tc filter extensions handle * * Returns true if at least one action is present. */ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT return exts->nr_actions; #else return false; #endif } /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer * @exts: tc filter extensions handle * @res: desired result * * Executes all configured extensions. Returns TC_ACT_OK on a normal execution, * a negative number if the filter must be considered unmatched or * a positive action code (TC_ACT_*) which must be returned to the * underlying layer. */ static inline int tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT return tcf_action_exec(skb, exts->actions, exts->nr_actions, res); #endif return TC_ACT_OK; } static inline int tcf_exts_exec_ex(struct sk_buff *skb, struct tcf_exts *exts, int act_index, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT return tcf_action_exec(skb, exts->actions + act_index, exts->nr_actions - act_index, res); #else return TC_ACT_OK; #endif } int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** * struct tcf_pkt_info - packet information * * @ptr: start of the pkt data * @nexthdr: offset of the next header */ struct tcf_pkt_info { unsigned char * ptr; int nexthdr; }; #ifdef CONFIG_NET_EMATCH struct tcf_ematch_ops; /** * struct tcf_ematch - extended match (ematch) * * @matchid: identifier to allow userspace to reidentify a match * @flags: flags specifying attributes and the relation to other matches * @ops: the operations lookup table of the corresponding ematch module * @datalen: length of the ematch specific configuration data * @data: ematch specific data * @net: the network namespace */ struct tcf_ematch { struct tcf_ematch_ops * ops; unsigned long data; unsigned int datalen; u16 matchid; u16 flags; struct net *net; }; static inline int tcf_em_is_container(struct tcf_ematch *em) { return !em->ops; } static inline int tcf_em_is_simple(struct tcf_ematch *em) { return em->flags & TCF_EM_SIMPLE; } static inline int tcf_em_is_inverted(struct tcf_ematch *em) { return em->flags & TCF_EM_INVERT; } static inline int tcf_em_last_match(struct tcf_ematch *em) { return (em->flags & TCF_EM_REL_MASK) == TCF_EM_REL_END; } static inline int tcf_em_early_end(struct tcf_ematch *em, int result) { if (tcf_em_last_match(em)) return 1; if (result == 0 && em->flags & TCF_EM_REL_AND) return 1; if (result != 0 && em->flags & TCF_EM_REL_OR) return 1; return 0; } /** * struct tcf_ematch_tree - ematch tree handle * * @hdr: ematch tree header supplied by userspace * @matches: array of ematches */ struct tcf_ematch_tree { struct tcf_ematch_tree_hdr hdr; struct tcf_ematch * matches; }; /** * struct tcf_ematch_ops - ematch module operations * * @kind: identifier (kind) of this ematch module * @datalen: length of expected configuration data (optional) * @change: called during validation (optional) * @match: called during ematch tree evaluation, must return 1/0 * @destroy: called during destroyage (optional) * @dump: called during dumping process (optional) * @owner: owner, must be set to THIS_MODULE * @link: link to previous/next ematch module (internal use) */ struct tcf_ematch_ops { int kind; int datalen; int (*change)(struct net *net, void *, int, struct tcf_ematch *); int (*match)(struct sk_buff *, struct tcf_ematch *, struct tcf_pkt_info *); void (*destroy)(struct tcf_ematch *); int (*dump)(struct sk_buff *, struct tcf_ematch *); struct module *owner; struct list_head link; }; int tcf_em_register(struct tcf_ematch_ops *); void tcf_em_unregister(struct tcf_ematch_ops *); int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *, struct tcf_ematch_tree *); void tcf_em_tree_destroy(struct tcf_ematch_tree *); int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int); int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** * tcf_em_tree_match - evaulate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation * @info: packet information examined by classifier * * This function matches @skb against the ematch tree in @tree by going * through all ematches respecting their logic relations returning * as soon as the result is obvious. * * Returns 1 if the ematch tree as-one matches, no ematches are configured * or ematch is not enabled in the kernel, otherwise 0 is returned. */ static inline int tcf_em_tree_match(struct sk_buff *skb, struct tcf_ematch_tree *tree, struct tcf_pkt_info *info) { if (tree->hdr.nmatches) return __tcf_em_tree_match(skb, tree, info); else return 1; } #define MODULE_ALIAS_TCF_EMATCH(kind) MODULE_ALIAS("ematch-kind-" __stringify(kind)) #else /* CONFIG_NET_EMATCH */ struct tcf_ematch_tree { }; #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0) #define tcf_em_tree_destroy(t) do { (void)(t); } while(0) #define tcf_em_tree_dump(skb, t, tlv) (0) #define tcf_em_tree_match(skb, t, info) ((void)(info), 1) #endif /* CONFIG_NET_EMATCH */ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) { switch (layer) { case TCF_LAYER_LINK: return skb_mac_header(skb); case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: return skb_transport_header(skb); } return NULL; } static inline int tcf_valid_offset(const struct sk_buff *skb, const unsigned char *ptr, const int len) { return likely((ptr + len) <= skb_tail_pointer(skb) && ptr >= skb->head && (ptr <= (ptr + len))); } static inline int tcf_change_indev(struct net *net, struct nlattr *indev_tlv, struct netlink_ext_ack *extack) { char indev[IFNAMSIZ]; struct net_device *dev; if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Interface name too long"); return -EINVAL; } dev = __dev_get_by_name(net, indev); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Network device not found"); return -ENODEV; } return dev->ifindex; } static inline bool tcf_match_indev(struct sk_buff *skb, int ifindex) { if (!ifindex) return true; if (!skb->skb_iif) return false; return ifindex == skb->skb_iif; } int tc_setup_offload_action(struct flow_action *flow_action, const struct tcf_exts *exts, struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, struct tc_action *actions[], u32 miss_cookie_base, struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *old_flags, unsigned int *old_in_hw_count, u32 *new_flags, unsigned int *new_in_hw_count, bool rtnl_held); int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, enum tc_setup_type type, void *type_data, void *cb_priv, u32 *flags, unsigned int *in_hw_count); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); #ifdef CONFIG_NET_CLS_ACT int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch); int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret); int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe); #else static inline int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) { } static inline int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline struct sk_buff * tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret) { return skb; } static inline int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) { return 0; } #endif struct tc_cls_u32_knode { struct tcf_exts *exts; struct tcf_result *res; struct tc_u32_sel *sel; u32 handle; u32 val; u32 mask; u32 link_handle; u8 fshift; }; struct tc_cls_u32_hnode { u32 handle; u32 prio; unsigned int divisor; }; enum tc_clsu32_command { TC_CLSU32_NEW_KNODE, TC_CLSU32_REPLACE_KNODE, TC_CLSU32_DELETE_KNODE, TC_CLSU32_NEW_HNODE, TC_CLSU32_REPLACE_HNODE, TC_CLSU32_DELETE_HNODE, }; struct tc_cls_u32_offload { struct flow_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { struct tc_cls_u32_knode knode; struct tc_cls_u32_hnode hnode; }; }; static inline bool tc_can_offload(const struct net_device *dev) { return dev->features & NETIF_F_HW_TC; } static inline bool tc_can_offload_extack(const struct net_device *dev, struct netlink_ext_ack *extack) { bool can = tc_can_offload(dev); if (!can) NL_SET_ERR_MSG(extack, "TC offload is disabled on net device"); return can; } static inline bool tc_cls_can_offload_and_chain0(const struct net_device *dev, struct flow_cls_common_offload *common) { if (!tc_can_offload_extack(dev, common->extack)) return false; if (common->chain_index) { NL_SET_ERR_MSG(common->extack, "Driver supports only offload of chain 0"); return false; } return true; } static inline bool tc_skip_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; } static inline bool tc_skip_sw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false; } /* SKIP_HW and SKIP_SW are mutually exclusive flags. */ static inline bool tc_flags_valid(u32 flags) { if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW | TCA_CLS_FLAGS_VERBOSE)) return false; flags &= TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW; if (!(flags ^ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW))) return false; return true; } static inline bool tc_in_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false; } static inline void tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, const struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) { struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); if (tc_skb_ext) memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); return tc_skb_ext; } #endif enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, TC_CLSMATCHALL_STATS, }; struct tc_cls_matchall_offload { struct flow_cls_common_offload common; enum tc_matchall_command command; struct flow_rule *rule; struct flow_stats stats; bool use_act_stats; unsigned long cookie; }; enum tc_clsbpf_command { TC_CLSBPF_OFFLOAD, TC_CLSBPF_STATS, }; struct tc_cls_bpf_offload { struct flow_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; struct bpf_prog *oldprog; const char *name; bool exts_integrated; }; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers */ struct tc_cookie { u8 *data; u32 len; struct rcu_head rcu; }; struct tc_qopt_offload_stats { struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; enum tc_mq_command { TC_MQ_CREATE, TC_MQ_DESTROY, TC_MQ_STATS, TC_MQ_GRAFT, }; struct tc_mq_opt_offload_graft_params { unsigned long queue; u32 child_handle; }; struct tc_mq_qopt_offload { enum tc_mq_command command; u32 handle; union { struct tc_qopt_offload_stats stats; struct tc_mq_opt_offload_graft_params graft_params; }; }; enum tc_htb_command { /* Root */ TC_HTB_CREATE, /* Initialize HTB offload. */ TC_HTB_DESTROY, /* Destroy HTB offload. */ /* Classes */ /* Allocate qid and create leaf. */ TC_HTB_LEAF_ALLOC_QUEUE, /* Convert leaf to inner, preserve and return qid, create new leaf. */ TC_HTB_LEAF_TO_INNER, /* Delete leaf, while siblings remain. */ TC_HTB_LEAF_DEL, /* Delete leaf, convert parent to leaf, preserving qid. */ TC_HTB_LEAF_DEL_LAST, /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */ TC_HTB_LEAF_DEL_LAST_FORCE, /* Modify parameters of a node. */ TC_HTB_NODE_MODIFY, /* Class qdisc */ TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */ }; struct tc_htb_qopt_offload { struct netlink_ext_ack *extack; enum tc_htb_command command; u32 parent_classid; u16 classid; u16 qid; u32 quantum; u64 rate; u64 ceil; u8 prio; }; #define TC_HTB_CLASSID_ROOT U32_MAX enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, TC_RED_STATS, TC_RED_XSTATS, TC_RED_GRAFT, }; struct tc_red_qopt_offload_params { u32 min; u32 max; u32 probability; u32 limit; bool is_ecn; bool is_harddrop; bool is_nodrop; struct gnet_stats_queue *qstats; }; struct tc_red_qopt_offload { enum tc_red_command command; u32 handle; u32 parent; union { struct tc_red_qopt_offload_params set; struct tc_qopt_offload_stats stats; struct red_stats *xstats; u32 child_handle; }; }; enum tc_gred_command { TC_GRED_REPLACE, TC_GRED_DESTROY, TC_GRED_STATS, }; struct tc_gred_vq_qopt_offload_params { bool present; u32 limit; u32 prio; u32 min; u32 max; bool is_ecn; bool is_harddrop; u32 probability; /* Only need backlog, see struct tc_prio_qopt_offload_params */ u32 *backlog; }; struct tc_gred_qopt_offload_params { bool grio_on; bool wred_on; unsigned int dp_cnt; unsigned int dp_def; struct gnet_stats_queue *qstats; struct tc_gred_vq_qopt_offload_params tab[MAX_DPs]; }; struct tc_gred_qopt_offload_stats { struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; struct tc_gred_qopt_offload { enum tc_gred_command command; u32 handle; u32 parent; union { struct tc_gred_qopt_offload_params set; struct tc_gred_qopt_offload_stats stats; }; }; enum tc_prio_command { TC_PRIO_REPLACE, TC_PRIO_DESTROY, TC_PRIO_STATS, TC_PRIO_GRAFT, }; struct tc_prio_qopt_offload_params { int bands; u8 priomap[TC_PRIO_MAX + 1]; /* At the point of un-offloading the Qdisc, the reported backlog and * qlen need to be reduced by the portion that is in HW. */ struct gnet_stats_queue *qstats; }; struct tc_prio_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_prio_qopt_offload { enum tc_prio_command command; u32 handle; u32 parent; union { struct tc_prio_qopt_offload_params replace_params; struct tc_qopt_offload_stats stats; struct tc_prio_qopt_offload_graft_params graft_params; }; }; enum tc_root_command { TC_ROOT_GRAFT, }; struct tc_root_qopt_offload { enum tc_root_command command; u32 handle; bool ingress; }; enum tc_ets_command { TC_ETS_REPLACE, TC_ETS_DESTROY, TC_ETS_STATS, TC_ETS_GRAFT, }; struct tc_ets_qopt_offload_replace_params { unsigned int bands; u8 priomap[TC_PRIO_MAX + 1]; unsigned int quanta[TCQ_ETS_MAX_BANDS]; /* 0 for strict bands. */ unsigned int weights[TCQ_ETS_MAX_BANDS]; struct gnet_stats_queue *qstats; }; struct tc_ets_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_ets_qopt_offload { enum tc_ets_command command; u32 handle; u32 parent; union { struct tc_ets_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; struct tc_ets_qopt_offload_graft_params graft_params; }; }; enum tc_tbf_command { TC_TBF_REPLACE, TC_TBF_DESTROY, TC_TBF_STATS, TC_TBF_GRAFT, }; struct tc_tbf_qopt_offload_replace_params { struct psched_ratecfg rate; u32 max_size; struct gnet_stats_queue *qstats; }; struct tc_tbf_qopt_offload { enum tc_tbf_command command; u32 handle; u32 parent; union { struct tc_tbf_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; u32 child_handle; }; }; enum tc_fifo_command { TC_FIFO_REPLACE, TC_FIFO_DESTROY, TC_FIFO_STATS, }; struct tc_fifo_qopt_offload { enum tc_fifo_command command; u32 handle; u32 parent; union { struct tc_qopt_offload_stats stats; }; }; #ifdef CONFIG_NET_CLS_ACT DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); void tc_skb_ext_tc_enable(void); void tc_skb_ext_tc_disable(void); #define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) #else /* CONFIG_NET_CLS_ACT */ static inline void tc_skb_ext_tc_enable(void) { } static inline void tc_skb_ext_tc_disable(void) { } #define tc_skb_ext_tc_enabled() false #endif #endif |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Device management routines * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/slab.h> #include <linux/time.h> #include <linux/export.h> #include <linux/errno.h> #include <sound/core.h> /** * snd_device_new - create an ALSA device component * @card: the card instance * @type: the device type, SNDRV_DEV_XXX * @device_data: the data pointer of this device * @ops: the operator table * * Creates a new device component for the given data pointer. * The device will be assigned to the card and managed together * by the card. * * The data pointer plays a role as the identifier, too, so the * pointer address must be unique and unchanged. * * Return: Zero if successful, or a negative error code on failure. */ int snd_device_new(struct snd_card *card, enum snd_device_type type, void *device_data, const struct snd_device_ops *ops) { struct snd_device *dev; struct list_head *p; if (snd_BUG_ON(!card || !device_data || !ops)) return -ENXIO; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; INIT_LIST_HEAD(&dev->list); dev->card = card; dev->type = type; dev->state = SNDRV_DEV_BUILD; dev->device_data = device_data; dev->ops = ops; /* insert the entry in an incrementally sorted list */ list_for_each_prev(p, &card->devices) { struct snd_device *pdev = list_entry(p, struct snd_device, list); if ((unsigned int)pdev->type <= (unsigned int)type) break; } list_add(&dev->list, p); return 0; } EXPORT_SYMBOL(snd_device_new); static void __snd_device_disconnect(struct snd_device *dev) { if (dev->state == SNDRV_DEV_REGISTERED) { if (dev->ops->dev_disconnect && dev->ops->dev_disconnect(dev)) dev_err(dev->card->dev, "device disconnect failure\n"); dev->state = SNDRV_DEV_DISCONNECTED; } } static void __snd_device_free(struct snd_device *dev) { /* unlink */ list_del(&dev->list); __snd_device_disconnect(dev); if (dev->ops->dev_free) { if (dev->ops->dev_free(dev)) dev_err(dev->card->dev, "device free failure\n"); } kfree(dev); } static struct snd_device *look_for_dev(struct snd_card *card, void *device_data) { struct snd_device *dev; list_for_each_entry(dev, &card->devices, list) if (dev->device_data == device_data) return dev; return NULL; } /** * snd_device_disconnect - disconnect the device * @card: the card instance * @device_data: the data pointer to disconnect * * Turns the device into the disconnection state, invoking * dev_disconnect callback, if the device was already registered. * * Usually called from snd_card_disconnect(). * * Return: Zero if successful, or a negative error code on failure or if the * device not found. */ void snd_device_disconnect(struct snd_card *card, void *device_data) { struct snd_device *dev; if (snd_BUG_ON(!card || !device_data)) return; dev = look_for_dev(card, device_data); if (dev) __snd_device_disconnect(dev); else dev_dbg(card->dev, "device disconnect %p (from %pS), not found\n", device_data, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(snd_device_disconnect); /** * snd_device_free - release the device from the card * @card: the card instance * @device_data: the data pointer to release * * Removes the device from the list on the card and invokes the * callbacks, dev_disconnect and dev_free, corresponding to the state. * Then release the device. */ void snd_device_free(struct snd_card *card, void *device_data) { struct snd_device *dev; if (snd_BUG_ON(!card || !device_data)) return; dev = look_for_dev(card, device_data); if (dev) __snd_device_free(dev); else dev_dbg(card->dev, "device free %p (from %pS), not found\n", device_data, __builtin_return_address(0)); } EXPORT_SYMBOL(snd_device_free); static int __snd_device_register(struct snd_device *dev) { if (dev->state == SNDRV_DEV_BUILD) { if (dev->ops->dev_register) { int err = dev->ops->dev_register(dev); if (err < 0) return err; } dev->state = SNDRV_DEV_REGISTERED; } return 0; } /** * snd_device_register - register the device * @card: the card instance * @device_data: the data pointer to register * * Registers the device which was already created via * snd_device_new(). Usually this is called from snd_card_register(), * but it can be called later if any new devices are created after * invocation of snd_card_register(). * * Return: Zero if successful, or a negative error code on failure or if the * device not found. */ int snd_device_register(struct snd_card *card, void *device_data) { struct snd_device *dev; if (snd_BUG_ON(!card || !device_data)) return -ENXIO; dev = look_for_dev(card, device_data); if (dev) return __snd_device_register(dev); snd_BUG(); return -ENXIO; } EXPORT_SYMBOL(snd_device_register); /* * register all the devices on the card. * called from init.c */ int snd_device_register_all(struct snd_card *card) { struct snd_device *dev; int err; if (snd_BUG_ON(!card)) return -ENXIO; list_for_each_entry(dev, &card->devices, list) { err = __snd_device_register(dev); if (err < 0) return err; } return 0; } /* * disconnect all the devices on the card. * called from init.c */ void snd_device_disconnect_all(struct snd_card *card) { struct snd_device *dev; if (snd_BUG_ON(!card)) return; list_for_each_entry_reverse(dev, &card->devices, list) __snd_device_disconnect(dev); } /* * release all the devices on the card. * called from init.c */ void snd_device_free_all(struct snd_card *card) { struct snd_device *dev, *next; if (snd_BUG_ON(!card)) return; list_for_each_entry_safe_reverse(dev, next, &card->devices, list) { /* exception: free ctl and lowlevel stuff later */ if (dev->type == SNDRV_DEV_CONTROL || dev->type == SNDRV_DEV_LOWLEVEL) continue; __snd_device_free(dev); } /* free all */ list_for_each_entry_safe_reverse(dev, next, &card->devices, list) __snd_device_free(dev); } /** * snd_device_get_state - Get the current state of the given device * @card: the card instance * @device_data: the data pointer to release * * Returns the current state of the given device object. For the valid * device, either @SNDRV_DEV_BUILD, @SNDRV_DEV_REGISTERED or * @SNDRV_DEV_DISCONNECTED is returned. * Or for a non-existing device, -1 is returned as an error. * * Return: the current state, or -1 if not found */ int snd_device_get_state(struct snd_card *card, void *device_data) { struct snd_device *dev; dev = look_for_dev(card, device_data); if (dev) return dev->state; return -1; } EXPORT_SYMBOL_GPL(snd_device_get_state); |
| 2 2 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 | /* * llc_c_ev.c - Connection component state transition event qualifiers * * A 'state' consists of a number of possible event matching functions, * the actions associated with each being executed when that event is * matched; a 'state machine' accepts events in a serial fashion from an * event queue. Each event is passed to each successive event matching * function until a match is made (the event matching function returns * success, or '0') or the list of event matching functions is exhausted. * If a match is made, the actions associated with the event are executed * and the state is changed to that event's transition state. Before some * events are recognized, even after a match has been made, a certain * number of 'event qualifier' functions must also be executed. If these * all execute successfully, then the event is finally executed. * * These event functions must return 0 for success, to show a matched * event, of 1 if the event does not match. Event qualifier functions * must return a 0 for success or a non-zero for failure. Each function * is simply responsible for verifying one single thing and returning * either a success or failure. * * All of followed event functions are described in 802.2 LLC Protocol * standard document except two functions that we added that will explain * in their comments, at below. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/netdevice.h> #include <net/llc_conn.h> #include <net/llc_sap.h> #include <net/sock.h> #include <net/llc_c_ac.h> #include <net/llc_c_ev.h> #include <net/llc_pdu.h> #if 1 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) #endif /** * llc_util_ns_inside_rx_window - check if sequence number is in rx window * @ns: sequence number of received pdu. * @vr: sequence number which receiver expects to receive. * @rw: receive window size of receiver. * * Checks if sequence number of received PDU is in range of receive * window. Returns 0 for success, 1 otherwise */ static u16 llc_util_ns_inside_rx_window(u8 ns, u8 vr, u8 rw) { return !llc_circular_between(vr, ns, (vr + rw - 1) % LLC_2_SEQ_NBR_MODULO); } /** * llc_util_nr_inside_tx_window - check if sequence number is in tx window * @sk: current connection. * @nr: N(R) of received PDU. * * This routine checks if N(R) of received PDU is in range of transmit * window; on the other hand checks if received PDU acknowledges some * outstanding PDUs that are in transmit window. Returns 0 for success, 1 * otherwise. */ static u16 llc_util_nr_inside_tx_window(struct sock *sk, u8 nr) { u8 nr1, nr2; struct sk_buff *skb; struct llc_pdu_sn *pdu; struct llc_sock *llc = llc_sk(sk); int rc = 0; if (llc->dev->flags & IFF_LOOPBACK) goto out; rc = 1; if (skb_queue_empty(&llc->pdu_unack_q)) goto out; skb = skb_peek(&llc->pdu_unack_q); pdu = llc_pdu_sn_hdr(skb); nr1 = LLC_I_GET_NS(pdu); skb = skb_peek_tail(&llc->pdu_unack_q); pdu = llc_pdu_sn_hdr(skb); nr2 = LLC_I_GET_NS(pdu); rc = !llc_circular_between(nr1, nr, (nr2 + 1) % LLC_2_SEQ_NBR_MODULO); out: return rc; } int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->prim == LLC_CONN_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->prim == LLC_DATA_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->prim == LLC_DISC_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->prim == LLC_RESET_PRIM && ev->prim_type == LLC_PRIM_TYPE_REQ ? 0 : 1; } int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type == LLC_CONN_EV_TYPE_SIMPLE && ev->prim_type == LLC_CONN_EV_LOCAL_BUSY_DETECTED ? 0 : 1; } int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type == LLC_CONN_EV_TYPE_SIMPLE && ev->prim_type == LLC_CONN_EV_LOCAL_BUSY_CLEARED ? 0 : 1; } int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb) { return 1; } int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_2_PDU_CMD_DISC ? 0 : 1; } int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_2_PDU_RSP_DM ? 0 : 1; } int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_2_PDU_RSP_FRMR ? 0 : 1; } int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_0(pdu) && LLC_I_GET_NS(pdu) == llc_sk(sk)->vR ? 0 : 1; } int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_1(pdu) && LLC_I_GET_NS(pdu) == llc_sk(sk)->vR ? 0 : 1; } int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_0(pdu) && ns != vr && !llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; } int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_1(pdu) && ns != vr && !llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; } int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn * pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); const u16 rc = LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_I(pdu) && ns != vr && llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; if (!rc) dprintk("%s: matched, state=%d, ns=%d, vr=%d\n", __func__, llc_sk(sk)->state, ns, vr); return rc; } int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_0(pdu) && LLC_I_GET_NS(pdu) == llc_sk(sk)->vR ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_1(pdu) && LLC_I_GET_NS(pdu) == llc_sk(sk)->vR ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_GET_NS(pdu) == llc_sk(sk)->vR ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_0(pdu) && ns != vr && !llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_1(pdu) && ns != vr && !llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && ns != vr && !llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; } int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vr = llc_sk(sk)->vR; const u8 ns = LLC_I_GET_NS(pdu); const u16 rc = LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && ns != vr && llc_util_ns_inside_rx_window(ns, vr, llc_sk(sk)->rw) ? 0 : 1; if (!rc) dprintk("%s: matched, state=%d, ns=%d, vr=%d\n", __func__, llc_sk(sk)->state, ns, vr); return rc; } int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_REJ ? 0 : 1; } int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_REJ ? 0 : 1; } int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_REJ ? 0 : 1; } int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_REJ ? 0 : 1; } int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_REJ ? 0 : 1; } int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_RNR ? 0 : 1; } int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_RNR ? 0 : 1; } int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_RNR ? 0 : 1; } int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_RNR ? 0 : 1; } int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_RR ? 0 : 1; } int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_CMD(pdu) == LLC_2_PDU_CMD_RR ? 0 : 1; } int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_0(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_RR ? 0 : 1; } int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); return llc_conn_space(sk, skb) && LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_S(pdu) && LLC_S_PF_IS_1(pdu) && LLC_S_PDU_RSP(pdu) == LLC_2_PDU_RSP_RR ? 0 : 1; } int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb) { const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_2_PDU_CMD_SABME ? 0 : 1; } int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_2_PDU_RSP_UA ? 0 : 1; } int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb) { u16 rc = 1; const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if (LLC_PDU_IS_CMD(pdu)) { if (LLC_PDU_TYPE_IS_I(pdu) || LLC_PDU_TYPE_IS_S(pdu)) { if (LLC_I_PF_IS_1(pdu)) rc = 0; } else if (LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PF_IS_1(pdu)) rc = 0; } return rc; } int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb) { u16 rc = 1; const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); if (LLC_PDU_IS_CMD(pdu)) { if (LLC_PDU_TYPE_IS_I(pdu) || LLC_PDU_TYPE_IS_S(pdu)) rc = 0; else if (LLC_PDU_TYPE_IS_U(pdu)) switch (LLC_U_PDU_CMD(pdu)) { case LLC_2_PDU_CMD_SABME: case LLC_2_PDU_CMD_DISC: rc = 0; break; } } return rc; } int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb) { u16 rc = 1; const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); if (LLC_PDU_IS_RSP(pdu)) { if (LLC_PDU_TYPE_IS_I(pdu) || LLC_PDU_TYPE_IS_S(pdu)) rc = 0; else if (LLC_PDU_TYPE_IS_U(pdu)) switch (LLC_U_PDU_RSP(pdu)) { case LLC_2_PDU_RSP_UA: case LLC_2_PDU_RSP_DM: case LLC_2_PDU_RSP_FRMR: rc = 0; break; } } return rc; } int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb) { u16 rc = 1; const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vs = llc_sk(sk)->vS; const u8 nr = LLC_I_GET_NR(pdu); if (LLC_PDU_IS_CMD(pdu) && (LLC_PDU_TYPE_IS_I(pdu) || LLC_PDU_TYPE_IS_S(pdu)) && nr != vs && llc_util_nr_inside_tx_window(sk, nr)) { dprintk("%s: matched, state=%d, vs=%d, nr=%d\n", __func__, llc_sk(sk)->state, vs, nr); rc = 0; } return rc; } int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb) { u16 rc = 1; const struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); const u8 vs = llc_sk(sk)->vS; const u8 nr = LLC_I_GET_NR(pdu); if (LLC_PDU_IS_RSP(pdu) && (LLC_PDU_TYPE_IS_I(pdu) || LLC_PDU_TYPE_IS_S(pdu)) && nr != vs && llc_util_nr_inside_tx_window(sk, nr)) { rc = 0; dprintk("%s: matched, state=%d, vs=%d, nr=%d\n", __func__, llc_sk(sk)->state, vs, nr); } return rc; } int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb) { return 0; } int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type != LLC_CONN_EV_TYPE_P_TMR; } int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type != LLC_CONN_EV_TYPE_ACK_TMR; } int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type != LLC_CONN_EV_TYPE_REJ_TMR; } int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type != LLC_CONN_EV_TYPE_BUSY_TMR; } int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb) { return 1; } int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb) { const struct llc_conn_state_ev *ev = llc_conn_ev(skb); return ev->type == LLC_CONN_EV_TYPE_SIMPLE && ev->prim_type == LLC_CONN_EV_TX_BUFF_FULL ? 0 : 1; } /* Event qualifier functions * * these functions simply verify the value of a state flag associated with * the connection and return either a 0 for success or a non-zero value * for not-success; verify the event is the type we expect */ int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->data_flag != 1; } int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->data_flag; } int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->data_flag != 2; } int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->p_flag != 1; } /** * llc_conn_ev_qlfy_last_frame_eq_1 - checks if frame is last in tx window * @sk: current connection structure. * @skb: current event. * * This function determines when frame which is sent, is last frame of * transmit window, if it is then this function return zero else return * one. This function is used for sending last frame of transmit window * as I-format command with p-bit set to one. Returns 0 if frame is last * frame, 1 otherwise. */ int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb) { return !(skb_queue_len(&llc_sk(sk)->pdu_unack_q) + 1 == llc_sk(sk)->k); } /** * llc_conn_ev_qlfy_last_frame_eq_0 - checks if frame isn't last in tx window * @sk: current connection structure. * @skb: current event. * * This function determines when frame which is sent, isn't last frame of * transmit window, if it isn't then this function return zero else return * one. Returns 0 if frame isn't last frame, 1 otherwise. */ int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb) { return skb_queue_len(&llc_sk(sk)->pdu_unack_q) + 1 == llc_sk(sk)->k; } int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->p_flag; } int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb) { u8 f_bit; llc_pdu_decode_pf_bit(skb, &f_bit); return llc_sk(sk)->p_flag == f_bit ? 0 : 1; } int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->remote_busy_flag; } int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb) { return !llc_sk(sk)->remote_busy_flag; } int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb) { return !(llc_sk(sk)->retry_count < llc_sk(sk)->n2); } int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb) { return !(llc_sk(sk)->retry_count >= llc_sk(sk)->n2); } int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb) { return !llc_sk(sk)->s_flag; } int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->s_flag; } int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb) { return !llc_sk(sk)->cause_flag; } int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb) { return llc_sk(sk)->cause_flag; } int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_CONN; return 0; } int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_DISC; return 0; } int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_FAILED; return 0; } int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_REMOTE_BUSY; return 0; } int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_REFUSE; return 0; } int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_CONFLICT; return 0; } int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->status = LLC_STATUS_RESET_DONE; return 0; } |
| 27 187 35 190 186 190 189 189 39 38 39 193 140 138 1 1 1 1 8 10 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> struct fib_config { u8 fc_dst_len; dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; netdevice_tracker nhc_dev_tracker; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_dev_tracker nh_common.nhc_dev_tracker #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; bool pfsrc_removed; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[] __counted_by(fib_nhs); }; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_rt_info { struct fib_info *fi; u32 tb_id; __be32 dst; int dst_len; dscp_t dscp; u8 type; u8 offload:1, trap:1, offload_failed:1, unused:5; }; struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; dscp_t dscp; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; bool rtnl_held; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return false; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib4_rules_seq_read(struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return net->ipv4.fib_has_custom_rules; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); /* Fields used for sysctl_fib_multipath_hash_fields. * Common to IPv4 and IPv6. * * Add new fields at the end. This is user API. */ #define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) #define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) #define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) #define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) #define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) #define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) #define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) #define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) #define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ FIB_MULTIPATH_HASH_FIELD_INNER_MASK) #define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO) #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to generic helpers functions */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/scatterlist.h> #include "blk.h" static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector) { unsigned int discard_granularity = bdev_discard_granularity(bdev); sector_t granularity_aligned_sector; if (bdev_is_partition(bdev)) sector += bdev->bd_start_sect; granularity_aligned_sector = round_up(sector, discard_granularity >> SECTOR_SHIFT); /* * Make sure subsequent bios start aligned to the discard granularity if * it needs to be split. */ if (granularity_aligned_sector != sector) return granularity_aligned_sector - sector; /* * Align the bio size to the discard granularity to make splitting the bio * at discard granularity boundaries easier in the driver if needed. */ return round_down(UINT_MAX, discard_granularity) >> SECTOR_SHIFT; } struct bio *blk_alloc_discard_bio(struct block_device *bdev, sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask) { sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector)); struct bio *bio; if (!bio_sects) return NULL; bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask); if (!bio) return NULL; bio->bi_iter.bi_sector = *sector; bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT; *sector += bio_sects; *nr_sects -= bio_sects; /* * We can loop for a long time in here if someone does full device * discards (like mkfs). Be nice and allow us to schedule out to avoid * softlocking if preempt is disabled. */ cond_resched(); return bio; } int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { struct bio *bio; while ((bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, gfp_mask))) *biop = bio_chain_and_submit(*biop, bio); return 0; } EXPORT_SYMBOL(__blkdev_issue_discard); /** * blkdev_issue_discard - queue a discard * @bdev: blockdev to issue discard for * @sector: start sector * @nr_sects: number of sectors to discard * @gfp_mask: memory allocation flags (for bio_alloc) * * Description: * Issue a discard request for the sectors in question. */ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask) { struct bio *bio = NULL; struct blk_plug plug; int ret; blk_start_plug(&plug); ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio); if (!ret && bio) { ret = submit_bio_wait(bio); if (ret == -EOPNOTSUPP) ret = 0; bio_put(bio); } blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(blkdev_issue_discard); static int __blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { struct bio *bio = *biop; unsigned int max_sectors; if (bdev_read_only(bdev)) return -EPERM; /* Ensure that max_sectors doesn't overflow bi_size */ max_sectors = bdev_write_zeroes_sectors(bdev); if (max_sectors == 0) return -EOPNOTSUPP; while (nr_sects) { unsigned int len = min_t(sector_t, nr_sects, max_sectors); bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask); bio->bi_iter.bi_sector = sector; if (flags & BLKDEV_ZERO_NOUNMAP) bio->bi_opf |= REQ_NOUNMAP; bio->bi_iter.bi_size = len << SECTOR_SHIFT; nr_sects -= len; sector += len; cond_resched(); } *biop = bio; return 0; } /* * Convert a number of 512B sectors to a number of pages. * The result is limited to a number of pages that can fit into a BIO. * Also make sure that the result is always at least 1 (page) for the cases * where nr_sects is lower than the number of sectors in a page. */ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) { sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512); return min(pages, (sector_t)BIO_MAX_VECS); } static int __blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop) { struct bio *bio = *biop; int bi_size = 0; unsigned int sz; if (bdev_read_only(bdev)) return -EPERM; while (nr_sects != 0) { bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects), REQ_OP_WRITE, gfp_mask); bio->bi_iter.bi_sector = sector; while (nr_sects != 0) { sz = min((sector_t) PAGE_SIZE, nr_sects << 9); bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0); nr_sects -= bi_size >> 9; sector += bi_size >> 9; if (bi_size < sz) break; } cond_resched(); } *biop = bio; return 0; } /** * __blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue * @sector: start sector * @nr_sects: number of sectors to write * @gfp_mask: memory allocation flags (for bio_alloc) * @biop: pointer to anchor bio * @flags: controls detailed behavior * * Description: * Zero-fill a block range, either using hardware offload or by explicitly * writing zeroes to the device. * * If a device is using logical block provisioning, the underlying space will * not be released if %flags contains BLKDEV_ZERO_NOUNMAP. * * If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return * -EOPNOTSUPP if no explicit hardware offload for zeroing is provided. */ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, unsigned flags) { int ret; sector_t bs_mask; bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, biop, flags); if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK)) return ret; return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, biop); } EXPORT_SYMBOL(__blkdev_issue_zeroout); /** * blkdev_issue_zeroout - zero-fill a block range * @bdev: blockdev to write * @sector: start sector * @nr_sects: number of sectors to write * @gfp_mask: memory allocation flags (for bio_alloc) * @flags: controls detailed behavior * * Description: * Zero-fill a block range, either using hardware offload or by explicitly * writing zeroes to the device. See __blkdev_issue_zeroout() for the * valid values for %flags. */ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags) { int ret = 0; sector_t bs_mask; struct bio *bio; struct blk_plug plug; bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev); bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; if ((sector | nr_sects) & bs_mask) return -EINVAL; retry: bio = NULL; blk_start_plug(&plug); if (try_write_zeroes) { ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, &bio, flags); } else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, &bio); } else { /* No zeroing offload support */ ret = -EOPNOTSUPP; } if (ret == 0 && bio) { ret = submit_bio_wait(bio); bio_put(bio); } blk_finish_plug(&plug); if (ret && try_write_zeroes) { if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { try_write_zeroes = false; goto retry; } if (!bdev_write_zeroes_sectors(bdev)) { /* * Zeroing offload support was indicated, but the * device reported ILLEGAL REQUEST (for some devices * there is no non-destructive way to verify whether * WRITE ZEROES is actually supported). */ ret = -EOPNOTSUPP; } } return ret; } EXPORT_SYMBOL(blkdev_issue_zeroout); int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp) { sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev); struct bio *bio = NULL; struct blk_plug plug; int ret = 0; /* make sure that "len << SECTOR_SHIFT" doesn't overflow */ if (max_sectors > UINT_MAX >> SECTOR_SHIFT) max_sectors = UINT_MAX >> SECTOR_SHIFT; max_sectors &= ~bs_mask; if (max_sectors == 0) return -EOPNOTSUPP; if ((sector | nr_sects) & bs_mask) return -EINVAL; if (bdev_read_only(bdev)) return -EPERM; blk_start_plug(&plug); while (nr_sects) { unsigned int len = min_t(sector_t, nr_sects, max_sectors); bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp); bio->bi_iter.bi_sector = sector; bio->bi_iter.bi_size = len << SECTOR_SHIFT; sector += len; nr_sects -= len; cond_resched(); } if (bio) { ret = submit_bio_wait(bio); bio_put(bio); } blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(blkdev_issue_secure_erase); |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor function for pathnames * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2010 Canonical Ltd. */ #include <linux/magic.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/nsproxy.h> #include <linux/path.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "include/apparmor.h" #include "include/path.h" #include "include/policy.h" /* modified from dcache.c */ static int prepend(char **buffer, int buflen, const char *str, int namelen) { buflen -= namelen; if (buflen < 0) return -ENAMETOOLONG; *buffer -= namelen; memcpy(*buffer, str, namelen); return 0; } #define CHROOT_NSCONNECT (PATH_CHROOT_REL | PATH_CHROOT_NSCONNECT) /* If the path is not connected to the expected root, * check if it is a sysctl and handle specially else remove any * leading / that __d_path may have returned. * Unless * specifically directed to connect the path, * OR * if in a chroot and doing chroot relative paths and the path * resolves to the namespace root (would be connected outside * of chroot) and specifically directed to connect paths to * namespace root. */ static int disconnect(const struct path *path, char *buf, char **name, int flags, const char *disconnected) { int error = 0; if (!(flags & PATH_CONNECT_PATH) && !(((flags & CHROOT_NSCONNECT) == CHROOT_NSCONNECT) && our_mnt(path->mnt))) { /* disconnected path, don't return pathname starting * with '/' */ error = -EACCES; if (**name == '/') *name = *name + 1; } else { if (**name != '/') /* CONNECT_PATH with missing root */ error = prepend(name, *name - buf, "/", 1); if (!error && disconnected) error = prepend(name, *name - buf, disconnected, strlen(disconnected)); } return error; } /** * d_namespace_path - lookup a name associated with a given path * @path: path to lookup (NOT NULL) * @buf: buffer to store path to (NOT NULL) * @name: Returns - pointer for start of path name with in @buf (NOT NULL) * @flags: flags controlling path lookup * @disconnected: string to prefix to disconnected paths * * Handle path name lookup. * * Returns: %0 else error code if path lookup fails * When no error the path name is returned in @name which points to * a position in @buf */ static int d_namespace_path(const struct path *path, char *buf, char **name, int flags, const char *disconnected) { char *res; int error = 0; int connected = 1; int isdir = (flags & PATH_IS_DIR) ? 1 : 0; int buflen = aa_g_path_max - isdir; if (path->mnt->mnt_flags & MNT_INTERNAL) { /* it's not mounted anywhere */ res = dentry_path(path->dentry, buf, buflen); *name = res; if (IS_ERR(res)) { *name = buf; return PTR_ERR(res); } if (path->dentry->d_sb->s_magic == PROC_SUPER_MAGIC && strncmp(*name, "/sys/", 5) == 0) { /* TODO: convert over to using a per namespace * control instead of hard coded /proc */ error = prepend(name, *name - buf, "/proc", 5); goto out; } else error = disconnect(path, buf, name, flags, disconnected); goto out; } /* resolve paths relative to chroot?*/ if (flags & PATH_CHROOT_REL) { struct path root; get_fs_root(current->fs, &root); res = __d_path(path, &root, buf, buflen); path_put(&root); } else { res = d_absolute_path(path, buf, buflen); if (!our_mnt(path->mnt)) connected = 0; } /* handle error conditions - and still allow a partial path to * be returned. */ if (!res || IS_ERR(res)) { if (PTR_ERR(res) == -ENAMETOOLONG) { error = -ENAMETOOLONG; *name = buf; goto out; } connected = 0; res = dentry_path_raw(path->dentry, buf, buflen); if (IS_ERR(res)) { error = PTR_ERR(res); *name = buf; goto out; } } else if (!our_mnt(path->mnt)) connected = 0; *name = res; if (!connected) error = disconnect(path, buf, name, flags, disconnected); /* Handle two cases: * 1. A deleted dentry && profile is not allowing mediation of deleted * 2. On some filesystems, newly allocated dentries appear to the * security_path hooks as a deleted dentry except without an inode * allocated. */ if (d_unlinked(path->dentry) && d_is_positive(path->dentry) && !(flags & (PATH_MEDIATE_DELETED | PATH_DELEGATE_DELETED))) { error = -ENOENT; goto out; } out: /* * Append "/" to the pathname. The root directory is a special * case; it already ends in slash. */ if (!error && isdir && ((*name)[1] != '\0' || (*name)[0] != '/')) strcpy(&buf[aa_g_path_max - 2], "/"); return error; } /** * aa_path_name - get the pathname to a buffer ensure dir / is appended * @path: path the file (NOT NULL) * @flags: flags controlling path name generation * @buffer: buffer to put name in (NOT NULL) * @name: Returns - the generated path name if !error (NOT NULL) * @info: Returns - information on why the path lookup failed (MAYBE NULL) * @disconnected: string to prepend to disconnected paths * * @name is a pointer to the beginning of the pathname (which usually differs * from the beginning of the buffer), or NULL. If there is an error @name * may contain a partial or invalid name that can be used for audit purposes, * but it can not be used for mediation. * * We need PATH_IS_DIR to indicate whether the file is a directory or not * because the file may not yet exist, and so we cannot check the inode's * file type. * * Returns: %0 else error code if could retrieve name */ int aa_path_name(const struct path *path, int flags, char *buffer, const char **name, const char **info, const char *disconnected) { char *str = NULL; int error = d_namespace_path(path, buffer, &str, flags, disconnected); if (info && error) { if (error == -ENOENT) *info = "Failed name lookup - deleted entry"; else if (error == -EACCES) *info = "Failed name lookup - disconnected path"; else if (error == -ENAMETOOLONG) *info = "Failed name lookup - name too long"; else *info = "Failed name lookup"; } *name = str; return error; } |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 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 | // SPDX-License-Identifier: GPL-2.0 // rc-main.c - Remote Controller core module // // Copyright (C) 2009-2010 by Mauro Carvalho Chehab #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <media/rc-core.h> #include <linux/bsearch.h> #include <linux/spinlock.h> #include <linux/delay.h> #include <linux/input.h> #include <linux/leds.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/device.h> #include <linux/module.h> #include "rc-core-priv.h" /* Sizes are in bytes, 256 bytes allows for 32 entries on x64 */ #define IR_TAB_MIN_SIZE 256 #define IR_TAB_MAX_SIZE 8192 static const struct { const char *name; unsigned int repeat_period; unsigned int scancode_bits; } protocols[] = { [RC_PROTO_UNKNOWN] = { .name = "unknown", .repeat_period = 125 }, [RC_PROTO_OTHER] = { .name = "other", .repeat_period = 125 }, [RC_PROTO_RC5] = { .name = "rc-5", .scancode_bits = 0x1f7f, .repeat_period = 114 }, [RC_PROTO_RC5X_20] = { .name = "rc-5x-20", .scancode_bits = 0x1f7f3f, .repeat_period = 114 }, [RC_PROTO_RC5_SZ] = { .name = "rc-5-sz", .scancode_bits = 0x2fff, .repeat_period = 114 }, [RC_PROTO_JVC] = { .name = "jvc", .scancode_bits = 0xffff, .repeat_period = 125 }, [RC_PROTO_SONY12] = { .name = "sony-12", .scancode_bits = 0x1f007f, .repeat_period = 100 }, [RC_PROTO_SONY15] = { .name = "sony-15", .scancode_bits = 0xff007f, .repeat_period = 100 }, [RC_PROTO_SONY20] = { .name = "sony-20", .scancode_bits = 0x1fff7f, .repeat_period = 100 }, [RC_PROTO_NEC] = { .name = "nec", .scancode_bits = 0xffff, .repeat_period = 110 }, [RC_PROTO_NECX] = { .name = "nec-x", .scancode_bits = 0xffffff, .repeat_period = 110 }, [RC_PROTO_NEC32] = { .name = "nec-32", .scancode_bits = 0xffffffff, .repeat_period = 110 }, [RC_PROTO_SANYO] = { .name = "sanyo", .scancode_bits = 0x1fffff, .repeat_period = 125 }, [RC_PROTO_MCIR2_KBD] = { .name = "mcir2-kbd", .scancode_bits = 0xffffff, .repeat_period = 100 }, [RC_PROTO_MCIR2_MSE] = { .name = "mcir2-mse", .scancode_bits = 0x1fffff, .repeat_period = 100 }, [RC_PROTO_RC6_0] = { .name = "rc-6-0", .scancode_bits = 0xffff, .repeat_period = 114 }, [RC_PROTO_RC6_6A_20] = { .name = "rc-6-6a-20", .scancode_bits = 0xfffff, .repeat_period = 114 }, [RC_PROTO_RC6_6A_24] = { .name = "rc-6-6a-24", .scancode_bits = 0xffffff, .repeat_period = 114 }, [RC_PROTO_RC6_6A_32] = { .name = "rc-6-6a-32", .scancode_bits = 0xffffffff, .repeat_period = 114 }, [RC_PROTO_RC6_MCE] = { .name = "rc-6-mce", .scancode_bits = 0xffff7fff, .repeat_period = 114 }, [RC_PROTO_SHARP] = { .name = "sharp", .scancode_bits = 0x1fff, .repeat_period = 125 }, [RC_PROTO_XMP] = { .name = "xmp", .repeat_period = 125 }, [RC_PROTO_CEC] = { .name = "cec", .repeat_period = 0 }, [RC_PROTO_IMON] = { .name = "imon", .scancode_bits = 0x7fffffff, .repeat_period = 114 }, [RC_PROTO_RCMM12] = { .name = "rc-mm-12", .scancode_bits = 0x00000fff, .repeat_period = 114 }, [RC_PROTO_RCMM24] = { .name = "rc-mm-24", .scancode_bits = 0x00ffffff, .repeat_period = 114 }, [RC_PROTO_RCMM32] = { .name = "rc-mm-32", .scancode_bits = 0xffffffff, .repeat_period = 114 }, [RC_PROTO_XBOX_DVD] = { .name = "xbox-dvd", .repeat_period = 64 }, }; /* Used to keep track of known keymaps */ static LIST_HEAD(rc_map_list); static DEFINE_SPINLOCK(rc_map_lock); static struct led_trigger *led_feedback; /* Used to keep track of rc devices */ static DEFINE_IDA(rc_ida); static struct rc_map_list *seek_rc_map(const char *name) { struct rc_map_list *map = NULL; spin_lock(&rc_map_lock); list_for_each_entry(map, &rc_map_list, list) { if (!strcmp(name, map->map.name)) { spin_unlock(&rc_map_lock); return map; } } spin_unlock(&rc_map_lock); return NULL; } struct rc_map *rc_map_get(const char *name) { struct rc_map_list *map; map = seek_rc_map(name); #ifdef CONFIG_MODULES if (!map) { int rc = request_module("%s", name); if (rc < 0) { pr_err("Couldn't load IR keymap %s\n", name); return NULL; } msleep(20); /* Give some time for IR to register */ map = seek_rc_map(name); } #endif if (!map) { pr_err("IR keymap %s not found\n", name); return NULL; } printk(KERN_INFO "Registered IR keymap %s\n", map->map.name); return &map->map; } EXPORT_SYMBOL_GPL(rc_map_get); int rc_map_register(struct rc_map_list *map) { spin_lock(&rc_map_lock); list_add_tail(&map->list, &rc_map_list); spin_unlock(&rc_map_lock); return 0; } EXPORT_SYMBOL_GPL(rc_map_register); void rc_map_unregister(struct rc_map_list *map) { spin_lock(&rc_map_lock); list_del(&map->list); spin_unlock(&rc_map_lock); } EXPORT_SYMBOL_GPL(rc_map_unregister); static struct rc_map_table empty[] = { { 0x2a, KEY_COFFEE }, }; static struct rc_map_list empty_map = { .map = { .scan = empty, .size = ARRAY_SIZE(empty), .rc_proto = RC_PROTO_UNKNOWN, /* Legacy IR type */ .name = RC_MAP_EMPTY, } }; /** * scancode_to_u64() - converts scancode in &struct input_keymap_entry * @ke: keymap entry containing scancode to be converted. * @scancode: pointer to the location where converted scancode should * be stored. * * This function is a version of input_scancode_to_scalar specialized for * rc-core. */ static int scancode_to_u64(const struct input_keymap_entry *ke, u64 *scancode) { switch (ke->len) { case 1: *scancode = *((u8 *)ke->scancode); break; case 2: *scancode = *((u16 *)ke->scancode); break; case 4: *scancode = *((u32 *)ke->scancode); break; case 8: *scancode = *((u64 *)ke->scancode); break; default: return -EINVAL; } return 0; } /** * ir_create_table() - initializes a scancode table * @dev: the rc_dev device * @rc_map: the rc_map to initialize * @name: name to assign to the table * @rc_proto: ir type to assign to the new table * @size: initial size of the table * * This routine will initialize the rc_map and will allocate * memory to hold at least the specified number of elements. * * return: zero on success or a negative error code */ static int ir_create_table(struct rc_dev *dev, struct rc_map *rc_map, const char *name, u64 rc_proto, size_t size) { rc_map->name = kstrdup(name, GFP_KERNEL); if (!rc_map->name) return -ENOMEM; rc_map->rc_proto = rc_proto; rc_map->alloc = roundup_pow_of_two(size * sizeof(struct rc_map_table)); rc_map->size = rc_map->alloc / sizeof(struct rc_map_table); rc_map->scan = kmalloc(rc_map->alloc, GFP_KERNEL); if (!rc_map->scan) { kfree(rc_map->name); rc_map->name = NULL; return -ENOMEM; } dev_dbg(&dev->dev, "Allocated space for %u keycode entries (%u bytes)\n", rc_map->size, rc_map->alloc); return 0; } /** * ir_free_table() - frees memory allocated by a scancode table * @rc_map: the table whose mappings need to be freed * * This routine will free memory alloctaed for key mappings used by given * scancode table. */ static void ir_free_table(struct rc_map *rc_map) { rc_map->size = 0; kfree(rc_map->name); rc_map->name = NULL; kfree(rc_map->scan); rc_map->scan = NULL; } /** * ir_resize_table() - resizes a scancode table if necessary * @dev: the rc_dev device * @rc_map: the rc_map to resize * @gfp_flags: gfp flags to use when allocating memory * * This routine will shrink the rc_map if it has lots of * unused entries and grow it if it is full. * * return: zero on success or a negative error code */ static int ir_resize_table(struct rc_dev *dev, struct rc_map *rc_map, gfp_t gfp_flags) { unsigned int oldalloc = rc_map->alloc; unsigned int newalloc = oldalloc; struct rc_map_table *oldscan = rc_map->scan; struct rc_map_table *newscan; if (rc_map->size == rc_map->len) { /* All entries in use -> grow keytable */ if (rc_map->alloc >= IR_TAB_MAX_SIZE) return -ENOMEM; newalloc *= 2; dev_dbg(&dev->dev, "Growing table to %u bytes\n", newalloc); } if ((rc_map->len * 3 < rc_map->size) && (oldalloc > IR_TAB_MIN_SIZE)) { /* Less than 1/3 of entries in use -> shrink keytable */ newalloc /= 2; dev_dbg(&dev->dev, "Shrinking table to %u bytes\n", newalloc); } if (newalloc == oldalloc) return 0; newscan = kmalloc(newalloc, gfp_flags); if (!newscan) return -ENOMEM; memcpy(newscan, rc_map->scan, rc_map->len * sizeof(struct rc_map_table)); rc_map->scan = newscan; rc_map->alloc = newalloc; rc_map->size = rc_map->alloc / sizeof(struct rc_map_table); kfree(oldscan); return 0; } /** * ir_update_mapping() - set a keycode in the scancode->keycode table * @dev: the struct rc_dev device descriptor * @rc_map: scancode table to be adjusted * @index: index of the mapping that needs to be updated * @new_keycode: the desired keycode * * This routine is used to update scancode->keycode mapping at given * position. * * return: previous keycode assigned to the mapping * */ static unsigned int ir_update_mapping(struct rc_dev *dev, struct rc_map *rc_map, unsigned int index, unsigned int new_keycode) { int old_keycode = rc_map->scan[index].keycode; int i; /* Did the user wish to remove the mapping? */ if (new_keycode == KEY_RESERVED || new_keycode == KEY_UNKNOWN) { dev_dbg(&dev->dev, "#%d: Deleting scan 0x%04llx\n", index, rc_map->scan[index].scancode); rc_map->len--; memmove(&rc_map->scan[index], &rc_map->scan[index+ 1], (rc_map->len - index) * sizeof(struct rc_map_table)); } else { dev_dbg(&dev->dev, "#%d: %s scan 0x%04llx with key 0x%04x\n", index, old_keycode == KEY_RESERVED ? "New" : "Replacing", rc_map->scan[index].scancode, new_keycode); rc_map->scan[index].keycode = new_keycode; __set_bit(new_keycode, dev->input_dev->keybit); } if (old_keycode != KEY_RESERVED) { /* A previous mapping was updated... */ __clear_bit(old_keycode, dev->input_dev->keybit); /* ... but another scancode might use the same keycode */ for (i = 0; i < rc_map->len; i++) { if (rc_map->scan[i].keycode == old_keycode) { __set_bit(old_keycode, dev->input_dev->keybit); break; } } /* Possibly shrink the keytable, failure is not a problem */ ir_resize_table(dev, rc_map, GFP_ATOMIC); } return old_keycode; } /** * ir_establish_scancode() - set a keycode in the scancode->keycode table * @dev: the struct rc_dev device descriptor * @rc_map: scancode table to be searched * @scancode: the desired scancode * @resize: controls whether we allowed to resize the table to * accommodate not yet present scancodes * * This routine is used to locate given scancode in rc_map. * If scancode is not yet present the routine will allocate a new slot * for it. * * return: index of the mapping containing scancode in question * or -1U in case of failure. */ static unsigned int ir_establish_scancode(struct rc_dev *dev, struct rc_map *rc_map, u64 scancode, bool resize) { unsigned int i; /* * Unfortunately, some hardware-based IR decoders don't provide * all bits for the complete IR code. In general, they provide only * the command part of the IR code. Yet, as it is possible to replace * the provided IR with another one, it is needed to allow loading * IR tables from other remotes. So, we support specifying a mask to * indicate the valid bits of the scancodes. */ if (dev->scancode_mask) scancode &= dev->scancode_mask; /* First check if we already have a mapping for this ir command */ for (i = 0; i < rc_map->len; i++) { if (rc_map->scan[i].scancode == scancode) return i; /* Keytable is sorted from lowest to highest scancode */ if (rc_map->scan[i].scancode >= scancode) break; } /* No previous mapping found, we might need to grow the table */ if (rc_map->size == rc_map->len) { if (!resize || ir_resize_table(dev, rc_map, GFP_ATOMIC)) return -1U; } /* i is the proper index to insert our new keycode */ if (i < rc_map->len) memmove(&rc_map->scan[i + 1], &rc_map->scan[i], (rc_map->len - i) * sizeof(struct rc_map_table)); rc_map->scan[i].scancode = scancode; rc_map->scan[i].keycode = KEY_RESERVED; rc_map->len++; return i; } /** * ir_setkeycode() - set a keycode in the scancode->keycode table * @idev: the struct input_dev device descriptor * @ke: Input keymap entry * @old_keycode: result * * This routine is used to handle evdev EVIOCSKEY ioctl. * * return: -EINVAL if the keycode could not be inserted, otherwise zero. */ static int ir_setkeycode(struct input_dev *idev, const struct input_keymap_entry *ke, unsigned int *old_keycode) { struct rc_dev *rdev = input_get_drvdata(idev); struct rc_map *rc_map = &rdev->rc_map; unsigned int index; u64 scancode; int retval = 0; unsigned long flags; spin_lock_irqsave(&rc_map->lock, flags); if (ke->flags & INPUT_KEYMAP_BY_INDEX) { index = ke->index; if (index >= rc_map->len) { retval = -EINVAL; goto out; } } else { retval = scancode_to_u64(ke, &scancode); if (retval) goto out; index = ir_establish_scancode(rdev, rc_map, scancode, true); if (index >= rc_map->len) { retval = -ENOMEM; goto out; } } *old_keycode = ir_update_mapping(rdev, rc_map, index, ke->keycode); out: spin_unlock_irqrestore(&rc_map->lock, flags); return retval; } /** * ir_setkeytable() - sets several entries in the scancode->keycode table * @dev: the struct rc_dev device descriptor * @from: the struct rc_map to copy entries from * * This routine is used to handle table initialization. * * return: -ENOMEM if all keycodes could not be inserted, otherwise zero. */ static int ir_setkeytable(struct rc_dev *dev, const struct rc_map *from) { struct rc_map *rc_map = &dev->rc_map; unsigned int i, index; int rc; rc = ir_create_table(dev, rc_map, from->name, from->rc_proto, from->size); if (rc) return rc; for (i = 0; i < from->size; i++) { index = ir_establish_scancode(dev, rc_map, from->scan[i].scancode, false); if (index >= rc_map->len) { rc = -ENOMEM; break; } ir_update_mapping(dev, rc_map, index, from->scan[i].keycode); } if (rc) ir_free_table(rc_map); return rc; } static int rc_map_cmp(const void *key, const void *elt) { const u64 *scancode = key; const struct rc_map_table *e = elt; if (*scancode < e->scancode) return -1; else if (*scancode > e->scancode) return 1; return 0; } /** * ir_lookup_by_scancode() - locate mapping by scancode * @rc_map: the struct rc_map to search * @scancode: scancode to look for in the table * * This routine performs binary search in RC keykeymap table for * given scancode. * * return: index in the table, -1U if not found */ static unsigned int ir_lookup_by_scancode(const struct rc_map *rc_map, u64 scancode) { struct rc_map_table *res; res = bsearch(&scancode, rc_map->scan, rc_map->len, sizeof(struct rc_map_table), rc_map_cmp); if (!res) return -1U; else return res - rc_map->scan; } /** * ir_getkeycode() - get a keycode from the scancode->keycode table * @idev: the struct input_dev device descriptor * @ke: Input keymap entry * * This routine is used to handle evdev EVIOCGKEY ioctl. * * return: always returns zero. */ static int ir_getkeycode(struct input_dev *idev, struct input_keymap_entry *ke) { struct rc_dev *rdev = input_get_drvdata(idev); struct rc_map *rc_map = &rdev->rc_map; struct rc_map_table *entry; unsigned long flags; unsigned int index; u64 scancode; int retval; spin_lock_irqsave(&rc_map->lock, flags); if (ke->flags & INPUT_KEYMAP_BY_INDEX) { index = ke->index; } else { retval = scancode_to_u64(ke, &scancode); if (retval) goto out; index = ir_lookup_by_scancode(rc_map, scancode); } if (index < rc_map->len) { entry = &rc_map->scan[index]; ke->index = index; ke->keycode = entry->keycode; ke->len = sizeof(entry->scancode); memcpy(ke->scancode, &entry->scancode, sizeof(entry->scancode)); } else if (!(ke->flags & INPUT_KEYMAP_BY_INDEX)) { /* * We do not really know the valid range of scancodes * so let's respond with KEY_RESERVED to anything we * do not have mapping for [yet]. */ ke->index = index; ke->keycode = KEY_RESERVED; } else { retval = -EINVAL; goto out; } retval = 0; out: spin_unlock_irqrestore(&rc_map->lock, flags); return retval; } /** * rc_g_keycode_from_table() - gets the keycode that corresponds to a scancode * @dev: the struct rc_dev descriptor of the device * @scancode: the scancode to look for * * This routine is used by drivers which need to convert a scancode to a * keycode. Normally it should not be used since drivers should have no * interest in keycodes. * * return: the corresponding keycode, or KEY_RESERVED */ u32 rc_g_keycode_from_table(struct rc_dev *dev, u64 scancode) { struct rc_map *rc_map = &dev->rc_map; unsigned int keycode; unsigned int index; unsigned long flags; spin_lock_irqsave(&rc_map->lock, flags); index = ir_lookup_by_scancode(rc_map, scancode); keycode = index < rc_map->len ? rc_map->scan[index].keycode : KEY_RESERVED; spin_unlock_irqrestore(&rc_map->lock, flags); if (keycode != KEY_RESERVED) dev_dbg(&dev->dev, "%s: scancode 0x%04llx keycode 0x%02x\n", dev->device_name, scancode, keycode); return keycode; } EXPORT_SYMBOL_GPL(rc_g_keycode_from_table); /** * ir_do_keyup() - internal function to signal the release of a keypress * @dev: the struct rc_dev descriptor of the device * @sync: whether or not to call input_sync * * This function is used internally to release a keypress, it must be * called with keylock held. */ static void ir_do_keyup(struct rc_dev *dev, bool sync) { if (!dev->keypressed) return; dev_dbg(&dev->dev, "keyup key 0x%04x\n", dev->last_keycode); del_timer(&dev->timer_repeat); input_report_key(dev->input_dev, dev->last_keycode, 0); led_trigger_event(led_feedback, LED_OFF); if (sync) input_sync(dev->input_dev); dev->keypressed = false; } /** * rc_keyup() - signals the release of a keypress * @dev: the struct rc_dev descriptor of the device * * This routine is used to signal that a key has been released on the * remote control. */ void rc_keyup(struct rc_dev *dev) { unsigned long flags; spin_lock_irqsave(&dev->keylock, flags); ir_do_keyup(dev, true); spin_unlock_irqrestore(&dev->keylock, flags); } EXPORT_SYMBOL_GPL(rc_keyup); /** * ir_timer_keyup() - generates a keyup event after a timeout * * @t: a pointer to the struct timer_list * * This routine will generate a keyup event some time after a keydown event * is generated when no further activity has been detected. */ static void ir_timer_keyup(struct timer_list *t) { struct rc_dev *dev = from_timer(dev, t, timer_keyup); unsigned long flags; /* * ir->keyup_jiffies is used to prevent a race condition if a * hardware interrupt occurs at this point and the keyup timer * event is moved further into the future as a result. * * The timer will then be reactivated and this function called * again in the future. We need to exit gracefully in that case * to allow the input subsystem to do its auto-repeat magic or * a keyup event might follow immediately after the keydown. */ spin_lock_irqsave(&dev->keylock, flags); if (time_is_before_eq_jiffies(dev->keyup_jiffies)) ir_do_keyup(dev, true); spin_unlock_irqrestore(&dev->keylock, flags); } /** * ir_timer_repeat() - generates a repeat event after a timeout * * @t: a pointer to the struct timer_list * * This routine will generate a soft repeat event every REP_PERIOD * milliseconds. */ static void ir_timer_repeat(struct timer_list *t) { struct rc_dev *dev = from_timer(dev, t, timer_repeat); struct input_dev *input = dev->input_dev; unsigned long flags; spin_lock_irqsave(&dev->keylock, flags); if (dev->keypressed) { input_event(input, EV_KEY, dev->last_keycode, 2); input_sync(input); if (input->rep[REP_PERIOD]) mod_timer(&dev->timer_repeat, jiffies + msecs_to_jiffies(input->rep[REP_PERIOD])); } spin_unlock_irqrestore(&dev->keylock, flags); } static unsigned int repeat_period(int protocol) { if (protocol >= ARRAY_SIZE(protocols)) return 100; return protocols[protocol].repeat_period; } /** * rc_repeat() - signals that a key is still pressed * @dev: the struct rc_dev descriptor of the device * * This routine is used by IR decoders when a repeat message which does * not include the necessary bits to reproduce the scancode has been * received. */ void rc_repeat(struct rc_dev *dev) { unsigned long flags; unsigned int timeout = usecs_to_jiffies(dev->timeout) + msecs_to_jiffies(repeat_period(dev->last_protocol)); struct lirc_scancode sc = { .scancode = dev->last_scancode, .rc_proto = dev->last_protocol, .keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED, .flags = LIRC_SCANCODE_FLAG_REPEAT | (dev->last_toggle ? LIRC_SCANCODE_FLAG_TOGGLE : 0) }; if (dev->allowed_protocols != RC_PROTO_BIT_CEC) lirc_scancode_event(dev, &sc); spin_lock_irqsave(&dev->keylock, flags); if (dev->last_scancode <= U32_MAX) { input_event(dev->input_dev, EV_MSC, MSC_SCAN, dev->last_scancode); input_sync(dev->input_dev); } if (dev->keypressed) { dev->keyup_jiffies = jiffies + timeout; mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } spin_unlock_irqrestore(&dev->keylock, flags); } EXPORT_SYMBOL_GPL(rc_repeat); /** * ir_do_keydown() - internal function to process a keypress * @dev: the struct rc_dev descriptor of the device * @protocol: the protocol of the keypress * @scancode: the scancode of the keypress * @keycode: the keycode of the keypress * @toggle: the toggle value of the keypress * * This function is used internally to register a keypress, it must be * called with keylock held. */ static void ir_do_keydown(struct rc_dev *dev, enum rc_proto protocol, u64 scancode, u32 keycode, u8 toggle) { bool new_event = (!dev->keypressed || dev->last_protocol != protocol || dev->last_scancode != scancode || dev->last_toggle != toggle); struct lirc_scancode sc = { .scancode = scancode, .rc_proto = protocol, .flags = (toggle ? LIRC_SCANCODE_FLAG_TOGGLE : 0) | (!new_event ? LIRC_SCANCODE_FLAG_REPEAT : 0), .keycode = keycode }; if (dev->allowed_protocols != RC_PROTO_BIT_CEC) lirc_scancode_event(dev, &sc); if (new_event && dev->keypressed) ir_do_keyup(dev, false); if (scancode <= U32_MAX) input_event(dev->input_dev, EV_MSC, MSC_SCAN, scancode); dev->last_protocol = protocol; dev->last_scancode = scancode; dev->last_toggle = toggle; dev->last_keycode = keycode; if (new_event && keycode != KEY_RESERVED) { /* Register a keypress */ dev->keypressed = true; dev_dbg(&dev->dev, "%s: key down event, key 0x%04x, protocol 0x%04x, scancode 0x%08llx\n", dev->device_name, keycode, protocol, scancode); input_report_key(dev->input_dev, keycode, 1); led_trigger_event(led_feedback, LED_FULL); } /* * For CEC, start sending repeat messages as soon as the first * repeated message is sent, as long as REP_DELAY = 0 and REP_PERIOD * is non-zero. Otherwise, the input layer will generate repeat * messages. */ if (!new_event && keycode != KEY_RESERVED && dev->allowed_protocols == RC_PROTO_BIT_CEC && !timer_pending(&dev->timer_repeat) && dev->input_dev->rep[REP_PERIOD] && !dev->input_dev->rep[REP_DELAY]) { input_event(dev->input_dev, EV_KEY, keycode, 2); mod_timer(&dev->timer_repeat, jiffies + msecs_to_jiffies(dev->input_dev->rep[REP_PERIOD])); } input_sync(dev->input_dev); } /** * rc_keydown() - generates input event for a key press * @dev: the struct rc_dev descriptor of the device * @protocol: the protocol for the keypress * @scancode: the scancode for the keypress * @toggle: the toggle value (protocol dependent, if the protocol doesn't * support toggle values, this should be set to zero) * * This routine is used to signal that a key has been pressed on the * remote control. */ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u64 scancode, u8 toggle) { unsigned long flags; u32 keycode = rc_g_keycode_from_table(dev, scancode); spin_lock_irqsave(&dev->keylock, flags); ir_do_keydown(dev, protocol, scancode, keycode, toggle); if (dev->keypressed) { dev->keyup_jiffies = jiffies + usecs_to_jiffies(dev->timeout) + msecs_to_jiffies(repeat_period(protocol)); mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } spin_unlock_irqrestore(&dev->keylock, flags); } EXPORT_SYMBOL_GPL(rc_keydown); /** * rc_keydown_notimeout() - generates input event for a key press without * an automatic keyup event at a later time * @dev: the struct rc_dev descriptor of the device * @protocol: the protocol for the keypress * @scancode: the scancode for the keypress * @toggle: the toggle value (protocol dependent, if the protocol doesn't * support toggle values, this should be set to zero) * * This routine is used to signal that a key has been pressed on the * remote control. The driver must manually call rc_keyup() at a later stage. */ void rc_keydown_notimeout(struct rc_dev *dev, enum rc_proto protocol, u64 scancode, u8 toggle) { unsigned long flags; u32 keycode = rc_g_keycode_from_table(dev, scancode); spin_lock_irqsave(&dev->keylock, flags); ir_do_keydown(dev, protocol, scancode, keycode, toggle); spin_unlock_irqrestore(&dev->keylock, flags); } EXPORT_SYMBOL_GPL(rc_keydown_notimeout); /** * rc_validate_scancode() - checks that a scancode is valid for a protocol. * For nec, it should do the opposite of ir_nec_bytes_to_scancode() * @proto: protocol * @scancode: scancode */ bool rc_validate_scancode(enum rc_proto proto, u32 scancode) { switch (proto) { /* * NECX has a 16-bit address; if the lower 8 bits match the upper * 8 bits inverted, then the address would match regular nec. */ case RC_PROTO_NECX: if ((((scancode >> 16) ^ ~(scancode >> 8)) & 0xff) == 0) return false; break; /* * NEC32 has a 16 bit address and 16 bit command. If the lower 8 bits * of the command match the upper 8 bits inverted, then it would * be either NEC or NECX. */ case RC_PROTO_NEC32: if ((((scancode >> 8) ^ ~scancode) & 0xff) == 0) return false; break; /* * If the customer code (top 32-bit) is 0x800f, it is MCE else it * is regular mode-6a 32 bit */ case RC_PROTO_RC6_MCE: if ((scancode & 0xffff0000) != 0x800f0000) return false; break; case RC_PROTO_RC6_6A_32: if ((scancode & 0xffff0000) == 0x800f0000) return false; break; default: break; } return true; } /** * rc_validate_filter() - checks that the scancode and mask are valid and * provides sensible defaults * @dev: the struct rc_dev descriptor of the device * @filter: the scancode and mask * * return: 0 or -EINVAL if the filter is not valid */ static int rc_validate_filter(struct rc_dev *dev, struct rc_scancode_filter *filter) { u32 mask, s = filter->data; enum rc_proto protocol = dev->wakeup_protocol; if (protocol >= ARRAY_SIZE(protocols)) return -EINVAL; mask = protocols[protocol].scancode_bits; if (!rc_validate_scancode(protocol, s)) return -EINVAL; filter->data &= mask; filter->mask &= mask; /* * If we have to raw encode the IR for wakeup, we cannot have a mask */ if (dev->encode_wakeup && filter->mask != 0 && filter->mask != mask) return -EINVAL; return 0; } int rc_open(struct rc_dev *rdev) { int rval = 0; if (!rdev) return -EINVAL; mutex_lock(&rdev->lock); if (!rdev->registered) { rval = -ENODEV; } else { if (!rdev->users++ && rdev->open) rval = rdev->open(rdev); if (rval) rdev->users--; } mutex_unlock(&rdev->lock); return rval; } static int ir_open(struct input_dev *idev) { struct rc_dev *rdev = input_get_drvdata(idev); return rc_open(rdev); } void rc_close(struct rc_dev *rdev) { if (rdev) { mutex_lock(&rdev->lock); if (!--rdev->users && rdev->close && rdev->registered) rdev->close(rdev); mutex_unlock(&rdev->lock); } } static void ir_close(struct input_dev *idev) { struct rc_dev *rdev = input_get_drvdata(idev); rc_close(rdev); } /* class for /sys/class/rc */ static char *rc_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "rc/%s", dev_name(dev)); } static struct class rc_class = { .name = "rc", .devnode = rc_devnode, }; /* * These are the protocol textual descriptions that are * used by the sysfs protocols file. Note that the order * of the entries is relevant. */ static const struct { u64 type; const char *name; const char *module_name; } proto_names[] = { { RC_PROTO_BIT_NONE, "none", NULL }, { RC_PROTO_BIT_OTHER, "other", NULL }, { RC_PROTO_BIT_UNKNOWN, "unknown", NULL }, { RC_PROTO_BIT_RC5 | RC_PROTO_BIT_RC5X_20, "rc-5", "ir-rc5-decoder" }, { RC_PROTO_BIT_NEC | RC_PROTO_BIT_NECX | RC_PROTO_BIT_NEC32, "nec", "ir-nec-decoder" }, { RC_PROTO_BIT_RC6_0 | RC_PROTO_BIT_RC6_6A_20 | RC_PROTO_BIT_RC6_6A_24 | RC_PROTO_BIT_RC6_6A_32 | RC_PROTO_BIT_RC6_MCE, "rc-6", "ir-rc6-decoder" }, { RC_PROTO_BIT_JVC, "jvc", "ir-jvc-decoder" }, { RC_PROTO_BIT_SONY12 | RC_PROTO_BIT_SONY15 | RC_PROTO_BIT_SONY20, "sony", "ir-sony-decoder" }, { RC_PROTO_BIT_RC5_SZ, "rc-5-sz", "ir-rc5-decoder" }, { RC_PROTO_BIT_SANYO, "sanyo", "ir-sanyo-decoder" }, { RC_PROTO_BIT_SHARP, "sharp", "ir-sharp-decoder" }, { RC_PROTO_BIT_MCIR2_KBD | RC_PROTO_BIT_MCIR2_MSE, "mce_kbd", "ir-mce_kbd-decoder" }, { RC_PROTO_BIT_XMP, "xmp", "ir-xmp-decoder" }, { RC_PROTO_BIT_CEC, "cec", NULL }, { RC_PROTO_BIT_IMON, "imon", "ir-imon-decoder" }, { RC_PROTO_BIT_RCMM12 | RC_PROTO_BIT_RCMM24 | RC_PROTO_BIT_RCMM32, "rc-mm", "ir-rcmm-decoder" }, { RC_PROTO_BIT_XBOX_DVD, "xbox-dvd", NULL }, }; /** * struct rc_filter_attribute - Device attribute relating to a filter type. * @attr: Device attribute. * @type: Filter type. * @mask: false for filter value, true for filter mask. */ struct rc_filter_attribute { struct device_attribute attr; enum rc_filter_type type; bool mask; }; #define to_rc_filter_attr(a) container_of(a, struct rc_filter_attribute, attr) #define RC_FILTER_ATTR(_name, _mode, _show, _store, _type, _mask) \ struct rc_filter_attribute dev_attr_##_name = { \ .attr = __ATTR(_name, _mode, _show, _store), \ .type = (_type), \ .mask = (_mask), \ } /** * show_protocols() - shows the current IR protocol(s) * @device: the device descriptor * @mattr: the device attribute struct * @buf: a pointer to the output buffer * * This routine is a callback routine for input read the IR protocol type(s). * it is triggered by reading /sys/class/rc/rc?/protocols. * It returns the protocol names of supported protocols. * Enabled protocols are printed in brackets. * * dev->lock is taken to guard against races between * store_protocols and show_protocols. */ static ssize_t show_protocols(struct device *device, struct device_attribute *mattr, char *buf) { struct rc_dev *dev = to_rc_dev(device); u64 allowed, enabled; char *tmp = buf; int i; mutex_lock(&dev->lock); enabled = dev->enabled_protocols; allowed = dev->allowed_protocols; if (dev->raw && !allowed) allowed = ir_raw_get_allowed_protocols(); mutex_unlock(&dev->lock); dev_dbg(&dev->dev, "%s: allowed - 0x%llx, enabled - 0x%llx\n", __func__, (long long)allowed, (long long)enabled); for (i = 0; i < ARRAY_SIZE(proto_names); i++) { if (allowed & enabled & proto_names[i].type) tmp += sprintf(tmp, "[%s] ", proto_names[i].name); else if (allowed & proto_names[i].type) tmp += sprintf(tmp, "%s ", proto_names[i].name); if (allowed & proto_names[i].type) allowed &= ~proto_names[i].type; } #ifdef CONFIG_LIRC if (dev->driver_type == RC_DRIVER_IR_RAW) tmp += sprintf(tmp, "[lirc] "); #endif if (tmp != buf) tmp--; *tmp = '\n'; return tmp + 1 - buf; } /** * parse_protocol_change() - parses a protocol change request * @dev: rc_dev device * @protocols: pointer to the bitmask of current protocols * @buf: pointer to the buffer with a list of changes * * Writing "+proto" will add a protocol to the protocol mask. * Writing "-proto" will remove a protocol from protocol mask. * Writing "proto" will enable only "proto". * Writing "none" will disable all protocols. * Returns the number of changes performed or a negative error code. */ static int parse_protocol_change(struct rc_dev *dev, u64 *protocols, const char *buf) { const char *tmp; unsigned count = 0; bool enable, disable; u64 mask; int i; while ((tmp = strsep((char **)&buf, " \n")) != NULL) { if (!*tmp) break; if (*tmp == '+') { enable = true; disable = false; tmp++; } else if (*tmp == '-') { enable = false; disable = true; tmp++; } else { enable = false; disable = false; } for (i = 0; i < ARRAY_SIZE(proto_names); i++) { if (!strcasecmp(tmp, proto_names[i].name)) { mask = proto_names[i].type; break; } } if (i == ARRAY_SIZE(proto_names)) { if (!strcasecmp(tmp, "lirc")) mask = 0; else { dev_dbg(&dev->dev, "Unknown protocol: '%s'\n", tmp); return -EINVAL; } } count++; if (enable) *protocols |= mask; else if (disable) *protocols &= ~mask; else *protocols = mask; } if (!count) { dev_dbg(&dev->dev, "Protocol not specified\n"); return -EINVAL; } return count; } void ir_raw_load_modules(u64 *protocols) { u64 available; int i, ret; for (i = 0; i < ARRAY_SIZE(proto_names); i++) { if (proto_names[i].type == RC_PROTO_BIT_NONE || proto_names[i].type & (RC_PROTO_BIT_OTHER | RC_PROTO_BIT_UNKNOWN)) continue; available = ir_raw_get_allowed_protocols(); if (!(*protocols & proto_names[i].type & ~available)) continue; if (!proto_names[i].module_name) { pr_err("Can't enable IR protocol %s\n", proto_names[i].name); *protocols &= ~proto_names[i].type; continue; } ret = request_module("%s", proto_names[i].module_name); if (ret < 0) { pr_err("Couldn't load IR protocol module %s\n", proto_names[i].module_name); *protocols &= ~proto_names[i].type; continue; } msleep(20); available = ir_raw_get_allowed_protocols(); if (!(*protocols & proto_names[i].type & ~available)) continue; pr_err("Loaded IR protocol module %s, but protocol %s still not available\n", proto_names[i].module_name, proto_names[i].name); *protocols &= ~proto_names[i].type; } } /** * store_protocols() - changes the current/wakeup IR protocol(s) * @device: the device descriptor * @mattr: the device attribute struct * @buf: a pointer to the input buffer * @len: length of the input buffer * * This routine is for changing the IR protocol type. * It is triggered by writing to /sys/class/rc/rc?/[wakeup_]protocols. * See parse_protocol_change() for the valid commands. * Returns @len on success or a negative error code. * * dev->lock is taken to guard against races between * store_protocols and show_protocols. */ static ssize_t store_protocols(struct device *device, struct device_attribute *mattr, const char *buf, size_t len) { struct rc_dev *dev = to_rc_dev(device); u64 *current_protocols; struct rc_scancode_filter *filter; u64 old_protocols, new_protocols; ssize_t rc; dev_dbg(&dev->dev, "Normal protocol change requested\n"); current_protocols = &dev->enabled_protocols; filter = &dev->scancode_filter; if (!dev->change_protocol) { dev_dbg(&dev->dev, "Protocol switching not supported\n"); return -EINVAL; } mutex_lock(&dev->lock); if (!dev->registered) { mutex_unlock(&dev->lock); return -ENODEV; } old_protocols = *current_protocols; new_protocols = old_protocols; rc = parse_protocol_change(dev, &new_protocols, buf); if (rc < 0) goto out; if (dev->driver_type == RC_DRIVER_IR_RAW) ir_raw_load_modules(&new_protocols); rc = dev->change_protocol(dev, &new_protocols); if (rc < 0) { dev_dbg(&dev->dev, "Error setting protocols to 0x%llx\n", (long long)new_protocols); goto out; } if (new_protocols != old_protocols) { *current_protocols = new_protocols; dev_dbg(&dev->dev, "Protocols changed to 0x%llx\n", (long long)new_protocols); } /* * If a protocol change was attempted the filter may need updating, even * if the actual protocol mask hasn't changed (since the driver may have * cleared the filter). * Try setting the same filter with the new protocol (if any). * Fall back to clearing the filter. */ if (dev->s_filter && filter->mask) { if (new_protocols) rc = dev->s_filter(dev, filter); else rc = -1; if (rc < 0) { filter->data = 0; filter->mask = 0; dev->s_filter(dev, filter); } } rc = len; out: mutex_unlock(&dev->lock); return rc; } /** * show_filter() - shows the current scancode filter value or mask * @device: the device descriptor * @attr: the device attribute struct * @buf: a pointer to the output buffer * * This routine is a callback routine to read a scancode filter value or mask. * It is triggered by reading /sys/class/rc/rc?/[wakeup_]filter[_mask]. * It prints the current scancode filter value or mask of the appropriate filter * type in hexadecimal into @buf and returns the size of the buffer. * * Bits of the filter value corresponding to set bits in the filter mask are * compared against input scancodes and non-matching scancodes are discarded. * * dev->lock is taken to guard against races between * store_filter and show_filter. */ static ssize_t show_filter(struct device *device, struct device_attribute *attr, char *buf) { struct rc_dev *dev = to_rc_dev(device); struct rc_filter_attribute *fattr = to_rc_filter_attr(attr); struct rc_scancode_filter *filter; u32 val; mutex_lock(&dev->lock); if (fattr->type == RC_FILTER_NORMAL) filter = &dev->scancode_filter; else filter = &dev->scancode_wakeup_filter; if (fattr->mask) val = filter->mask; else val = filter->data; mutex_unlock(&dev->lock); return sprintf(buf, "%#x\n", val); } /** * store_filter() - changes the scancode filter value * @device: the device descriptor * @attr: the device attribute struct * @buf: a pointer to the input buffer * @len: length of the input buffer * * This routine is for changing a scancode filter value or mask. * It is triggered by writing to /sys/class/rc/rc?/[wakeup_]filter[_mask]. * Returns -EINVAL if an invalid filter value for the current protocol was * specified or if scancode filtering is not supported by the driver, otherwise * returns @len. * * Bits of the filter value corresponding to set bits in the filter mask are * compared against input scancodes and non-matching scancodes are discarded. * * dev->lock is taken to guard against races between * store_filter and show_filter. */ static ssize_t store_filter(struct device *device, struct device_attribute *attr, const char *buf, size_t len) { struct rc_dev *dev = to_rc_dev(device); struct rc_filter_attribute *fattr = to_rc_filter_attr(attr); struct rc_scancode_filter new_filter, *filter; int ret; unsigned long val; int (*set_filter)(struct rc_dev *dev, struct rc_scancode_filter *filter); ret = kstrtoul(buf, 0, &val); if (ret < 0) return ret; if (fattr->type == RC_FILTER_NORMAL) { set_filter = dev->s_filter; filter = &dev->scancode_filter; } else { set_filter = dev->s_wakeup_filter; filter = &dev->scancode_wakeup_filter; } if (!set_filter) return -EINVAL; mutex_lock(&dev->lock); if (!dev->registered) { mutex_unlock(&dev->lock); return -ENODEV; } new_filter = *filter; if (fattr->mask) new_filter.mask = val; else new_filter.data = val; if (fattr->type == RC_FILTER_WAKEUP) { /* * Refuse to set a filter unless a protocol is enabled * and the filter is valid for that protocol */ if (dev->wakeup_protocol != RC_PROTO_UNKNOWN) ret = rc_validate_filter(dev, &new_filter); else ret = -EINVAL; if (ret != 0) goto unlock; } if (fattr->type == RC_FILTER_NORMAL && !dev->enabled_protocols && val) { /* refuse to set a filter unless a protocol is enabled */ ret = -EINVAL; goto unlock; } ret = set_filter(dev, &new_filter); if (ret < 0) goto unlock; *filter = new_filter; unlock: mutex_unlock(&dev->lock); return (ret < 0) ? ret : len; } /** * show_wakeup_protocols() - shows the wakeup IR protocol * @device: the device descriptor * @mattr: the device attribute struct * @buf: a pointer to the output buffer * * This routine is a callback routine for input read the IR protocol type(s). * it is triggered by reading /sys/class/rc/rc?/wakeup_protocols. * It returns the protocol names of supported protocols. * The enabled protocols are printed in brackets. * * dev->lock is taken to guard against races between * store_wakeup_protocols and show_wakeup_protocols. */ static ssize_t show_wakeup_protocols(struct device *device, struct device_attribute *mattr, char *buf) { struct rc_dev *dev = to_rc_dev(device); u64 allowed; enum rc_proto enabled; char *tmp = buf; int i; mutex_lock(&dev->lock); allowed = dev->allowed_wakeup_protocols; enabled = dev->wakeup_protocol; mutex_unlock(&dev->lock); dev_dbg(&dev->dev, "%s: allowed - 0x%llx, enabled - %d\n", __func__, (long long)allowed, enabled); for (i = 0; i < ARRAY_SIZE(protocols); i++) { if (allowed & (1ULL << i)) { if (i == enabled) tmp += sprintf(tmp, "[%s] ", protocols[i].name); else tmp += sprintf(tmp, "%s ", protocols[i].name); } } if (tmp != buf) tmp--; *tmp = '\n'; return tmp + 1 - buf; } /** * store_wakeup_protocols() - changes the wakeup IR protocol(s) * @device: the device descriptor * @mattr: the device attribute struct * @buf: a pointer to the input buffer * @len: length of the input buffer * * This routine is for changing the IR protocol type. * It is triggered by writing to /sys/class/rc/rc?/wakeup_protocols. * Returns @len on success or a negative error code. * * dev->lock is taken to guard against races between * store_wakeup_protocols and show_wakeup_protocols. */ static ssize_t store_wakeup_protocols(struct device *device, struct device_attribute *mattr, const char *buf, size_t len) { struct rc_dev *dev = to_rc_dev(device); enum rc_proto protocol = RC_PROTO_UNKNOWN; ssize_t rc; u64 allowed; int i; mutex_lock(&dev->lock); if (!dev->registered) { mutex_unlock(&dev->lock); return -ENODEV; } allowed = dev->allowed_wakeup_protocols; if (!sysfs_streq(buf, "none")) { for (i = 0; i < ARRAY_SIZE(protocols); i++) { if ((allowed & (1ULL << i)) && sysfs_streq(buf, protocols[i].name)) { protocol = i; break; } } if (i == ARRAY_SIZE(protocols)) { rc = -EINVAL; goto out; } if (dev->encode_wakeup) { u64 mask = 1ULL << protocol; ir_raw_load_modules(&mask); if (!mask) { rc = -EINVAL; goto out; } } } if (dev->wakeup_protocol != protocol) { dev->wakeup_protocol = protocol; dev_dbg(&dev->dev, "Wakeup protocol changed to %d\n", protocol); if (protocol == RC_PROTO_RC6_MCE) dev->scancode_wakeup_filter.data = 0x800f0000; else dev->scancode_wakeup_filter.data = 0; dev->scancode_wakeup_filter.mask = 0; rc = dev->s_wakeup_filter(dev, &dev->scancode_wakeup_filter); if (rc == 0) rc = len; } else { rc = len; } out: mutex_unlock(&dev->lock); return rc; } static void rc_dev_release(struct device *device) { struct rc_dev *dev = to_rc_dev(device); kfree(dev); } static int rc_dev_uevent(const struct device *device, struct kobj_uevent_env *env) { struct rc_dev *dev = to_rc_dev(device); int ret = 0; mutex_lock(&dev->lock); if (!dev->registered) ret = -ENODEV; if (ret == 0 && dev->rc_map.name) ret = add_uevent_var(env, "NAME=%s", dev->rc_map.name); if (ret == 0 && dev->driver_name) ret = add_uevent_var(env, "DRV_NAME=%s", dev->driver_name); if (ret == 0 && dev->device_name) ret = add_uevent_var(env, "DEV_NAME=%s", dev->device_name); mutex_unlock(&dev->lock); return ret; } /* * Static device attribute struct with the sysfs attributes for IR's */ static struct device_attribute dev_attr_ro_protocols = __ATTR(protocols, 0444, show_protocols, NULL); static struct device_attribute dev_attr_rw_protocols = __ATTR(protocols, 0644, show_protocols, store_protocols); static DEVICE_ATTR(wakeup_protocols, 0644, show_wakeup_protocols, store_wakeup_protocols); static RC_FILTER_ATTR(filter, S_IRUGO|S_IWUSR, show_filter, store_filter, RC_FILTER_NORMAL, false); static RC_FILTER_ATTR(filter_mask, S_IRUGO|S_IWUSR, show_filter, store_filter, RC_FILTER_NORMAL, true); static RC_FILTER_ATTR(wakeup_filter, S_IRUGO|S_IWUSR, show_filter, store_filter, RC_FILTER_WAKEUP, false); static RC_FILTER_ATTR(wakeup_filter_mask, S_IRUGO|S_IWUSR, show_filter, store_filter, RC_FILTER_WAKEUP, true); static struct attribute *rc_dev_rw_protocol_attrs[] = { &dev_attr_rw_protocols.attr, NULL, }; static const struct attribute_group rc_dev_rw_protocol_attr_grp = { .attrs = rc_dev_rw_protocol_attrs, }; static struct attribute *rc_dev_ro_protocol_attrs[] = { &dev_attr_ro_protocols.attr, NULL, }; static const struct attribute_group rc_dev_ro_protocol_attr_grp = { .attrs = rc_dev_ro_protocol_attrs, }; static struct attribute *rc_dev_filter_attrs[] = { &dev_attr_filter.attr.attr, &dev_attr_filter_mask.attr.attr, NULL, }; static const struct attribute_group rc_dev_filter_attr_grp = { .attrs = rc_dev_filter_attrs, }; static struct attribute *rc_dev_wakeup_filter_attrs[] = { &dev_attr_wakeup_filter.attr.attr, &dev_attr_wakeup_filter_mask.attr.attr, &dev_attr_wakeup_protocols.attr, NULL, }; static const struct attribute_group rc_dev_wakeup_filter_attr_grp = { .attrs = rc_dev_wakeup_filter_attrs, }; static const struct device_type rc_dev_type = { .release = rc_dev_release, .uevent = rc_dev_uevent, }; struct rc_dev *rc_allocate_device(enum rc_driver_type type) { struct rc_dev *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; if (type != RC_DRIVER_IR_RAW_TX) { dev->input_dev = input_allocate_device(); if (!dev->input_dev) { kfree(dev); return NULL; } dev->input_dev->getkeycode = ir_getkeycode; dev->input_dev->setkeycode = ir_setkeycode; input_set_drvdata(dev->input_dev, dev); dev->timeout = IR_DEFAULT_TIMEOUT; timer_setup(&dev->timer_keyup, ir_timer_keyup, 0); timer_setup(&dev->timer_repeat, ir_timer_repeat, 0); spin_lock_init(&dev->rc_map.lock); spin_lock_init(&dev->keylock); } mutex_init(&dev->lock); dev->dev.type = &rc_dev_type; dev->dev.class = &rc_class; device_initialize(&dev->dev); dev->driver_type = type; __module_get(THIS_MODULE); return dev; } EXPORT_SYMBOL_GPL(rc_allocate_device); void rc_free_device(struct rc_dev *dev) { if (!dev) return; input_free_device(dev->input_dev); put_device(&dev->dev); /* kfree(dev) will be called by the callback function rc_dev_release() */ module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(rc_free_device); static void devm_rc_alloc_release(struct device *dev, void *res) { rc_free_device(*(struct rc_dev **)res); } struct rc_dev *devm_rc_allocate_device(struct device *dev, enum rc_driver_type type) { struct rc_dev **dr, *rc; dr = devres_alloc(devm_rc_alloc_release, sizeof(*dr), GFP_KERNEL); if (!dr) return NULL; rc = rc_allocate_device(type); if (!rc) { devres_free(dr); return NULL; } rc->dev.parent = dev; rc->managed_alloc = true; *dr = rc; devres_add(dev, dr); return rc; } EXPORT_SYMBOL_GPL(devm_rc_allocate_device); static int rc_prepare_rx_device(struct rc_dev *dev) { int rc; struct rc_map *rc_map; u64 rc_proto; if (!dev->map_name) return -EINVAL; rc_map = rc_map_get(dev->map_name); if (!rc_map) rc_map = rc_map_get(RC_MAP_EMPTY); if (!rc_map || !rc_map->scan || rc_map->size == 0) return -EINVAL; rc = ir_setkeytable(dev, rc_map); if (rc) return rc; rc_proto = BIT_ULL(rc_map->rc_proto); if (dev->driver_type == RC_DRIVER_SCANCODE && !dev->change_protocol) dev->enabled_protocols = dev->allowed_protocols; if (dev->driver_type == RC_DRIVER_IR_RAW) ir_raw_load_modules(&rc_proto); if (dev->change_protocol) { rc = dev->change_protocol(dev, &rc_proto); if (rc < 0) goto out_table; dev->enabled_protocols = rc_proto; } /* Keyboard events */ set_bit(EV_KEY, dev->input_dev->evbit); set_bit(EV_REP, dev->input_dev->evbit); set_bit(EV_MSC, dev->input_dev->evbit); set_bit(MSC_SCAN, dev->input_dev->mscbit); /* Pointer/mouse events */ set_bit(INPUT_PROP_POINTING_STICK, dev->input_dev->propbit); set_bit(EV_REL, dev->input_dev->evbit); set_bit(REL_X, dev->input_dev->relbit); set_bit(REL_Y, dev->input_dev->relbit); if (dev->open) dev->input_dev->open = ir_open; if (dev->close) dev->input_dev->close = ir_close; dev->input_dev->dev.parent = &dev->dev; memcpy(&dev->input_dev->id, &dev->input_id, sizeof(dev->input_id)); dev->input_dev->phys = dev->input_phys; dev->input_dev->name = dev->device_name; return 0; out_table: ir_free_table(&dev->rc_map); return rc; } static int rc_setup_rx_device(struct rc_dev *dev) { int rc; /* rc_open will be called here */ rc = input_register_device(dev->input_dev); if (rc) return rc; /* * Default delay of 250ms is too short for some protocols, especially * since the timeout is currently set to 250ms. Increase it to 500ms, * to avoid wrong repetition of the keycodes. Note that this must be * set after the call to input_register_device(). */ if (dev->allowed_protocols == RC_PROTO_BIT_CEC) dev->input_dev->rep[REP_DELAY] = 0; else dev->input_dev->rep[REP_DELAY] = 500; /* * As a repeat event on protocols like RC-5 and NEC take as long as * 110/114ms, using 33ms as a repeat period is not the right thing * to do. */ dev->input_dev->rep[REP_PERIOD] = 125; return 0; } static void rc_free_rx_device(struct rc_dev *dev) { if (!dev) return; if (dev->input_dev) { input_unregister_device(dev->input_dev); dev->input_dev = NULL; } ir_free_table(&dev->rc_map); } int rc_register_device(struct rc_dev *dev) { const char *path; int attr = 0; int minor; int rc; if (!dev) return -EINVAL; minor = ida_alloc_max(&rc_ida, RC_DEV_MAX - 1, GFP_KERNEL); if (minor < 0) return minor; dev->minor = minor; dev_set_name(&dev->dev, "rc%u", dev->minor); dev_set_drvdata(&dev->dev, dev); dev->dev.groups = dev->sysfs_groups; if (dev->driver_type == RC_DRIVER_SCANCODE && !dev->change_protocol) dev->sysfs_groups[attr++] = &rc_dev_ro_protocol_attr_grp; else if (dev->driver_type != RC_DRIVER_IR_RAW_TX) dev->sysfs_groups[attr++] = &rc_dev_rw_protocol_attr_grp; if (dev->s_filter) dev->sysfs_groups[attr++] = &rc_dev_filter_attr_grp; if (dev->s_wakeup_filter) dev->sysfs_groups[attr++] = &rc_dev_wakeup_filter_attr_grp; dev->sysfs_groups[attr++] = NULL; if (dev->driver_type == RC_DRIVER_IR_RAW) { rc = ir_raw_event_prepare(dev); if (rc < 0) goto out_minor; } if (dev->driver_type != RC_DRIVER_IR_RAW_TX) { rc = rc_prepare_rx_device(dev); if (rc) goto out_raw; } dev->registered = true; rc = device_add(&dev->dev); if (rc) goto out_rx_free; path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); dev_info(&dev->dev, "%s as %s\n", dev->device_name ?: "Unspecified device", path ?: "N/A"); kfree(path); /* * once the input device is registered in rc_setup_rx_device, * userspace can open the input device and rc_open() will be called * as a result. This results in driver code being allowed to submit * keycodes with rc_keydown, so lirc must be registered first. */ if (dev->allowed_protocols != RC_PROTO_BIT_CEC) { rc = lirc_register(dev); if (rc < 0) goto out_dev; } if (dev->driver_type != RC_DRIVER_IR_RAW_TX) { rc = rc_setup_rx_device(dev); if (rc) goto out_lirc; } if (dev->driver_type == RC_DRIVER_IR_RAW) { rc = ir_raw_event_register(dev); if (rc < 0) goto out_rx; } dev_dbg(&dev->dev, "Registered rc%u (driver: %s)\n", dev->minor, dev->driver_name ? dev->driver_name : "unknown"); return 0; out_rx: rc_free_rx_device(dev); out_lirc: if (dev->allowed_protocols != RC_PROTO_BIT_CEC) lirc_unregister(dev); out_dev: device_del(&dev->dev); out_rx_free: ir_free_table(&dev->rc_map); out_raw: ir_raw_event_free(dev); out_minor: ida_free(&rc_ida, minor); return rc; } EXPORT_SYMBOL_GPL(rc_register_device); static void devm_rc_release(struct device *dev, void *res) { rc_unregister_device(*(struct rc_dev **)res); } int devm_rc_register_device(struct device *parent, struct rc_dev *dev) { struct rc_dev **dr; int ret; dr = devres_alloc(devm_rc_release, sizeof(*dr), GFP_KERNEL); if (!dr) return -ENOMEM; ret = rc_register_device(dev); if (ret) { devres_free(dr); return ret; } *dr = dev; devres_add(parent, dr); return 0; } EXPORT_SYMBOL_GPL(devm_rc_register_device); void rc_unregister_device(struct rc_dev *dev) { if (!dev) return; if (dev->driver_type == RC_DRIVER_IR_RAW) ir_raw_event_unregister(dev); del_timer_sync(&dev->timer_keyup); del_timer_sync(&dev->timer_repeat); mutex_lock(&dev->lock); if (dev->users && dev->close) dev->close(dev); dev->registered = false; mutex_unlock(&dev->lock); rc_free_rx_device(dev); /* * lirc device should be freed with dev->registered = false, so * that userspace polling will get notified. */ if (dev->allowed_protocols != RC_PROTO_BIT_CEC) lirc_unregister(dev); device_del(&dev->dev); ida_free(&rc_ida, dev->minor); if (!dev->managed_alloc) rc_free_device(dev); } EXPORT_SYMBOL_GPL(rc_unregister_device); /* * Init/exit code for the module. Basically, creates/removes /sys/class/rc */ static int __init rc_core_init(void) { int rc = class_register(&rc_class); if (rc) { pr_err("rc_core: unable to register rc class\n"); return rc; } rc = lirc_dev_init(); if (rc) { pr_err("rc_core: unable to init lirc\n"); class_unregister(&rc_class); return rc; } led_trigger_register_simple("rc-feedback", &led_feedback); rc_map_register(&empty_map); #ifdef CONFIG_MEDIA_CEC_RC rc_map_register(&cec_map); #endif return 0; } static void __exit rc_core_exit(void) { lirc_dev_exit(); class_unregister(&rc_class); led_trigger_unregister_simple(led_feedback); #ifdef CONFIG_MEDIA_CEC_RC rc_map_unregister(&cec_map); #endif rc_map_unregister(&empty_map); } subsys_initcall(rc_core_init); module_exit(rc_core_exit); MODULE_AUTHOR("Mauro Carvalho Chehab"); MODULE_LICENSE("GPL v2"); |
| 32 38 526 555 90 557 8 10 32 50 303 6 5 284 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { refcount_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred_many - Get references on a new set of credentials * @cred: The new credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of new credentials. The caller must * release all acquired references. */ static inline struct cred *get_new_cred_many(struct cred *cred, int nr) { atomic_long_add(nr, &cred->usage); return cred; } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { return get_new_cred_many(cred, 1); } /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of credentials. The caller must release * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; nonconst_cred->non_rcu = 0; return get_new_cred_many(nonconst_cred, nr); } /* * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. */ static inline const struct cred *get_cred(const struct cred *cred) { return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } /* * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. */ static inline void put_cred(const struct cred *cred) { put_cred_many(cred, 1); } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) #define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 78 19 19 33 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __string(dev, dev ? dev->name : "NULL") __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( __be32 *p32; __entry->family = tbl->family; __assign_str(dev); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { struct in6_addr *pin6; pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; if (lladdr) memcpy(__entry->new_lladdr, lladdr, lladdr_len); __entry->new_state = new; __entry->update_flags = flags; __entry->pid = nlmsg_pid; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu new_lladdr %s " "new_state %s update_flags %02x pid %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), neigh_state_str(__entry->new_state), __entry->update_flags, __entry->pid) ); DECLARE_EVENT_CLASS(neigh__update, TP_PROTO(struct neighbour *n, int err), TP_ARGS(n, err), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __field(u32, err) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; __entry->err = err; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu err %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __entry->err) ); DEFINE_EVENT(neigh__update, neigh_update_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_timer_handler, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_dead, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, TP_PROTO(struct neighbour *neigh, int rc), TP_ARGS(neigh, rc) ); #endif /* _TRACE_NEIGH_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 13 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap #if !defined(_TRACE_MMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_H #include <linux/tracepoint.h> TRACE_EVENT(vm_unmapped_area, TP_PROTO(unsigned long addr, struct vm_unmapped_area_info *info), TP_ARGS(addr, info), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, total_vm) __field(unsigned long, flags) __field(unsigned long, length) __field(unsigned long, low_limit) __field(unsigned long, high_limit) __field(unsigned long, align_mask) __field(unsigned long, align_offset) ), TP_fast_assign( __entry->addr = addr; __entry->total_vm = current->mm->total_vm; __entry->flags = info->flags; __entry->length = info->length; __entry->low_limit = info->low_limit; __entry->high_limit = info->high_limit; __entry->align_mask = info->align_mask; __entry->align_offset = info->align_offset; ), TP_printk("addr=0x%lx err=%ld total_vm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx", IS_ERR_VALUE(__entry->addr) ? 0 : __entry->addr, IS_ERR_VALUE(__entry->addr) ? __entry->addr : 0, __entry->total_vm, __entry->flags, __entry->length, __entry->low_limit, __entry->high_limit, __entry->align_mask, __entry->align_offset) ); TRACE_EVENT(vma_mas_szero, TP_PROTO(struct maple_tree *mt, unsigned long start, unsigned long end), TP_ARGS(mt, start, end), TP_STRUCT__entry( __field(struct maple_tree *, mt) __field(unsigned long, start) __field(unsigned long, end) ), TP_fast_assign( __entry->mt = mt; __entry->start = start; __entry->end = end; ), TP_printk("mt_mod %p, (NULL), SNULL, %lu, %lu,", __entry->mt, (unsigned long) __entry->start, (unsigned long) __entry->end ) ); TRACE_EVENT(vma_store, TP_PROTO(struct maple_tree *mt, struct vm_area_struct *vma), TP_ARGS(mt, vma), TP_STRUCT__entry( __field(struct maple_tree *, mt) __field(struct vm_area_struct *, vma) __field(unsigned long, vm_start) __field(unsigned long, vm_end) ), TP_fast_assign( __entry->mt = mt; __entry->vma = vma; __entry->vm_start = vma->vm_start; __entry->vm_end = vma->vm_end - 1; ), TP_printk("mt_mod %p, (%p), STORE, %lu, %lu,", __entry->mt, __entry->vma, (unsigned long) __entry->vm_start, (unsigned long) __entry->vm_end ) ); TRACE_EVENT(exit_mmap, TP_PROTO(struct mm_struct *mm), TP_ARGS(mm), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(struct maple_tree *, mt) ), TP_fast_assign( __entry->mm = mm; __entry->mt = &mm->mm_mt; ), TP_printk("mt_mod %p, DESTROY", __entry->mt ) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SHRINKER_H #define _LINUX_SHRINKER_H #include <linux/atomic.h> #include <linux/types.h> #include <linux/refcount.h> #include <linux/completion.h> #define SHRINKER_UNIT_BITS BITS_PER_LONG /* * Bitmap and deferred work of shrinker::id corresponding to memcg-aware * shrinkers, which have elements charged to the memcg. */ struct shrinker_info_unit { atomic_long_t nr_deferred[SHRINKER_UNIT_BITS]; DECLARE_BITMAP(map, SHRINKER_UNIT_BITS); }; struct shrinker_info { struct rcu_head rcu; int map_nr_max; struct shrinker_info_unit *unit[]; }; /* * This struct is used to pass information from page reclaim to the shrinkers. * We consolidate the values for easier extension later. * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. */ struct shrink_control { gfp_t gfp_mask; /* current node being shrunk (for NUMA aware shrinkers) */ int nid; /* * How many objects scan_objects should scan and try to reclaim. * This is reset before every call, so it is safe for callees * to modify. */ unsigned long nr_to_scan; /* * How many objects did scan_objects process? * This defaults to nr_to_scan before every call, but the callee * should track its actual progress. */ unsigned long nr_scanned; /* current memcg being shrunk (for memcg aware shrinkers) */ struct mem_cgroup *memcg; }; #define SHRINK_STOP (~0UL) #define SHRINK_EMPTY (~0UL - 1) /* * A callback you can register to apply pressure to ageable caches. * * @count_objects should return the number of freeable items in the cache. If * there are no objects to free, it should return SHRINK_EMPTY, while 0 is * returned in cases of the number of freeable items cannot be determined * or shrinker should skip this cache for this time (e.g., their number * is below shrinkable limit). No deadlock checks should be done during the * count callback - the shrinker relies on aggregating scan counts that couldn't * be executed due to potential deadlocks to be run at a later call when the * deadlock condition is no longer pending. * * @scan_objects will only be called if @count_objects returned a non-zero * value for the number of freeable objects. The callout should scan the cache * and attempt to free items from the cache. It should then return the number * of objects freed during the scan, or SHRINK_STOP if progress cannot be made * due to potential deadlocks. If SHRINK_STOP is returned, then no further * attempts to call the @scan_objects will be made from the current reclaim * context. * * @flags determine the shrinker abilities, like numa awareness */ struct shrinker { unsigned long (*count_objects)(struct shrinker *, struct shrink_control *sc); unsigned long (*scan_objects)(struct shrinker *, struct shrink_control *sc); long batch; /* reclaim batch size, 0 = default */ int seeks; /* seeks to recreate an obj */ unsigned flags; /* * The reference count of this shrinker. Registered shrinker have an * initial refcount of 1, then the lookup operations are now allowed * to use it via shrinker_try_get(). Later in the unregistration step, * the initial refcount will be discarded, and will free the shrinker * asynchronously via RCU after its refcount reaches 0. */ refcount_t refcount; struct completion done; /* use to wait for refcount to reach 0 */ struct rcu_head rcu; void *private_data; /* These are for internal use */ struct list_head list; #ifdef CONFIG_MEMCG /* ID in shrinker_idr */ int id; #endif #ifdef CONFIG_SHRINKER_DEBUG int debugfs_id; const char *name; struct dentry *debugfs_entry; #endif /* objs pending delete, per node */ atomic_long_t *nr_deferred; }; #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Internal flags */ #define SHRINKER_REGISTERED BIT(0) #define SHRINKER_ALLOCATED BIT(1) /* Flags for users to use */ #define SHRINKER_NUMA_AWARE BIT(2) #define SHRINKER_MEMCG_AWARE BIT(3) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ #define SHRINKER_NONSLAB BIT(4) __printf(2, 3) struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...); void shrinker_register(struct shrinker *shrinker); void shrinker_free(struct shrinker *shrinker); static inline bool shrinker_try_get(struct shrinker *shrinker) { return refcount_inc_not_zero(&shrinker->refcount); } static inline void shrinker_put(struct shrinker *shrinker) { if (refcount_dec_and_test(&shrinker->refcount)) complete(&shrinker->done); } #ifdef CONFIG_SHRINKER_DEBUG extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { return 0; } #endif /* CONFIG_SHRINKER_DEBUG */ #endif /* _LINUX_SHRINKER_H */ |
| 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 | /* tnum: tracked (or tristate) numbers * * A tnum tracks knowledge about the bits of a value. Each bit can be either * known (0 or 1), or unknown (x). Arithmetic operations on tnums will * propagate the unknown bits such that the tnum result represents all the * possible results for possible values of the operands. */ #ifndef _LINUX_TNUM_H #define _LINUX_TNUM_H #include <linux/types.h> struct tnum { u64 value; u64 mask; }; /* Constructors */ /* Represent a known constant as a tnum. */ struct tnum tnum_const(u64 value); /* A completely unknown value */ extern const struct tnum tnum_unknown; /* An unknown value that is a superset of @min <= value <= @max. * * Could include values outside the range of [@min, @max]. * For example tnum_range(0, 2) is represented by {0, 1, 2, *3*}, * rather than the intended set of {0, 1, 2}. */ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ /* Shift a tnum left (by a fixed shift) */ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ struct tnum tnum_sub(struct tnum a, struct tnum b); /* Bitwise-AND, return @a & @b */ struct tnum tnum_and(struct tnum a, struct tnum b); /* Bitwise-OR, return @a | @b */ struct tnum tnum_or(struct tnum a, struct tnum b); /* Bitwise-XOR, return @a ^ @b */ struct tnum tnum_xor(struct tnum a, struct tnum b); /* Multiply two tnums, return @a * @b */ struct tnum tnum_mul(struct tnum a, struct tnum b); /* Return a tnum representing numbers satisfying both @a and @b */ struct tnum tnum_intersect(struct tnum a, struct tnum b); /* Return @a with all but the lowest @size bytes cleared */ struct tnum tnum_cast(struct tnum a, u8 size); /* Returns true if @a is a known constant */ static inline bool tnum_is_const(struct tnum a) { return !a.mask; } /* Returns true if @a == tnum_const(@b) */ static inline bool tnum_equals_const(struct tnum a, u64 b) { return tnum_is_const(a) && a.value == b; } /* Returns true if @a is completely unknown */ static inline bool tnum_is_unknown(struct tnum a) { return !~a.mask; } /* Returns true if @a is known to be a multiple of @size. * @size must be a power of two. */ bool tnum_is_aligned(struct tnum a, u64 size); /* Returns true if @b represents a subset of @a. * * Note that using tnum_range() as @a requires extra cautions as tnum_in() may * return true unexpectedly due to tnum limited ability to represent tight * range, e.g. * * tnum_in(tnum_range(0, 2), tnum_const(3)) == true * * As a rule of thumb, if @a is explicitly coded rather than coming from * reg->var_off, it should be in form of tnum_const(), tnum_range(0, 2**n - 1), * or tnum_range(2**n, 2**(n+1) - 1). */ bool tnum_in(struct tnum a, struct tnum b); /* Formatting functions. These have snprintf-like semantics: they will write * up to @size bytes (including the terminating NUL byte), and return the number * of bytes (excluding the terminating NUL) which would have been written had * sufficient space been available. (Thus tnum_sbin always returns 64.) */ /* Format a tnum as a pair of hex numbers (value; mask) */ int tnum_strn(char *str, size_t size, struct tnum a); /* Format a tnum as tristate binary expansion */ int tnum_sbin(char *str, size_t size, struct tnum a); /* Returns the 32-bit subreg */ struct tnum tnum_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg cleared */ struct tnum tnum_clear_subreg(struct tnum a); /* Returns the tnum with the lower 32-bit subreg in *reg* set to the lower * 32-bit subreg in *subreg* */ struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg); /* Returns the tnum with the lower 32-bit subreg set to value */ struct tnum tnum_const_subreg(struct tnum a, u32 value); /* Returns true if 32-bit subreg @a is a known constant*/ static inline bool tnum_subreg_is_const(struct tnum a) { return !(tnum_subreg(a)).mask; } #endif /* _LINUX_TNUM_H */ |
| 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* dummy.c: a dummy net driver The purpose of this driver is to provide a device to point a route through, but not to actually transmit packets. Why? If you have a machine whose only connection is an occasional PPP/SLIP/PLIP link, you can only connect to your own hostname when the link is up. Otherwise you have to use localhost. This isn't very consistent. One solution is to set up a dummy link using PPP/SLIP/PLIP, but this seems (to me) too much overhead for too little gain. This driver provides a small alternative. Thus you can do [when not running slip] ifconfig dummy slip.addr.ess.here up [to go to slip] ifconfig dummy down dip whatever This was written by looking at Donald Becker's skeleton driver and the loopback driver. I then threw away anything that didn't apply! Thanks to Alan Cox for the key clue on what to do with misguided packets. Nick Holloway, 27th May 1994 [I tweaked this explanation a little but that's all] Alan Cox, 30th May 1994 */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/rtnetlink.h> #include <linux/net_tstamp.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #define DRV_NAME "dummy" static int numdummies = 1; /* fake multicast ability */ static void set_multicast_list(struct net_device *dev) { } static void dummy_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { dev_lstats_read(dev, &stats->tx_packets, &stats->tx_bytes); } static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev) { dev_lstats_add(dev, skb->len); skb_tx_timestamp(skb); dev_kfree_skb(skb); return NETDEV_TX_OK; } static int dummy_dev_init(struct net_device *dev) { dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; netdev_lockdep_set_classes(dev); return 0; } static int dummy_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) netif_carrier_on(dev); else netif_carrier_off(dev); return 0; } static const struct net_device_ops dummy_netdev_ops = { .ndo_init = dummy_dev_init, .ndo_start_xmit = dummy_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = set_multicast_list, .ndo_set_mac_address = eth_mac_addr, .ndo_get_stats64 = dummy_get_stats64, .ndo_change_carrier = dummy_change_carrier, }; static const struct ethtool_ops dummy_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, }; static void dummy_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &dummy_netdev_ops; dev->ethtool_ops = &dummy_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST; dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX; dev->features |= NETIF_F_GSO_ENCAP_ALL; dev->hw_features |= dev->features; dev->hw_enc_features |= dev->features; eth_hw_addr_random(dev); dev->min_mtu = 0; dev->max_mtu = 0; } static int dummy_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static struct rtnl_link_ops dummy_link_ops __read_mostly = { .kind = DRV_NAME, .setup = dummy_setup, .validate = dummy_validate, }; /* Number of dummy devices to be set up by this module. */ module_param(numdummies, int, 0); MODULE_PARM_DESC(numdummies, "Number of dummy pseudo devices"); static int __init dummy_init_one(void) { struct net_device *dev_dummy; int err; dev_dummy = alloc_netdev(0, "dummy%d", NET_NAME_ENUM, dummy_setup); if (!dev_dummy) return -ENOMEM; dev_dummy->rtnl_link_ops = &dummy_link_ops; err = register_netdevice(dev_dummy); if (err < 0) goto err; return 0; err: free_netdev(dev_dummy); return err; } static int __init dummy_init_module(void) { int i, err = 0; down_write(&pernet_ops_rwsem); rtnl_lock(); err = __rtnl_link_register(&dummy_link_ops); if (err < 0) goto out; for (i = 0; i < numdummies && !err; i++) { err = dummy_init_one(); cond_resched(); } if (err < 0) __rtnl_link_unregister(&dummy_link_ops); out: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } static void __exit dummy_cleanup_module(void) { rtnl_link_unregister(&dummy_link_ops); } module_init(dummy_init_module); module_exit(dummy_cleanup_module); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Dummy netdevice driver which discards all packets sent to it"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 3 3 5 5 10 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU #ifdef CONFIG_SWAP #include <linux/swapfile.h> #endif /* CONFIG_SWAP */ /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS #define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ #define SWP_PFN_BITS min_t(int, \ sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ #define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: * * |----------+--------------------| * | swp_type | swp_offset | * |----------+--------+-+-+-------| * | | resv |D|A| PFN | * |----------+--------+-+-+-------| * * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) * * Note: A/D bits will be stored in migration entries iff there're enough * free bits in arch specific swp offset. By default we'll ignore A/D bits * when migrating a page. Please refer to migration_entry_supports_ad() * for more information. If there're more bits besides PFN and A/D bits, * they should be reserved and always be zeros. */ #define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) #define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) #define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) #define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) #define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) static inline bool is_pfn_swap_entry(swp_entry_t entry); /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_exclusive(pte)) pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* * This should only be called upon a pfn swap entry to get the PFN stored * in the swap entry. Please refers to is_pfn_swap_entry() for definition * of pfn swap entry. */ static inline unsigned long swp_offset_pfn(swp_entry_t entry) { VM_BUG_ON(!is_pfn_swap_entry(entry)); return swp_offset(entry) & SWP_PFN_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_READ, offset); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline bool is_device_exclusive_entry(swp_entry_t entry) { return false; } static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_readable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ); } static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); } static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); } /* * Returns whether the host has large enough swap offset field to support * carrying over pgtable A/D bits for page migrations. The result is * pretty much arch specific. */ static inline bool migration_entry_supports_ad(void) { #ifdef CONFIG_SWAP return swap_migration_ad_supported; #else /* CONFIG_SWAP */ return false; #endif /* CONFIG_SWAP */ } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_YOUNG); return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_YOUNG; /* Keep the old behavior of aging page after migration */ return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_entry(swp_type(entry), swp_offset(entry) | SWP_MIG_DIRTY); return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { if (migration_entry_supports_ad()) return swp_offset(entry) & SWP_MIG_DIRTY; /* Keep the old behavior of clean page after migration */ return false; } extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } static inline int is_readable_migration_entry(swp_entry_t entry) { return 0; } static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_young(swp_entry_t entry) { return false; } static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) { return entry; } static inline bool is_migration_entry_dirty(swp_entry_t entry) { return false; } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } #endif typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) /* * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. */ #define PTE_MARKER_POISONED BIT(1) #define PTE_MARKER_MASK (BIT(2) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { return swp_entry(SWP_PTE_MARKER, marker); } static inline bool is_pte_marker_entry(swp_entry_t entry) { return swp_type(entry) == SWP_PTE_MARKER; } static inline pte_marker pte_marker_get(swp_entry_t entry) { return swp_offset(entry) & PTE_MARKER_MASK; } static inline bool is_pte_marker(pte_t pte) { return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); } static inline pte_t make_pte_marker(pte_marker marker) { return swp_entry_to_pte(make_pte_marker_entry(marker)); } static inline swp_entry_t make_poisoned_swp_entry(void) { return make_pte_marker_entry(PTE_MARKER_POISONED); } static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); } /* * This is a special version to check pte_none() just to cover the case when * the pte is a pte marker. It existed because in many cases the pte marker * should be seen as a none pte; it's just that we have stored some information * onto the none pte so it becomes not-none any more. * * It should be used when the pte is file-backed, ram-based and backing * userspace pages, like shmem. It is not needed upon pgtables that do not * support pte markers at all. For example, it's not needed on anonymous * memory, kernel-only memory (including when the system is during-boot), * non-ram based generic file-system. It's fine to be used even there, but the * extra pte marker check will be pure overhead. */ static inline int pte_none_mostly(pte_t pte) { return pte_none(pte) || is_pte_marker(pte); } static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(is_migration_entry(entry) && !PageLocked(p)); return p; } static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) { struct folio *folio = pfn_folio(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the * corresponding folio is locked */ BUG_ON(is_migration_entry(entry) && !folio_test_locked(folio)); return folio; } /* * A pfn swap entry is a special type of swap entry that always has a pfn stored * in the swap offset. They can either be used to represent unaddressable device * memory, to restrict access to a page undergoing migration or to represent a * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { /* Make sure the swp offset can always store the needed fields */ BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 31 30 24 12 31 32 30 31 32 32 2 4 4 4 8 4 4 3 4 7 2 7 7 7 4 4 4 1 4 3 3 3 3 5 5 3 3 3 1 5 4 4 4 4 5 1 1 3 3 4 4 4 4 4 4 11 11 44 42 26 26 26 26 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/stat.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/compat.h> #include <linux/iversion.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include "internal.h" #include "mount.h" /** * generic_fillattr - Fill in the basic attributes from the inode struct * @idmap: idmap of the mount the inode was found from * @request_mask: statx request_mask * @inode: Inode to use as the source * @stat: Where to fill in the attributes * * Fill in the basic attributes in the kstat structure from data that's to be * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, struct inode *inode, struct kstat *stat) { vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; stat->uid = vfsuid_into_kuid(vfsuid); stat->gid = vfsgid_into_kgid(vfsgid); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode_get_atime(inode); stat->mtime = inode_get_mtime(inode); stat->ctime = inode_get_ctime(inode); stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { stat->result_mask |= STATX_CHANGE_COOKIE; stat->change_cookie = inode_query_iversion(inode); } } EXPORT_SYMBOL(generic_fillattr); /** * generic_fill_statx_attr - Fill in the statx attributes from the inode flags * @inode: Inode to use as the source * @stat: Where to fill in the attribute flags * * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the * inode that are published on i_flags and enforced by the VFS. */ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) { if (inode->i_flags & S_IMMUTABLE) stat->attributes |= STATX_ATTR_IMMUTABLE; if (inode->i_flags & S_APPEND) stat->attributes |= STATX_ATTR_APPEND; stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS; } EXPORT_SYMBOL(generic_fill_statx_attr); /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from * @stat: structure to return attributes in * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Get attributes without calling security_inode_getattr. * * Currently the only caller other than vfs_getattr is internal to the * filehandle lookup code, which uses only the inode number and returns no * attributes to any user. Any other code probably wants vfs_getattr. */ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct mnt_idmap *idmap; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); stat->result_mask |= STATX_BASIC_STATS; query_flags &= AT_STATX_SYNC_TYPE; /* allow the fs to override these if it really wants to */ /* SB_NOATIME means filesystem supplies dummy atime value */ if (inode->i_sb->s_flags & SB_NOATIME) stat->result_mask &= ~STATX_ATIME; /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. */ if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | STATX_ATTR_DAX); idmap = mnt_idmap(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(idmap, path, stat, request_mask, query_flags | AT_GETATTR_NOSEC); generic_fillattr(idmap, request_mask, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); /* * vfs_getattr - Get the enhanced basic attributes of a file * @path: The file of interest * @stat: Where to return the statistics * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Ask the filesystem for a file's attributes. The caller must indicate in * request_mask and query_flags to indicate what they want. * * If the file is remote, the filesystem can be forced to update the attributes * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can * suppress the update by passing AT_STATX_DONT_SYNC. * * Bits must have been set in request_mask to indicate which attributes the * caller wants retrieving. Any such attribute not requested may be returned * anyway, but the value may be approximate, and, if remote, may not have been * synchronised with the server. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { int retval; if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC)) return -EPERM; retval = security_inode_getattr(path); if (retval) return retval; return vfs_getattr_nosec(path, stat, request_mask, query_flags); } EXPORT_SYMBOL(vfs_getattr); /** * vfs_fstat - Get the basic attributes by file descriptor * @fd: The file descriptor referring to the file of interest * @stat: The result structure to fill in. * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a file descriptor to determine the file location. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_fstat(int fd, struct kstat *stat) { struct fd f; int error; f = fdget_raw(fd); if (!f.file) return -EBADF; error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0); fdput(f); return error; } int getname_statx_lookup_flags(int flags) { int lookup_flags = 0; if (!(flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (!(flags & AT_NO_AUTOMOUNT)) lookup_flags |= LOOKUP_AUTOMOUNT; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; return lookup_flags; } /** * vfs_statx - Get basic and extra attributes by filename * @dfd: A file descriptor representing the base dir for a relative filename * @filename: The name of the file of interest * @flags: Flags to control the query * @stat: The result structure to fill in. * @request_mask: STATX_xxx flags indicating what the caller wants * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a filename and base directory to determine the file location. * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ static int vfs_statx(int dfd, struct filename *filename, int flags, struct kstat *stat, u32 request_mask) { struct path path; unsigned int lookup_flags = getname_statx_lookup_flags(flags); int error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH | AT_STATX_SYNC_TYPE)) return -EINVAL; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = vfs_getattr(&path, stat, request_mask, flags); if (request_mask & STATX_MNT_ID_UNIQUE) { stat->mnt_id = real_mount(path.mnt)->mnt_id_unique; stat->result_mask |= STATX_MNT_ID_UNIQUE; } else { stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; } if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; /* Handle STATX_DIOALIGN for block devices. */ if (request_mask & STATX_DIOALIGN) { struct inode *inode = d_backing_inode(path.dentry); if (S_ISBLK(inode->i_mode)) bdev_statx_dioalign(inode, stat); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { int ret; int statx_flags = flags | AT_NO_AUTOMOUNT; struct filename *name; /* * Work around glibc turning fstat() into fstatat(AT_EMPTY_PATH) * * If AT_EMPTY_PATH is set, we expect the common case to be that * empty path, and avoid doing all the extra pathname work. */ if (dfd >= 0 && flags == AT_EMPTY_PATH) { char c; ret = get_user(c, filename); if (unlikely(ret)) return ret; if (likely(!c)) return vfs_fstat(dfd, stat); } name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL); ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS); putname(name); return ret; } #ifdef __ARCH_WANT_OLD_STAT /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf) { static int warncount = 5; struct __old_kernel_stat tmp; if (warncount > 0) { warncount--; printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n", current->comm); } else if (warncount < 0) { /* it's laughable, but... */ warncount = 0; } memset(&tmp, 0, sizeof(struct __old_kernel_stat)); tmp.st_dev = old_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(lstat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_old_stat(&stat, statbuf); return error; } #endif /* __ARCH_WANT_OLD_STAT */ #ifdef __ARCH_WANT_NEW_STAT #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif INIT_STRUCT_STAT_PADDING(tmp); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; #ifdef STAT_HAVE_NSEC tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; #endif tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(newstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT) SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, struct stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat(&stat, statbuf); } #endif SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat(&stat, statbuf); return error; } #endif static int do_readlinkat(int dfd, const char __user *pathname, char __user *buf, int bufsiz) { struct path path; int error; int empty = 0; unsigned int lookup_flags = LOOKUP_EMPTY; if (bufsiz <= 0) return -EINVAL; retry: error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty); if (!error) { struct inode *inode = d_backing_inode(path.dentry); error = empty ? -ENOENT : -EINVAL; /* * AFS mountpoints allow readlink(2) but are not symlinks */ if (d_is_symlink(path.dentry) || inode->i_op->readlink) { error = security_inode_readlink(path.dentry); if (!error) { touch_atime(&path); error = vfs_readlink(path.dentry, buf, bufsiz); } } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, char __user *, buf, int, bufsiz) { return do_readlinkat(dfd, pathname, buf, bufsiz); } SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, int, bufsiz) { return do_readlinkat(AT_FDCWD, path, buf, bufsiz); } /* ---------- LFS-64 ----------- */ #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) #ifndef INIT_STRUCT_STAT64_PADDING # define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) #endif static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else tmp.st_dev = huge_encode_dev(stat->dev); tmp.st_rdev = huge_encode_dev(stat->rdev); #endif tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; #ifdef STAT64_HAS_BROKEN_ST_INO tmp.__st_ino = stat->ino; #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_size = stat->size; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(lstat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_lstat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat64(&stat, statbuf); } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ static noinline_for_stack int cp_statx(const struct kstat *stat, struct statx __user *buffer) { struct statx tmp; memset(&tmp, 0, sizeof(tmp)); /* STATX_CHANGE_COOKIE is kernel-only for now */ tmp.stx_mask = stat->result_mask & ~STATX_CHANGE_COOKIE; tmp.stx_blksize = stat->blksize; /* STATX_ATTR_CHANGE_MONOTONIC is kernel-only for now */ tmp.stx_attributes = stat->attributes & ~STATX_ATTR_CHANGE_MONOTONIC; tmp.stx_nlink = stat->nlink; tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.stx_mode = stat->mode; tmp.stx_ino = stat->ino; tmp.stx_size = stat->size; tmp.stx_blocks = stat->blocks; tmp.stx_attributes_mask = stat->attributes_mask; tmp.stx_atime.tv_sec = stat->atime.tv_sec; tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; tmp.stx_btime.tv_sec = stat->btime.tv_sec; tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; tmp.stx_rdev_major = MAJOR(stat->rdev); tmp.stx_rdev_minor = MINOR(stat->rdev); tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_subvol = stat->subvol; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer) { struct kstat stat; int error; if (mask & STATX__RESERVED) return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; /* STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests * from userland. */ mask &= ~STATX_CHANGE_COOKIE; error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; return cp_statx(&stat, buffer); } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. * @filename: File to stat or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * * Note that fstat() can be emulated by setting dfd to the fd of interest, * supplying "" as the filename and setting AT_EMPTY_PATH in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, unsigned int, mask, struct statx __user *, buffer) { int ret; struct filename *name; name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL); ret = do_statx(dfd, name, flags, mask, buffer); putname(name); return ret; } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT) static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } #ifndef __ARCH_WANT_STAT64 COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, const char __user *, filename, struct compat_stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_compat_stat(&stat, statbuf); } #endif COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_compat_stat(&stat, statbuf); return error; } #endif /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ void __inode_add_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks += bytes >> 9; bytes &= 511; inode->i_bytes += bytes; if (inode->i_bytes >= 512) { inode->i_blocks++; inode->i_bytes -= 512; } } EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_add_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_add_bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks -= bytes >> 9; bytes &= 511; if (inode->i_bytes < bytes) { inode->i_blocks--; inode->i_bytes += 512; } inode->i_bytes -= bytes; } EXPORT_SYMBOL(__inode_sub_bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_sub_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_sub_bytes); loff_t inode_get_bytes(struct inode *inode) { loff_t ret; spin_lock(&inode->i_lock); ret = __inode_get_bytes(inode); spin_unlock(&inode->i_lock); return ret; } EXPORT_SYMBOL(inode_get_bytes); void inode_set_bytes(struct inode *inode, loff_t bytes) { /* Caller is here responsible for sufficient locking * (ie. inode->i_lock) */ inode->i_blocks = bytes >> 9; inode->i_bytes = bytes & 511; } EXPORT_SYMBOL(inode_set_bytes); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* -*- linux-c -*- * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: Mar 22 2001: Martin Bokaemper <mbokaemper@unispherenetworks.com> * - reset skb->pkt_type on incoming packets when MAC was changed * - see that changed MAC is saddr for outgoing packets * Oct 20, 2001: Ard van Breeman: * - Fix MC-list, finally. * - Flush MC-list on VLAN destroy. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/net_tstamp.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/phy.h> #include <net/arp.h> #include <net/macsec.h> #include "vlan.h" #include "vlanproc.h" #include <linux/if_vlan.h> #include <linux/netpoll.h> /* * Create the VLAN header for an arbitrary protocol layer * * saddr=NULL means use device source address * daddr=NULL means leave destination address (eg unresolved arp) * * This is called when the SKB is moving down the stack towards the * physical devices. */ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_hdr *vhdr; unsigned int vhdrlen = 0; u16 vlan_tci = 0; int rc; if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) { vhdr = skb_push(skb, VLAN_HLEN); vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); vhdr->h_vlan_TCI = htons(vlan_tci); /* * Set the protocol type. For a packet of type ETH_P_802_3/2 we * put the length in here instead. */ if (type != ETH_P_802_3 && type != ETH_P_802_2) vhdr->h_vlan_encapsulated_proto = htons(type); else vhdr->h_vlan_encapsulated_proto = htons(len); skb->protocol = vlan->vlan_proto; type = ntohs(vlan->vlan_proto); vhdrlen = VLAN_HLEN; } /* Before delegating work to the lower layer, enter our MAC-address */ if (saddr == NULL) saddr = dev->dev_addr; /* Now make the underlying real hard header */ dev = vlan->real_dev; rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen); if (rc > 0) rc += vhdrlen; return rc; } static inline netdev_tx_t vlan_netpoll_send_skb(struct vlan_dev_priv *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); unsigned int len; int ret; /* Handle non-VLAN frames if they are sent to us, for example by DHCP. * * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ if (vlan->flags & VLAN_FLAG_REORDER_HDR || veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci); } skb->dev = vlan->real_dev; len = skb->len; if (unlikely(netpoll_tx_running(dev))) return vlan_netpoll_send_skb(vlan, skb); ret = dev_queue_xmit(skb); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *stats; stats = this_cpu_ptr(vlan->vlan_pcpu_stats); u64_stats_update_begin(&stats->syncp); u64_stats_inc(&stats->tx_packets); u64_stats_add(&stats->tx_bytes, len); u64_stats_update_end(&stats->syncp); } else { this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped); } return ret; } static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; unsigned int max_mtu = real_dev->mtu; if (netif_reduces_vlan_mtu(real_dev)) max_mtu -= VLAN_HLEN; if (max_mtu < new_mtu) return -ERANGE; WRITE_ONCE(dev->mtu, new_mtu); return 0; } void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio) vlan->nr_ingress_mappings--; else if (!vlan->ingress_priority_map[vlan_prio & 0x7] && skb_prio) vlan->nr_ingress_mappings++; vlan->ingress_priority_map[vlan_prio & 0x7] = skb_prio; } int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct vlan_priority_tci_mapping *mp = NULL; struct vlan_priority_tci_mapping *np; u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* See if a priority mapping exists.. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; while (mp) { if (mp->priority == skb_prio) { if (mp->vlan_qos && !vlan_qos) vlan->nr_egress_mappings--; else if (!mp->vlan_qos && vlan_qos) vlan->nr_egress_mappings++; mp->vlan_qos = vlan_qos; return 0; } mp = mp->next; } /* Create a new mapping then. */ mp = vlan->egress_priority_map[skb_prio & 0xF]; np = kmalloc(sizeof(struct vlan_priority_tci_mapping), GFP_KERNEL); if (!np) return -ENOBUFS; np->next = mp; np->priority = skb_prio; np->vlan_qos = vlan_qos; /* Before inserting this element in hash table, make sure all its fields * are committed to memory. * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask() */ smp_wmb(); vlan->egress_priority_map[skb_prio & 0xF] = np; if (vlan_qos) vlan->nr_egress_mappings++; return 0; } /* Flags are defined in the vlan_flags enum in * include/uapi/linux/if_vlan.h file. */ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); u32 old_flags = vlan->flags; if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP | VLAN_FLAG_BRIDGE_BINDING)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_GVRP) { if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); else vlan_gvrp_request_leave(dev); } if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_MVRP) { if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_join(dev); else vlan_mvrp_request_leave(dev); } return 0; } void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size) { strscpy_pad(result, vlan_dev_priv(dev)->real_dev->name, size); } bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev) { if (dev->addr_assign_type != NET_ADDR_STOLEN) return false; eth_hw_addr_set(dev, real_dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return true; } static int vlan_dev_open(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; int err; if (!(real_dev->flags & IFF_UP) && !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) && !vlan_dev_inherit_address(dev, real_dev)) { err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) goto out; } if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(real_dev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(real_dev, 1); if (err < 0) goto clear_allmulti; } ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_join(dev); if (netif_carrier_ok(real_dev) && !(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_carrier_on(dev); return 0; clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); del_unicast: if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); out: netif_carrier_off(dev); return err; } static int vlan_dev_stop(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, -1); if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_carrier_off(dev); return 0; } static int vlan_dev_set_mac_address(struct net_device *dev, void *p) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; struct sockaddr *addr = p; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (!(dev->flags & IFF_UP)) goto out; if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) { err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; } if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); out: eth_hw_addr_set(dev, addr->sa_data); return 0; } static int vlan_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; return generic_hwtstamp_get_lower(real_dev, cfg); } static int vlan_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; if (!net_eq(dev_net(dev), dev_net(real_dev))) return -EOPNOTSUPP; return generic_hwtstamp_set_lower(real_dev, cfg, extack); } static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; struct ifreq ifrr; int err = -EOPNOTSUPP; strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); ifrr.ifr_ifru = ifr->ifr_ifru; switch (cmd) { case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); break; } if (!err) ifr->ifr_ifru = ifrr.ifr_ifru; return err; } static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int err = 0; if (netif_device_present(real_dev) && ops->ndo_neigh_setup) err = ops->ndo_neigh_setup(real_dev, pa); return err; } #if IS_ENABLED(CONFIG_FCOE) static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = 0; if (ops->ndo_fcoe_ddp_setup) rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc); return rc; } static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int len = 0; if (ops->ndo_fcoe_ddp_done) len = ops->ndo_fcoe_ddp_done(real_dev, xid); return len; } static int vlan_dev_fcoe_enable(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_enable) rc = ops->ndo_fcoe_enable(real_dev); return rc; } static int vlan_dev_fcoe_disable(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_disable) rc = ops->ndo_fcoe_disable(real_dev); return rc; } static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = 0; if (ops->ndo_fcoe_ddp_target) rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc); return rc; } #endif #ifdef NETDEV_FCOE_WWNN static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; int rc = -EINVAL; if (ops->ndo_fcoe_get_wwn) rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); return rc; } #endif static void vlan_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } } static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } static __be16 vlan_parse_protocol(const struct sk_buff *skb) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); return __vlan_get_protocol(skb, veth->h_vlan_proto, NULL); } static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, .parse_protocol = vlan_parse_protocol, }; static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; if (saddr == NULL) saddr = dev->dev_addr; return dev_hard_header(skb, real_dev, type, daddr, saddr, len); } static const struct header_ops vlan_passthru_header_ops = { .create = vlan_passthru_hard_header, .parse = eth_header_parse, .parse_protocol = vlan_parse_protocol, }; static const struct device_type vlan_type = { .name = "vlan", }; static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; netif_carrier_off(dev); /* IFF_BROADCAST|IFF_MULTICAST; ??? */ dev->flags = real_dev->flags & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_MASTER | IFF_SLAVE); dev->state = (real_dev->state & ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); if (vlan->flags & VLAN_FLAG_BRIDGE_BINDING) dev->state |= (1 << __LINK_STATE_NOCARRIER); dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | NETIF_F_ALL_FCOE; if (real_dev->vlan_features & NETIF_F_HW_MACSEC) dev->hw_features |= NETIF_F_HW_MACSEC; dev->features |= dev->hw_features | NETIF_F_LLTX; netif_inherit_tso_max(dev, real_dev); if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; dev->hw_enc_features = vlan_tnl_features(real_dev); dev->mpls_features = real_dev->mpls_features; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; if (is_zero_ether_addr(dev->dev_addr)) { eth_hw_addr_set(dev, real_dev->dev_addr); dev->addr_assign_type = NET_ADDR_STOLEN; } if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); #if IS_ENABLED(CONFIG_FCOE) dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid; #endif dev->needed_headroom = real_dev->needed_headroom; if (vlan_hw_offload_capable(real_dev->features, vlan->vlan_proto)) { dev->header_ops = &vlan_passthru_header_ops; dev->hard_header_len = real_dev->hard_header_len; } else { dev->header_ops = &vlan_header_ops; dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN; } dev->netdev_ops = &vlan_netdev_ops; SET_NETDEV_DEVTYPE(dev, &vlan_type); netdev_lockdep_set_classes(dev); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) return -ENOMEM; /* Get vlan's reference to real_dev */ netdev_hold(real_dev, &vlan->dev_tracker, GFP_KERNEL); return 0; } /* Note: this function might be called multiple times for the same device. */ void vlan_dev_free_egress_priority(const struct net_device *dev) { struct vlan_priority_tci_mapping *pm; struct vlan_dev_priv *vlan = vlan_dev_priv(dev); int i; for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) { while ((pm = vlan->egress_priority_map[i]) != NULL) { vlan->egress_priority_map[i] = pm->next; kfree(pm); } } } static void vlan_dev_uninit(struct net_device *dev) { vlan_dev_free_egress_priority(dev); } static netdev_features_t vlan_dev_fix_features(struct net_device *dev, netdev_features_t features) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; netdev_features_t old_features = features; netdev_features_t lower_features; lower_features = netdev_intersect_features((real_dev->vlan_features | NETIF_F_RXCSUM), real_dev->features); /* Add HW_CSUM setting to preserve user ability to control * checksum offload on the vlan device. */ if (lower_features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) lower_features |= NETIF_F_HW_CSUM; features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE); features |= NETIF_F_LLTX; return features; } static int vlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); return __ethtool_get_link_ksettings(vlan->real_dev, cmd); } static void vlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, vlan_fullname, sizeof(info->driver)); strscpy(info->version, vlan_version, sizeof(info->version)); strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static int vlan_ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); return ethtool_get_ts_info_by_layer(vlan->real_dev, info); } static void vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct vlan_pcpu_stats *p; u32 rx_errors = 0, tx_dropped = 0; int i; for_each_possible_cpu(i) { u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes; unsigned int start; p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rxpackets = u64_stats_read(&p->rx_packets); rxbytes = u64_stats_read(&p->rx_bytes); rxmulticast = u64_stats_read(&p->rx_multicast); txpackets = u64_stats_read(&p->tx_packets); txbytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; stats->multicast += rxmulticast; stats->tx_packets += txpackets; stats->tx_bytes += txbytes; /* rx_errors & tx_dropped are u32 */ rx_errors += READ_ONCE(p->rx_errors); tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->tx_dropped = tx_dropped; } #ifdef CONFIG_NET_POLL_CONTROLLER static void vlan_dev_poll_controller(struct net_device *dev) { return; } static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void vlan_dev_netpoll_cleanup(struct net_device *dev) { struct vlan_dev_priv *vlan= vlan_dev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int vlan_dev_get_iflink(const struct net_device *dev) { const struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; return READ_ONCE(real_dev->ifindex); } static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct vlan_dev_priv *vlan = vlan_dev_priv(ctx->dev); path->type = DEV_PATH_VLAN; path->encap.id = vlan->vlan_id; path->encap.proto = vlan->vlan_proto; path->dev = ctx->dev; ctx->dev = vlan->real_dev; if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan)) return -ENOSPC; ctx->vlan[ctx->num_vlans].id = vlan->vlan_id; ctx->vlan[ctx->num_vlans].proto = vlan->vlan_proto; ctx->num_vlans++; return 0; } #if IS_ENABLED(CONFIG_MACSEC) static const struct macsec_ops *vlan_get_macsec_ops(const struct macsec_context *ctx) { return vlan_dev_priv(ctx->netdev)->real_dev->macsec_ops; } static int vlan_macsec_offload(int (* const func)(struct macsec_context *), struct macsec_context *ctx) { if (unlikely(!func)) return 0; return (*func)(ctx); } static int vlan_macsec_dev_open(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_dev_open, ctx); } static int vlan_macsec_dev_stop(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_dev_stop, ctx); } static int vlan_macsec_add_secy(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_add_secy, ctx); } static int vlan_macsec_upd_secy(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_upd_secy, ctx); } static int vlan_macsec_del_secy(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_del_secy, ctx); } static int vlan_macsec_add_rxsc(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_add_rxsc, ctx); } static int vlan_macsec_upd_rxsc(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_upd_rxsc, ctx); } static int vlan_macsec_del_rxsc(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_del_rxsc, ctx); } static int vlan_macsec_add_rxsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_add_rxsa, ctx); } static int vlan_macsec_upd_rxsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_upd_rxsa, ctx); } static int vlan_macsec_del_rxsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_del_rxsa, ctx); } static int vlan_macsec_add_txsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_add_txsa, ctx); } static int vlan_macsec_upd_txsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_upd_txsa, ctx); } static int vlan_macsec_del_txsa(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_del_txsa, ctx); } static int vlan_macsec_get_dev_stats(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_get_dev_stats, ctx); } static int vlan_macsec_get_tx_sc_stats(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_get_tx_sc_stats, ctx); } static int vlan_macsec_get_tx_sa_stats(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_get_tx_sa_stats, ctx); } static int vlan_macsec_get_rx_sc_stats(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_get_rx_sc_stats, ctx); } static int vlan_macsec_get_rx_sa_stats(struct macsec_context *ctx) { const struct macsec_ops *ops = vlan_get_macsec_ops(ctx); if (!ops) return -EOPNOTSUPP; return vlan_macsec_offload(ops->mdo_get_rx_sa_stats, ctx); } static const struct macsec_ops macsec_offload_ops = { /* Device wide */ .mdo_dev_open = vlan_macsec_dev_open, .mdo_dev_stop = vlan_macsec_dev_stop, /* SecY */ .mdo_add_secy = vlan_macsec_add_secy, .mdo_upd_secy = vlan_macsec_upd_secy, .mdo_del_secy = vlan_macsec_del_secy, /* Security channels */ .mdo_add_rxsc = vlan_macsec_add_rxsc, .mdo_upd_rxsc = vlan_macsec_upd_rxsc, .mdo_del_rxsc = vlan_macsec_del_rxsc, /* Security associations */ .mdo_add_rxsa = vlan_macsec_add_rxsa, .mdo_upd_rxsa = vlan_macsec_upd_rxsa, .mdo_del_rxsa = vlan_macsec_del_rxsa, .mdo_add_txsa = vlan_macsec_add_txsa, .mdo_upd_txsa = vlan_macsec_upd_txsa, .mdo_del_txsa = vlan_macsec_del_txsa, /* Statistics */ .mdo_get_dev_stats = vlan_macsec_get_dev_stats, .mdo_get_tx_sc_stats = vlan_macsec_get_tx_sc_stats, .mdo_get_tx_sa_stats = vlan_macsec_get_tx_sa_stats, .mdo_get_rx_sc_stats = vlan_macsec_get_rx_sc_stats, .mdo_get_rx_sa_stats = vlan_macsec_get_rx_sa_stats, }; #endif static const struct ethtool_ops vlan_ethtool_ops = { .get_link_ksettings = vlan_ethtool_get_link_ksettings, .get_drvinfo = vlan_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_ts_info = vlan_ethtool_get_ts_info, }; static const struct net_device_ops vlan_netdev_ops = { .ndo_change_mtu = vlan_dev_change_mtu, .ndo_init = vlan_dev_init, .ndo_uninit = vlan_dev_uninit, .ndo_open = vlan_dev_open, .ndo_stop = vlan_dev_stop, .ndo_start_xmit = vlan_dev_hard_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = vlan_dev_set_mac_address, .ndo_set_rx_mode = vlan_dev_set_rx_mode, .ndo_change_rx_flags = vlan_dev_change_rx_flags, .ndo_eth_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, .ndo_get_stats64 = vlan_dev_get_stats64, #if IS_ENABLED(CONFIG_FCOE) .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup, .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, .ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target, #endif #ifdef NETDEV_FCOE_WWNN .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, #endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = vlan_dev_poll_controller, .ndo_netpoll_setup = vlan_dev_netpoll_setup, .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, .ndo_get_iflink = vlan_dev_get_iflink, .ndo_fill_forward_path = vlan_dev_fill_forward_path, .ndo_hwtstamp_get = vlan_hwtstamp_get, .ndo_hwtstamp_set = vlan_hwtstamp_set, }; static void vlan_dev_free(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); free_percpu(vlan->vlan_pcpu_stats); vlan->vlan_pcpu_stats = NULL; /* Get rid of the vlan's reference to real_dev */ netdev_put(vlan->real_dev, &vlan->dev_tracker); } void vlan_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags |= IFF_802_1Q_VLAN | IFF_NO_QUEUE; dev->priv_flags |= IFF_UNICAST_FLT; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->netdev_ops = &vlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = vlan_dev_free; dev->ethtool_ops = &vlan_ethtool_ops; #if IS_ENABLED(CONFIG_MACSEC) dev->macsec_ops = &macsec_offload_ops; #endif dev->min_mtu = 0; dev->max_mtu = ETH_MAX_MTU; eth_zero_addr(dev->broadcast); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __INCLUDE_LINUX_OOM_H #define __INCLUDE_LINUX_OOM_H #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> #include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; struct notifier_block; struct mem_cgroup; struct task_struct; enum oom_constraint { CONSTRAINT_NONE, CONSTRAINT_CPUSET, CONSTRAINT_MEMORY_POLICY, CONSTRAINT_MEMCG, }; /* * Details of the page allocation that triggered the oom killer that are used to * determine what should be killed. */ struct oom_control { /* Used to determine cpuset */ struct zonelist *zonelist; /* Used to determine mempolicy */ nodemask_t *nodemask; /* Memory cgroup in which oom is invoked, or NULL for global oom */ struct mem_cgroup *memcg; /* Used to determine cpuset and node locality requirement */ const gfp_t gfp_mask; /* * order == -1 means the oom kill is required by sysrq, otherwise only * for display purposes. */ const int order; /* Used by oom implementation, do not set */ unsigned long totalpages; struct task_struct *chosen; long chosen_points; /* Used to print the constraint info. */ enum oom_constraint constraint; }; extern struct mutex oom_lock; extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { current->signal->oom_flag_origin = true; } static inline void clear_current_oom_origin(void) { current->signal->oom_flag_origin = false; } static inline bool oom_task_origin(const struct task_struct *p) { return p->signal->oom_flag_origin; } static inline bool tsk_is_oom_victim(struct task_struct * tsk) { return tsk->signal->oom_mm; } /* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in * the mm. At that moment any !shared mapping would lose the content * and could cause a memory corruption (zero pages instead of the * original content). * * User should call this before establishing a page table entry for * a !shared mapping and under the proper page table lock. * * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. */ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) { if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) return VM_FAULT_SIGBUS; return 0; } long oom_badness(struct task_struct *p, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); extern void exit_oom_victim(void); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); #endif /* _INCLUDE_LINUX_OOM_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Serial core port device driver * * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/ * Author: Tony Lindgren <tony@atomide.com> */ #include <linux/device.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/pnp.h> #include <linux/property.h> #include <linux/serial_core.h> #include <linux/spinlock.h> #include "serial_base.h" #define SERIAL_PORT_AUTOSUSPEND_DELAY_MS 500 /* Only considers pending TX for now. Caller must take care of locking */ static int __serial_port_busy(struct uart_port *port) { return !uart_tx_stopped(port) && !kfifo_is_empty(&port->state->port.xmit_fifo); } static int serial_port_runtime_resume(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); struct uart_port *port; unsigned long flags; port = port_dev->port; if (port->flags & UPF_DEAD) goto out; /* Flush any pending TX for the port */ uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) goto unlock; if (__serial_port_busy(port)) port->ops->start_tx(port); unlock: uart_port_unlock_irqrestore(port, flags); out: pm_runtime_mark_last_busy(dev); return 0; } static int serial_port_runtime_suspend(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); struct uart_port *port = port_dev->port; unsigned long flags; bool busy; if (port->flags & UPF_DEAD) return 0; uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) { uart_port_unlock_irqrestore(port, flags); return 0; } busy = __serial_port_busy(port); if (busy) port->ops->start_tx(port); uart_port_unlock_irqrestore(port, flags); if (busy) pm_runtime_mark_last_busy(dev); return busy ? -EBUSY : 0; } static void serial_base_port_set_tx(struct uart_port *port, struct serial_port_device *port_dev, bool enabled) { unsigned long flags; uart_port_lock_irqsave(port, &flags); port_dev->tx_enabled = enabled; uart_port_unlock_irqrestore(port, flags); } void serial_base_port_startup(struct uart_port *port) { struct serial_port_device *port_dev = port->port_dev; serial_base_port_set_tx(port, port_dev, true); } void serial_base_port_shutdown(struct uart_port *port) { struct serial_port_device *port_dev = port->port_dev; serial_base_port_set_tx(port, port_dev, false); } static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm, serial_port_runtime_suspend, serial_port_runtime_resume, NULL); static int serial_port_probe(struct device *dev) { pm_runtime_enable(dev); pm_runtime_set_autosuspend_delay(dev, SERIAL_PORT_AUTOSUSPEND_DELAY_MS); pm_runtime_use_autosuspend(dev); return 0; } static int serial_port_remove(struct device *dev) { pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); return 0; } /* * Serial core port device init functions. Note that the physical serial * port device driver may not have completed probe at this point. */ int uart_add_one_port(struct uart_driver *drv, struct uart_port *port) { return serial_ctrl_register_port(drv, port); } EXPORT_SYMBOL(uart_add_one_port); void uart_remove_one_port(struct uart_driver *drv, struct uart_port *port) { serial_ctrl_unregister_port(drv, port); } EXPORT_SYMBOL(uart_remove_one_port); /** * __uart_read_properties - read firmware properties of the given UART port * @port: corresponding port * @use_defaults: apply defaults (when %true) or validate the values (when %false) * * The following device properties are supported: * - clock-frequency (optional) * - fifo-size (optional) * - no-loopback-test (optional) * - reg-shift (defaults may apply) * - reg-offset (value may be validated) * - reg-io-width (defaults may apply or value may be validated) * - interrupts (OF only) * - serial [alias ID] (OF only) * * If the port->dev is of struct platform_device type the interrupt line * will be retrieved via platform_get_irq() call against that device. * Otherwise it will be assigned by fwnode_irq_get() call. In both cases * the index 0 of the resource is used. * * The caller is responsible to initialize the following fields of the @port * ->dev (must be valid) * ->flags * ->mapbase * ->mapsize * ->regshift (if @use_defaults is false) * before calling this function. Alternatively the above mentioned fields * may be zeroed, in such case the only ones, that have associated properties * found, will be set to the respective values. * * If no error happened, the ->irq, ->mapbase, ->mapsize will be altered. * The ->iotype is always altered. * * When @use_defaults is true and the respective property is not found * the following values will be applied: * ->regshift = 0 * In this case IRQ must be provided, otherwise an error will be returned. * * When @use_defaults is false and the respective property is found * the following values will be validated: * - reg-io-width (->iotype) * - reg-offset (->mapsize against ->mapbase) * * Returns: 0 on success or negative errno on failure */ static int __uart_read_properties(struct uart_port *port, bool use_defaults) { struct device *dev = port->dev; u32 value; int ret; /* Read optional UART functional clock frequency */ device_property_read_u32(dev, "clock-frequency", &port->uartclk); /* Read the registers alignment (default: 8-bit) */ ret = device_property_read_u32(dev, "reg-shift", &value); if (ret) port->regshift = use_defaults ? 0 : port->regshift; else port->regshift = value; /* Read the registers I/O access type (default: MMIO 8-bit) */ ret = device_property_read_u32(dev, "reg-io-width", &value); if (ret) { port->iotype = UPIO_MEM; } else { switch (value) { case 1: port->iotype = UPIO_MEM; break; case 2: port->iotype = UPIO_MEM16; break; case 4: port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32; break; default: if (!use_defaults) { dev_err(dev, "Unsupported reg-io-width (%u)\n", value); return -EINVAL; } port->iotype = UPIO_UNKNOWN; break; } } /* Read the address mapping base offset (default: no offset) */ ret = device_property_read_u32(dev, "reg-offset", &value); if (ret) value = 0; /* Check for shifted address mapping overflow */ if (!use_defaults && port->mapsize < value) { dev_err(dev, "reg-offset %u exceeds region size %pa\n", value, &port->mapsize); return -EINVAL; } port->mapbase += value; port->mapsize -= value; /* Read optional FIFO size */ device_property_read_u32(dev, "fifo-size", &port->fifosize); if (device_property_read_bool(dev, "no-loopback-test")) port->flags |= UPF_SKIP_TEST; /* Get index of serial line, if found in DT aliases */ ret = of_alias_get_id(dev_of_node(dev), "serial"); if (ret >= 0) port->line = ret; if (dev_is_platform(dev)) ret = platform_get_irq(to_platform_device(dev), 0); else if (dev_is_pnp(dev)) { ret = pnp_irq(to_pnp_dev(dev), 0); if (ret < 0) ret = -ENXIO; } else ret = fwnode_irq_get(dev_fwnode(dev), 0); if (ret == -EPROBE_DEFER) return ret; if (ret > 0) port->irq = ret; else if (use_defaults) /* By default IRQ support is mandatory */ return ret; else port->irq = 0; port->flags |= UPF_SHARE_IRQ; return 0; } int uart_read_port_properties(struct uart_port *port) { return __uart_read_properties(port, true); } EXPORT_SYMBOL_GPL(uart_read_port_properties); int uart_read_and_validate_port_properties(struct uart_port *port) { return __uart_read_properties(port, false); } EXPORT_SYMBOL_GPL(uart_read_and_validate_port_properties); static struct device_driver serial_port_driver = { .name = "port", .suppress_bind_attrs = true, .probe = serial_port_probe, .remove = serial_port_remove, .pm = pm_ptr(&serial_port_pm), }; int serial_base_port_init(void) { return serial_base_driver_register(&serial_port_driver); } void serial_base_port_exit(void) { serial_base_driver_unregister(&serial_port_driver); } MODULE_AUTHOR("Tony Lindgren <tony@atomide.com>"); MODULE_DESCRIPTION("Serial controller port driver"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 2 2 2 1 1 1 1 1 1 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv4/xfrm4_protocol.c */ #include <linux/init.h> #include <linux/mutex.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <net/ip6_route.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; static DEFINE_MUTEX(xfrm6_protocol_mutex); static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_handlers; case IPPROTO_AH: return &ah6_handlers; case IPPROTO_COMP: return &ipcomp6_handlers; } return NULL; } #define for_each_protocol_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(protocol); if (!head) return 0; for_each_protocol_rcu(*proto_handlers(protocol), handler) if ((ret = handler->cb_handler(skb, err)) <= 0) return ret; return 0; } int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { int ret; struct xfrm6_protocol *handler; struct xfrm6_protocol __rcu **head = proto_handlers(nexthdr); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); if (!head) goto out; if (!skb_dst(skb)) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int flags = RT6_LOOKUP_F_HAS_SADDR; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = ip6h->daddr, .saddr = ip6h->saddr, .flowlabel = ip6_flowinfo(ip6h), .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; dst = ip6_route_input_lookup(dev_net(skb->dev), skb->dev, &fl6, skb, flags); if (dst->error) goto drop; skb_dst_set(skb, dst); } for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; out: icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm6_rcv_encap); static int xfrm6_esp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(esp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(esp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ah_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ah6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ah6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int xfrm6_ipcomp_rcv(struct sk_buff *skb) { int ret; struct xfrm6_protocol *handler; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; for_each_protocol_rcu(ipcomp6_handlers, handler) if ((ret = handler->handler(skb)) != -EINVAL) return ret; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); kfree_skb(skb); return 0; } static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_protocol *handler; for_each_protocol_rcu(ipcomp6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol esp6_protocol = { .handler = xfrm6_esp_rcv, .err_handler = xfrm6_esp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ah6_protocol = { .handler = xfrm6_ah_rcv, .err_handler = xfrm6_ah_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol ipcomp6_protocol = { .handler = xfrm6_ipcomp_rcv, .err_handler = xfrm6_ipcomp_err, .flags = INET6_PROTO_NOPOLICY, }; static const struct xfrm_input_afinfo xfrm6_input_afinfo = { .family = AF_INET6, .callback = xfrm6_rcv_cb, }; static inline const struct inet6_protocol *netproto(unsigned char protocol) { switch (protocol) { case IPPROTO_ESP: return &esp6_protocol; case IPPROTO_AH: return &ah6_protocol; case IPPROTO_COMP: return &ipcomp6_protocol; } return NULL; } int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; bool add_netproto = false; int ret = -EEXIST; int priority = handler->priority; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) add_netproto = true; for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t->priority < priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&xfrm6_protocol_mutex); if (add_netproto) { if (inet6_add_protocol(netproto(protocol), protocol)) { pr_err("%s: can't add protocol\n", __func__); ret = -EAGAIN; } } return ret; } EXPORT_SYMBOL(xfrm6_protocol_register); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol) { struct xfrm6_protocol __rcu **pprev; struct xfrm6_protocol *t; int ret = -ENOENT; if (!proto_handlers(protocol) || !netproto(protocol)) return -EINVAL; mutex_lock(&xfrm6_protocol_mutex); for (pprev = proto_handlers(protocol); (t = rcu_dereference_protected(*pprev, lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } if (!rcu_dereference_protected(*proto_handlers(protocol), lockdep_is_held(&xfrm6_protocol_mutex))) { if (inet6_del_protocol(netproto(protocol), protocol) < 0) { pr_err("%s: can't remove protocol\n", __func__); ret = -EAGAIN; } } mutex_unlock(&xfrm6_protocol_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_protocol_deregister); int __init xfrm6_protocol_init(void) { return xfrm_input_register_afinfo(&xfrm6_input_afinfo); } void xfrm6_protocol_fini(void) { xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); } |
| 1 2 3 4 5 6 7 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RECIPROCAL_DIV_H #define _LINUX_RECIPROCAL_DIV_H #include <linux/types.h> /* * This algorithm is based on the paper "Division by Invariant * Integers Using Multiplication" by Torbjörn Granlund and Peter * L. Montgomery. * * The assembler implementation from Agner Fog, which this code is * based on, can be found here: * http://www.agner.org/optimize/asmlib.zip * * This optimization for A/B is helpful if the divisor B is mostly * runtime invariant. The reciprocal of B is calculated in the * slow-path with reciprocal_value(). The fast-path can then just use * a much faster multiplication operation with a variable dividend A * to calculate the division A/B. */ struct reciprocal_value { u32 m; u8 sh1, sh2; }; /* "reciprocal_value" and "reciprocal_divide" together implement the basic * version of the algorithm described in Figure 4.1 of the paper. */ struct reciprocal_value reciprocal_value(u32 d); static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R) { u32 t = (u32)(((u64)a * R.m) >> 32); return (t + ((a - t) >> R.sh1)) >> R.sh2; } struct reciprocal_value_adv { u32 m; u8 sh, exp; bool is_wide_m; }; /* "reciprocal_value_adv" implements the advanced version of the algorithm * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The * exception case could be easily handled before calling "reciprocal_value_adv". * * The advanced version requires more complex calculation to get the reciprocal * multiplier and other control variables, but then could reduce the required * emulation operations. * * It makes no sense to use this advanced version for host divide emulation, * those extra complexities for calculating multiplier etc could completely * waive our saving on emulation operations. * * However, it makes sense to use it for JIT divide code generation for which * we are willing to trade performance of JITed code with that of host. As shown * by the following pseudo code, the required emulation operations could go down * from 6 (the basic version) to 3 or 4. * * To use the result of "reciprocal_value_adv", suppose we want to calculate * n/d, the pseudo C code will be: * * struct reciprocal_value_adv rvalue; * u8 pre_shift, exp; * * // handle exception case. * if (d >= (1U << 31)) { * result = n >= d; * return; * } * * rvalue = reciprocal_value_adv(d, 32) * exp = rvalue.exp; * if (rvalue.is_wide_m && !(d & 1)) { * // floor(log2(d & (2^32 -d))) * pre_shift = fls(d & -d) - 1; * rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift); * } else { * pre_shift = 0; * } * * // code generation starts. * if (imm == 1U << exp) { * result = n >> exp; * } else if (rvalue.is_wide_m) { * // pre_shift must be zero when reached here. * t = (n * rvalue.m) >> 32; * result = n - t; * result >>= 1; * result += t; * result >>= rvalue.sh - 1; * } else { * if (pre_shift) * result = n >> pre_shift; * result = ((u64)result * rvalue.m) >> 32; * result >>= rvalue.sh; * } */ struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec); #endif /* _LINUX_RECIPROCAL_DIV_H */ |
| 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include "io_uring.h" #include "napi.h" #ifdef CONFIG_NET_RX_BUSY_POLL /* Timeout for cleanout of stale entries. */ #define NAPI_TIMEOUT (60 * SEC_CONVERSION) struct io_napi_entry { unsigned int napi_id; struct list_head list; unsigned long timeout; struct hlist_node node; struct rcu_head rcu; }; static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list, unsigned int napi_id) { struct io_napi_entry *e; hlist_for_each_entry_rcu(e, hash_list, node) { if (e->napi_id != napi_id) continue; e->timeout = jiffies + NAPI_TIMEOUT; return e; } return NULL; } void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock) { struct hlist_head *hash_list; unsigned int napi_id; struct sock *sk; struct io_napi_entry *e; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected. */ if (napi_id < MIN_NAPI_ID) return; hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; rcu_read_lock(); e = io_napi_hash_find(hash_list, napi_id); if (e) { e->timeout = jiffies + NAPI_TIMEOUT; rcu_read_unlock(); return; } rcu_read_unlock(); e = kmalloc(sizeof(*e), GFP_NOWAIT); if (!e) return; e->napi_id = napi_id; e->timeout = jiffies + NAPI_TIMEOUT; spin_lock(&ctx->napi_lock); if (unlikely(io_napi_hash_find(hash_list, napi_id))) { spin_unlock(&ctx->napi_lock); kfree(e); return; } hlist_add_tail_rcu(&e->node, hash_list); list_add_tail(&e->list, &ctx->napi_list); spin_unlock(&ctx->napi_lock); } static void __io_napi_remove_stale(struct io_ring_ctx *ctx) { struct io_napi_entry *e; unsigned int i; spin_lock(&ctx->napi_lock); hash_for_each(ctx->napi_ht, i, e, node) { if (time_after(jiffies, e->timeout)) { list_del(&e->list); hash_del_rcu(&e->node); kfree_rcu(e, rcu); } } spin_unlock(&ctx->napi_lock); } static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale) { if (is_stale) __io_napi_remove_stale(ctx); } static inline bool io_napi_busy_loop_timeout(unsigned long start_time, unsigned long bp_usec) { if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } return true; } static bool io_napi_busy_loop_should_end(void *data, unsigned long start_time) { struct io_wait_queue *iowq = data; if (signal_pending(current)) return true; if (io_should_wake(iowq) || io_has_work(iowq->ctx)) return true; if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to)) return true; return false; } static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx, void *loop_end_arg) { struct io_napi_entry *e; bool (*loop_end)(void *, unsigned long) = NULL; bool is_stale = false; if (loop_end_arg) loop_end = io_napi_busy_loop_should_end; list_for_each_entry_rcu(e, &ctx->napi_list, list) { napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg, ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET); if (time_after(jiffies, e->timeout)) is_stale = true; } return is_stale; } static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { unsigned long start_time = busy_loop_current_time(); void *loop_end_arg = NULL; bool is_stale = false; /* Singular lists use a different napi loop end check function and are * only executed once. */ if (list_is_singular(&ctx->napi_list)) loop_end_arg = iowq; rcu_read_lock(); do { is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg); } while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg); rcu_read_unlock(); io_napi_remove_stale(ctx, is_stale); } /* * io_napi_init() - Init napi settings * @ctx: pointer to io-uring context structure * * Init napi settings in the io-uring context. */ void io_napi_init(struct io_ring_ctx *ctx) { INIT_LIST_HEAD(&ctx->napi_list); spin_lock_init(&ctx->napi_lock); ctx->napi_prefer_busy_poll = false; ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll); } /* * io_napi_free() - Deallocate napi * @ctx: pointer to io-uring context structure * * Free the napi list and the hash table in the io-uring context. */ void io_napi_free(struct io_ring_ctx *ctx) { struct io_napi_entry *e; LIST_HEAD(napi_list); unsigned int i; spin_lock(&ctx->napi_lock); hash_for_each(ctx->napi_ht, i, e, node) { hash_del_rcu(&e->node); kfree_rcu(e, rcu); } spin_unlock(&ctx->napi_lock); } /* * io_napi_register() - Register napi with io-uring * @ctx: pointer to io-uring context structure * @arg: pointer to io_uring_napi structure * * Register napi in the io-uring context. */ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { .busy_poll_to = ctx->napi_busy_poll_to, .prefer_busy_poll = ctx->napi_prefer_busy_poll }; struct io_uring_napi napi; if (copy_from_user(&napi, arg, sizeof(napi))) return -EFAULT; if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv) return -EINVAL; if (copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll); WRITE_ONCE(ctx->napi_enabled, true); return 0; } /* * io_napi_unregister() - Unregister napi with io-uring * @ctx: pointer to io-uring context structure * @arg: pointer to io_uring_napi structure * * Unregister napi. If arg has been specified copy the busy poll timeout and * prefer busy poll setting to the passed in structure. */ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) { const struct io_uring_napi curr = { .busy_poll_to = ctx->napi_busy_poll_to, .prefer_busy_poll = ctx->napi_prefer_busy_poll }; if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; WRITE_ONCE(ctx->napi_busy_poll_to, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); WRITE_ONCE(ctx->napi_enabled, false); return 0; } /* * __io_napi_adjust_timeout() - Add napi id to the busy poll list * @ctx: pointer to io-uring context structure * @iowq: pointer to io wait queue * @ts: pointer to timespec or NULL * * Adjust the busy loop timeout according to timespec and busy poll timeout. */ void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, struct timespec64 *ts) { unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to); if (ts) { struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to); if (timespec64_compare(ts, &poll_to_ts) > 0) { *ts = timespec64_sub(*ts, poll_to_ts); } else { u64 to = timespec64_to_ns(ts); do_div(to, 1000); ts->tv_sec = 0; ts->tv_nsec = 0; } } iowq->napi_busy_poll_to = poll_to; } /* * __io_napi_busy_loop() - execute busy poll loop * @ctx: pointer to io-uring context structure * @iowq: pointer to io wait queue * * Execute the busy poll loop and merge the spliced off list. */ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll); if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled) io_napi_blocking_busy_loop(ctx, iowq); } /* * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll * @ctx: pointer to io-uring context structure * * Splice of the napi list and execute the napi busy poll loop. */ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) { LIST_HEAD(napi_list); bool is_stale = false; if (!READ_ONCE(ctx->napi_busy_poll_to)) return 0; if (list_empty_careful(&ctx->napi_list)) return 0; rcu_read_lock(); is_stale = __io_napi_do_busy_loop(ctx, NULL); rcu_read_unlock(); io_napi_remove_stale(ctx, is_stale); return 1; } #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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CRC32C *@Article{castagnoli-crc, * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 * and 32 Parity Bits}}, * journal = IEEE Transactions on Communication, * year = {1993}, * volume = {41}, * number = {6}, * pages = {}, * month = {June}, *} * Used by the iSCSI driver, possibly others, and derived from * the iscsi-crc.c module of the linux-iscsi driver at * http://linux-iscsi.sourceforge.net. * * Following the example of lib/crc32, this function is intended to be * flexible and useful for all users. Modules that currently have their * own crc32c, but hopefully may be able to use this one are: * net/sctp (please add all your doco to here if you change to * use this one!) * <endoflist> * * Copyright (c) 2004 Cisco Systems, Inc. */ #include <crypto/hash.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/crc32c.h> static struct crypto_shash *tfm; u32 crc32c(u32 crc, const void *address, unsigned int length) { SHASH_DESC_ON_STACK(shash, tfm); u32 ret, *ctx = (u32 *)shash_desc_ctx(shash); int err; shash->tfm = tfm; *ctx = crc; err = crypto_shash_update(shash, address, length); BUG_ON(err); ret = *ctx; barrier_data(ctx); return ret; } EXPORT_SYMBOL(crc32c); static int __init libcrc32c_mod_init(void) { tfm = crypto_alloc_shash("crc32c", 0, 0); return PTR_ERR_OR_ZERO(tfm); } static void __exit libcrc32c_mod_fini(void) { crypto_free_shash(tfm); } module_init(libcrc32c_mod_init); module_exit(libcrc32c_mod_fini); MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); MODULE_LICENSE("GPL"); MODULE_SOFTDEP("pre: crc32c"); |
| 1 1 1 1 1 1 2 2 1 1 1 1 1 1 49 49 3 3 3 15 15 11 11 6 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <linux/ethtool.h> #include "ipvlan.h" static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; unsigned int flags; int err; ASSERT_RTNL(); if (port->mode != nval) { list_for_each_entry(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { err = dev_change_flags(ipvlan->dev, flags | IFF_NOARP, extack); } else { err = dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, extack); } if (unlikely(err)) goto fail; } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_l3s_register(port); if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ ipvlan_l3s_unregister(port); } port->mode = nval; } return 0; fail: /* Undo the flags changes that have been done so far. */ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (port->mode == IPVLAN_MODE_L3 || port->mode == IPVLAN_MODE_L3S) dev_change_flags(ipvlan->dev, flags | IFF_NOARP, NULL); else dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, NULL); } return err; } static int ipvlan_port_create(struct net_device *dev) { struct ipvl_port *port; int err, idx; port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL); if (!port) return -ENOMEM; write_pnet(&port->pnet, dev_net(dev)); port->dev = dev; port->mode = IPVLAN_MODE_L3; INIT_LIST_HEAD(&port->ipvlans); for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); port->dev_id_start = 1; err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port); if (err) goto err; netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: kfree(port); return err; } static void ipvlan_port_destroy(struct net_device *dev) { struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { dev_put(skb->dev); kfree_skb(skb); } ida_destroy(&port->ida); kfree(port); } #define IPVLAN_ALWAYS_ON_OFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static int ipvlan_init(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; int err; dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; dev->features |= IPVLAN_ALWAYS_ON; dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; netdev_lockdep_set_classes(dev); ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; if (!netif_is_ipvlan_port(phy_dev)) { err = ipvlan_port_create(phy_dev); if (err < 0) { free_percpu(ipvlan->pcpu_stats); return err; } } port = ipvlan_port_get_rtnl(phy_dev); port->count += 1; return 0; } static void ipvlan_uninit(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; free_percpu(ipvlan->pcpu_stats); port = ipvlan_port_get_rtnl(phy_dev); port->count -= 1; if (!port->count) ipvlan_port_destroy(port->dev); } static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || ipvlan->port->mode == IPVLAN_MODE_L3S) dev->flags |= IFF_NOARP; else dev->flags &= ~IFF_NOARP; rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); return 0; } static int ipvlan_stop(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); rcu_read_unlock(); return 0; } static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); int skblen = skb->len; int ret; ret = ipvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct ipvl_pcpu_stats *pcptr; pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); u64_stats_inc(&pcptr->tx_pkts); u64_stats_add(&pcptr->tx_bytes, skblen); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->tx_drps); } return ret; } static netdev_features_t ipvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct ipvl_dev *ipvlan = netdev_priv(dev); features |= NETIF_F_ALL_FOR_ALL; features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); features = netdev_increment_features(ipvlan->phy_dev->features, features, features); features |= IPVLAN_ALWAYS_ON; features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; if (change & IFF_ALLMULTI) dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1); } static void ipvlan_set_multicast_mac_filter(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE); } else { struct netdev_hw_addr *ha; DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE); bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE); netdev_for_each_mc_addr(ha, dev) __set_bit(ipvlan_mac_hash(ha->addr), mc_filters); /* Turn-on broadcast bit irrespective of address family, * since broadcast is deferred to a work-queue, hence no * impact on fast-path processing. */ __set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters); bitmap_copy(ipvlan->mac_filters, mc_filters, IPVLAN_MAC_FILTER_SIZE); } dev_uc_sync(ipvlan->phy_dev, dev); dev_mc_sync(ipvlan->phy_dev, dev); } static void ipvlan_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (ipvlan->pcpu_stats) { struct ipvl_pcpu_stats *pcptr; u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes; u32 rx_errs = 0, tx_drps = 0; u32 strt; int idx; for_each_possible_cpu(idx) { pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); do { strt = u64_stats_fetch_begin(&pcptr->syncp); rx_pkts = u64_stats_read(&pcptr->rx_pkts); rx_bytes = u64_stats_read(&pcptr->rx_bytes); rx_mcast = u64_stats_read(&pcptr->rx_mcast); tx_pkts = u64_stats_read(&pcptr->tx_pkts); tx_bytes = u64_stats_read(&pcptr->tx_bytes); } while (u64_stats_fetch_retry(&pcptr->syncp, strt)); s->rx_packets += rx_pkts; s->rx_bytes += rx_bytes; s->multicast += rx_mcast; s->tx_packets += tx_pkts; s->tx_bytes += tx_bytes; /* u32 values are updated without syncp protection. */ rx_errs += READ_ONCE(pcptr->rx_errs); tx_drps += READ_ONCE(pcptr->tx_drps); } s->rx_errors = rx_errs; s->rx_dropped = rx_errs; s->tx_dropped = tx_drps; } s->tx_errors = DEV_STATS_READ(dev, tx_errors); } static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; return vlan_vid_add(phy_dev, proto, vid); } static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; vlan_vid_del(phy_dev, proto, vid); return 0; } static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { .ndo_init = ipvlan_init, .ndo_uninit = ipvlan_uninit, .ndo_open = ipvlan_open, .ndo_stop = ipvlan_stop, .ndo_start_xmit = ipvlan_start_xmit, .ndo_fix_features = ipvlan_fix_features, .ndo_change_rx_flags = ipvlan_change_rx_flags, .ndo_set_rx_mode = ipvlan_set_multicast_mac_filter, .ndo_get_stats64 = ipvlan_get_stats64, .ndo_vlan_rx_add_vid = ipvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ipvlan_vlan_rx_kill_vid, .ndo_get_iflink = ipvlan_get_iflink, }; static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; /* TODO Probably use a different field than dev_addr so that the * mac-address on the virtual device is portable and can be carried * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { .create = ipvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) { ipvlan->dev->mtu = dev->mtu; } static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ return dev->netdev_ops == &ipvlan_netdev_ops; } static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return __ethtool_get_link_ksettings(ipvlan->phy_dev, cmd); } static void ipvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver)); strscpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version)); } static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return ipvlan->msg_enable; } static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value) { struct ipvl_dev *ipvlan = netdev_priv(dev); ipvlan->msg_enable = value; } static const struct ethtool_ops ipvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = ipvlan_ethtool_get_link_ksettings, .get_drvinfo = ipvlan_ethtool_get_drvinfo, .get_msglevel = ipvlan_ethtool_get_msglevel, .set_msglevel = ipvlan_ethtool_set_msglevel, }; static int ipvlan_nl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; if (!data) return 0; if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode, extack); } if (!err && data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (flags & IPVLAN_F_PRIVATE) ipvlan_mark_private(port); else ipvlan_clear_private(port); if (flags & IPVLAN_F_VEPA) ipvlan_mark_vepa(port); else ipvlan_clear_vepa(port); } return err; } static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode >= IPVLAN_MODE_MAX) return -EINVAL; } if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); /* Only two bits are used at this moment. */ if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; /* Also both flags can't be active at the same time. */ if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } return 0; } static int ipvlan_nl_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int ret = -EINVAL; if (!port) goto err; ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) goto err; return 0; err: return ret; } int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port; struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; if (!tb[IFLA_LINK]) return -EINVAL; phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; if (netif_is_ipvlan(phy_dev)) { struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || phy_dev->flags & IFF_LOOPBACK) { netdev_err(phy_dev, "Master is either lo or non-ether device\n"); return -EINVAL; } if (netdev_is_rx_handler_busy(phy_dev)) { netdev_err(phy_dev, "Device is already in use.\n"); return -EBUSY; } } ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing * packets. */ eth_hw_addr_set(dev, phy_dev->dev_addr); dev->priv_flags |= IFF_NO_RX_HANDLER; err = register_netdevice(dev); if (err < 0) return err; /* ipvlan_init() would have created the port, if required */ port = ipvlan_port_get_rtnl(phy_dev); ipvlan->port = port; /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. */ if (port->dev_id_start == 0xFFFE) port->dev_id_start = 0x1; /* Since L2 address is shared among all IPvlan slaves including * master, use unique 16 bit dev-ids to differentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD, GFP_KERNEL); if (err < 0) err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1, GFP_KERNEL); if (err < 0) goto unregister_netdev; dev->dev_id = err; /* Increment id-base to the next slot for the future assignment */ port->dev_id_start = err + 1; err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) goto remove_ida; /* Flags are per port and latest update overrides. User has * to be consistent in setting it just like the mode attribute. */ if (data && data[IFLA_IPVLAN_FLAGS]) port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (data && data[IFLA_IPVLAN_MODE]) mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, mode, extack); if (err) goto unlink_netdev; list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; unlink_netdev: netdev_upper_dev_unlink(phy_dev, dev); remove_ida: ida_free(&port->ida, dev->dev_id); unregister_netdev: unregister_netdevice(dev); return err; } EXPORT_SYMBOL_GPL(ipvlan_link_new); void ipvlan_link_delete(struct net_device *dev, struct list_head *head) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; spin_lock_bh(&ipvlan->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } spin_unlock_bh(&ipvlan->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); } EXPORT_SYMBOL_GPL(ipvlan_link_delete); void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; dev->netdev_ops = &ipvlan_netdev_ops; dev->needs_free_netdev = true; dev->header_ops = &ipvlan_header_ops; dev->ethtool_ops = &ipvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct net *ipvlan_get_link_net(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return dev_net(ipvlan->phy_dev); } static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) { ops->get_size = ipvlan_nl_getsize; ops->policy = ipvlan_nl_policy; ops->validate = ipvlan_nl_validate; ops->fill_info = ipvlan_nl_fillinfo; ops->changelink = ipvlan_nl_changelink; ops->maxtype = IFLA_IPVLAN_MAX; return rtnl_link_register(ops); } EXPORT_SYMBOL_GPL(ipvlan_link_register); static int ipvlan_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 ipvl_dev *ipvlan, *next; struct ipvl_port *port; LIST_HEAD(lst_kill); int err; if (!netif_is_ipvlan_port(dev)) return NOTIFY_DONE; port = ipvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) netif_stacked_transfer_operstate(ipvlan->phy_dev, ipvlan->dev); break; case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) break; write_pnet(&port->pnet, newnet); if (port->mode == IPVLAN_MODE_L3S) ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev, &lst_kill); unregister_netdevice_many(&lst_kill); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_inherit_tso_max(ipvlan->dev, dev); netdev_update_features(ipvlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(ipvlan, &port->ipvlans, pnode) ipvlan_adjust_mtu(ipvlan, dev); break; case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { err = dev_pre_changeaddr_notify(ipvlan->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); } break; case NETDEV_CHANGEADDR: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { eth_hw_addr_set(ipvlan->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev); } break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } /* the caller must held the addrs lock */ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; addr->master = ipvlan; if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; #if IS_ENABLED(CONFIG_IPV6) } else { memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); addr->atype = IPVL_IPV6; #endif } list_add_tail_rcu(&addr->anode, &ipvlan->addrs); /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. */ if (netif_running(ipvlan->dev)) ipvlan_ht_addr_add(ipvlan, addr); return 0; } static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; spin_lock_bh(&ipvlan->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { spin_unlock_bh(&ipvlan->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); spin_unlock_bh(&ipvlan->addrs_lock); kfree_rcu(addr, rcu); } static bool ipvlan_is_valid_dev(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (!netif_is_ipvlan(dev)) return false; if (!ipvlan || !ipvlan->port) return false; return true; } #if IS_ENABLED(CONFIG_IPV6) static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { return ipvlan_del_addr(ipvlan, ip6_addr, true); } static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if6->idev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_add_addr6(ipvlan, &if6->addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ipvlan_del_addr6(ipvlan, &if6->addr); break; } return NOTIFY_OK; } static int ipvlan_addr6_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } #endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { return ipvlan_del_addr(ipvlan, ip4_addr, false); } static int ipvlan_addr4_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_ifaddr *if4 = (struct in_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if4->ifa_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); struct in_addr ip4_addr; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: ip4_addr.s_addr = if4->ifa_address; if (ipvlan_add_addr4(ipvlan, &ip4_addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ip4_addr.s_addr = if4->ifa_address; ipvlan_del_addr4(ipvlan, &ip4_addr); break; } return NOTIFY_OK; } static int ipvlan_addr4_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_event, }; static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_validator_event, }; static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; #if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; #endif static int __init ipvlan_init_module(void) { int err; ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { ipvlan_l3s_cleanup(); goto error; } return 0; error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif } module_init(ipvlan_init_module); module_exit(ipvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); |
| 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 1 3 1 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 2 3 3 2 2 3 3 1 1 1 1 1 1 3 3 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | /* FUSE: Filesystem in Userspace Copyright (C) 2001-2018 Miklos Szeredi <miklos@szeredi.hu> This program can be distributed under the terms of the GNU GPL. See the file COPYING. */ #include "fuse_i.h" #include <linux/iversion.h> #include <linux/posix_acl.h> #include <linux/pagemap.h> #include <linux/highmem.h> static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx) { struct fuse_conn *fc = get_fuse_conn(dir); struct fuse_inode *fi = get_fuse_inode(dir); if (!fc->do_readdirplus) return false; if (!fc->readdirplus_auto) return true; if (test_and_clear_bit(FUSE_I_ADVISE_RDPLUS, &fi->state)) return true; if (ctx->pos == 0) return true; return false; } static void fuse_add_dirent_to_cache(struct file *file, struct fuse_dirent *dirent, loff_t pos) { struct fuse_inode *fi = get_fuse_inode(file_inode(file)); size_t reclen = FUSE_DIRENT_SIZE(dirent); pgoff_t index; struct page *page; loff_t size; u64 version; unsigned int offset; void *addr; spin_lock(&fi->rdc.lock); /* * Is cache already completed? Or this entry does not go at the end of * cache? */ if (fi->rdc.cached || pos != fi->rdc.pos) { spin_unlock(&fi->rdc.lock); return; } version = fi->rdc.version; size = fi->rdc.size; offset = size & ~PAGE_MASK; index = size >> PAGE_SHIFT; /* Dirent doesn't fit in current page? Jump to next page. */ if (offset + reclen > PAGE_SIZE) { index++; offset = 0; } spin_unlock(&fi->rdc.lock); if (offset) { page = find_lock_page(file->f_mapping, index); } else { page = find_or_create_page(file->f_mapping, index, mapping_gfp_mask(file->f_mapping)); } if (!page) return; spin_lock(&fi->rdc.lock); /* Raced with another readdir */ if (fi->rdc.version != version || fi->rdc.size != size || WARN_ON(fi->rdc.pos != pos)) goto unlock; addr = kmap_local_page(page); if (!offset) { clear_page(addr); SetPageUptodate(page); } memcpy(addr + offset, dirent, reclen); kunmap_local(addr); fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen; fi->rdc.pos = dirent->off; unlock: spin_unlock(&fi->rdc.lock); unlock_page(page); put_page(page); } static void fuse_readdir_cache_end(struct file *file, loff_t pos) { struct fuse_inode *fi = get_fuse_inode(file_inode(file)); loff_t end; spin_lock(&fi->rdc.lock); /* does cache end position match current position? */ if (fi->rdc.pos != pos) { spin_unlock(&fi->rdc.lock); return; } fi->rdc.cached = true; end = ALIGN(fi->rdc.size, PAGE_SIZE); spin_unlock(&fi->rdc.lock); /* truncate unused tail of cache */ truncate_inode_pages(file->f_mapping, end); } static bool fuse_emit(struct file *file, struct dir_context *ctx, struct fuse_dirent *dirent) { struct fuse_file *ff = file->private_data; if (ff->open_flags & FOPEN_CACHE_DIR) fuse_add_dirent_to_cache(file, dirent, ctx->pos); return dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, dirent->type); } static int parse_dirfile(char *buf, size_t nbytes, struct file *file, struct dir_context *ctx) { while (nbytes >= FUSE_NAME_OFFSET) { struct fuse_dirent *dirent = (struct fuse_dirent *) buf; size_t reclen = FUSE_DIRENT_SIZE(dirent); if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX) return -EIO; if (reclen > nbytes) break; if (memchr(dirent->name, '/', dirent->namelen) != NULL) return -EIO; if (!fuse_emit(file, ctx, dirent)) break; buf += reclen; nbytes -= reclen; ctx->pos = dirent->off; } return 0; } static int fuse_direntplus_link(struct file *file, struct fuse_direntplus *direntplus, u64 attr_version) { struct fuse_entry_out *o = &direntplus->entry_out; struct fuse_dirent *dirent = &direntplus->dirent; struct dentry *parent = file->f_path.dentry; struct qstr name = QSTR_INIT(dirent->name, dirent->namelen); struct dentry *dentry; struct dentry *alias; struct inode *dir = d_inode(parent); struct fuse_conn *fc; struct inode *inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (!o->nodeid) { /* * Unlike in the case of fuse_lookup, zero nodeid does not mean * ENOENT. Instead, it only means the userspace filesystem did * not want to return attributes/handle for this entry. * * So do nothing. */ return 0; } if (name.name[0] == '.') { /* * We could potentially refresh the attributes of the directory * and its parent? */ if (name.len == 1) return 0; if (name.name[1] == '.' && name.len == 2) return 0; } if (invalid_nodeid(o->nodeid)) return -EIO; if (fuse_invalid_attr(&o->attr)) return -EIO; fc = get_fuse_conn(dir); name.hash = full_name_hash(parent, name.name, name.len); dentry = d_lookup(parent, &name); if (!dentry) { retry: dentry = d_alloc_parallel(parent, &name, &wq); if (IS_ERR(dentry)) return PTR_ERR(dentry); } if (!d_in_lookup(dentry)) { struct fuse_inode *fi; inode = d_inode(dentry); if (inode && get_node_id(inode) != o->nodeid) inode = NULL; if (!inode || fuse_stale_inode(inode, o->generation, &o->attr)) { if (inode) fuse_make_bad(inode); d_invalidate(dentry); dput(dentry); goto retry; } if (fuse_is_bad(inode)) { dput(dentry); return -EIO; } fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); forget_all_cached_acls(inode); fuse_change_attributes(inode, &o->attr, NULL, ATTR_TIMEOUT(o), attr_version); /* * The other branch comes via fuse_iget() * which bumps nlookup inside */ } else { inode = fuse_iget(dir->i_sb, o->nodeid, o->generation, &o->attr, ATTR_TIMEOUT(o), attr_version); if (!inode) inode = ERR_PTR(-ENOMEM); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { dput(dentry); dentry = alias; } if (IS_ERR(dentry)) { if (!IS_ERR(inode)) { struct fuse_inode *fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup--; spin_unlock(&fi->lock); } return PTR_ERR(dentry); } } if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); fuse_change_entry_timeout(dentry, o); dput(dentry); return 0; } static void fuse_force_forget(struct file *file, u64 nodeid) { struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_forget_in inarg; FUSE_ARGS(args); memset(&inarg, 0, sizeof(inarg)); inarg.nlookup = 1; args.opcode = FUSE_FORGET; args.nodeid = nodeid; args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.force = true; args.noreply = true; fuse_simple_request(fm, &args); /* ignore errors */ } static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, struct dir_context *ctx, u64 attr_version) { struct fuse_direntplus *direntplus; struct fuse_dirent *dirent; size_t reclen; int over = 0; int ret; while (nbytes >= FUSE_NAME_OFFSET_DIRENTPLUS) { direntplus = (struct fuse_direntplus *) buf; dirent = &direntplus->dirent; reclen = FUSE_DIRENTPLUS_SIZE(direntplus); if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX) return -EIO; if (reclen > nbytes) break; if (memchr(dirent->name, '/', dirent->namelen) != NULL) return -EIO; if (!over) { /* We fill entries into dstbuf only as much as it can hold. But we still continue iterating over remaining entries to link them. If not, we need to send a FORGET for each of those which we did not link. */ over = !fuse_emit(file, ctx, dirent); if (!over) ctx->pos = dirent->off; } buf += reclen; nbytes -= reclen; ret = fuse_direntplus_link(file, direntplus, attr_version); if (ret) fuse_force_forget(file, direntplus->entry_out.nodeid); } return 0; } static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx) { int plus; ssize_t res; struct page *page; struct inode *inode = file_inode(file); struct fuse_mount *fm = get_fuse_mount(inode); struct fuse_io_args ia = {}; struct fuse_args_pages *ap = &ia.ap; struct fuse_page_desc desc = { .length = PAGE_SIZE }; u64 attr_version = 0; bool locked; page = alloc_page(GFP_KERNEL); if (!page) return -ENOMEM; plus = fuse_use_readdirplus(inode, ctx); ap->args.out_pages = true; ap->num_pages = 1; ap->pages = &page; ap->descs = &desc; if (plus) { attr_version = fuse_get_attr_version(fm->fc); fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE, FUSE_READDIRPLUS); } else { fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE, FUSE_READDIR); } locked = fuse_lock_inode(inode); res = fuse_simple_request(fm, &ap->args); fuse_unlock_inode(inode, locked); if (res >= 0) { if (!res) { struct fuse_file *ff = file->private_data; if (ff->open_flags & FOPEN_CACHE_DIR) fuse_readdir_cache_end(file, ctx->pos); } else if (plus) { res = parse_dirplusfile(page_address(page), res, file, ctx, attr_version); } else { res = parse_dirfile(page_address(page), res, file, ctx); } } __free_page(page); fuse_invalidate_atime(inode); return res; } enum fuse_parse_result { FOUND_ERR = -1, FOUND_NONE = 0, FOUND_SOME, FOUND_ALL, }; static enum fuse_parse_result fuse_parse_cache(struct fuse_file *ff, void *addr, unsigned int size, struct dir_context *ctx) { unsigned int offset = ff->readdir.cache_off & ~PAGE_MASK; enum fuse_parse_result res = FOUND_NONE; WARN_ON(offset >= size); for (;;) { struct fuse_dirent *dirent = addr + offset; unsigned int nbytes = size - offset; size_t reclen; if (nbytes < FUSE_NAME_OFFSET || !dirent->namelen) break; reclen = FUSE_DIRENT_SIZE(dirent); /* derefs ->namelen */ if (WARN_ON(dirent->namelen > FUSE_NAME_MAX)) return FOUND_ERR; if (WARN_ON(reclen > nbytes)) return FOUND_ERR; if (WARN_ON(memchr(dirent->name, '/', dirent->namelen) != NULL)) return FOUND_ERR; if (ff->readdir.pos == ctx->pos) { res = FOUND_SOME; if (!dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, dirent->type)) return FOUND_ALL; ctx->pos = dirent->off; } ff->readdir.pos = dirent->off; ff->readdir.cache_off += reclen; offset += reclen; } return res; } static void fuse_rdc_reset(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); fi->rdc.cached = false; fi->rdc.version++; fi->rdc.size = 0; fi->rdc.pos = 0; } #define UNCACHED 1 static int fuse_readdir_cached(struct file *file, struct dir_context *ctx) { struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); enum fuse_parse_result res; pgoff_t index; unsigned int size; struct page *page; void *addr; /* Seeked? If so, reset the cache stream */ if (ff->readdir.pos != ctx->pos) { ff->readdir.pos = 0; ff->readdir.cache_off = 0; } /* * We're just about to start reading into the cache or reading the * cache; both cases require an up-to-date mtime value. */ if (!ctx->pos && fc->auto_inval_data) { int err = fuse_update_attributes(inode, file, STATX_MTIME); if (err) return err; } retry: spin_lock(&fi->rdc.lock); retry_locked: if (!fi->rdc.cached) { /* Starting cache? Set cache mtime. */ if (!ctx->pos && !fi->rdc.size) { fi->rdc.mtime = inode_get_mtime(inode); fi->rdc.iversion = inode_query_iversion(inode); } spin_unlock(&fi->rdc.lock); return UNCACHED; } /* * When at the beginning of the directory (i.e. just after opendir(3) or * rewinddir(3)), then need to check whether directory contents have * changed, and reset the cache if so. */ if (!ctx->pos) { struct timespec64 mtime = inode_get_mtime(inode); if (inode_peek_iversion(inode) != fi->rdc.iversion || !timespec64_equal(&fi->rdc.mtime, &mtime)) { fuse_rdc_reset(inode); goto retry_locked; } } /* * If cache version changed since the last getdents() call, then reset * the cache stream. */ if (ff->readdir.version != fi->rdc.version) { ff->readdir.pos = 0; ff->readdir.cache_off = 0; } /* * If at the beginning of the cache, than reset version to * current. */ if (ff->readdir.pos == 0) ff->readdir.version = fi->rdc.version; WARN_ON(fi->rdc.size < ff->readdir.cache_off); index = ff->readdir.cache_off >> PAGE_SHIFT; if (index == (fi->rdc.size >> PAGE_SHIFT)) size = fi->rdc.size & ~PAGE_MASK; else size = PAGE_SIZE; spin_unlock(&fi->rdc.lock); /* EOF? */ if ((ff->readdir.cache_off & ~PAGE_MASK) == size) return 0; page = find_get_page_flags(file->f_mapping, index, FGP_ACCESSED | FGP_LOCK); /* Page gone missing, then re-added to cache, but not initialized? */ if (page && !PageUptodate(page)) { unlock_page(page); put_page(page); page = NULL; } spin_lock(&fi->rdc.lock); if (!page) { /* * Uh-oh: page gone missing, cache is useless */ if (fi->rdc.version == ff->readdir.version) fuse_rdc_reset(inode); goto retry_locked; } /* Make sure it's still the same version after getting the page. */ if (ff->readdir.version != fi->rdc.version) { spin_unlock(&fi->rdc.lock); unlock_page(page); put_page(page); goto retry; } spin_unlock(&fi->rdc.lock); /* * Contents of the page are now protected against changing by holding * the page lock. */ addr = kmap_local_page(page); res = fuse_parse_cache(ff, addr, size, ctx); kunmap_local(addr); unlock_page(page); put_page(page); if (res == FOUND_ERR) return -EIO; if (res == FOUND_ALL) return 0; if (size == PAGE_SIZE) { /* We hit end of page: skip to next page. */ ff->readdir.cache_off = ALIGN(ff->readdir.cache_off, PAGE_SIZE); goto retry; } /* * End of cache reached. If found position, then we are done, otherwise * need to fall back to uncached, since the position we were looking for * wasn't in the cache. */ return res == FOUND_SOME ? 0 : UNCACHED; } int fuse_readdir(struct file *file, struct dir_context *ctx) { struct fuse_file *ff = file->private_data; struct inode *inode = file_inode(file); int err; if (fuse_is_bad(inode)) return -EIO; err = UNCACHED; if (ff->open_flags & FOPEN_CACHE_DIR) err = fuse_readdir_cached(file, ctx); if (err == UNCACHED) err = fuse_readdir_uncached(file, ctx); return err; } |
| 24 66 219 114 11 26 27 25 4 26 26 11 45 45 45 46 46 46 11 2 2 2 2 1 24 24 24 1 24 24 24 11 11 1 11 11 11 29 29 26 29 29 26 26 16 4 14 14 14 14 14 12 12 12 1 12 12 12 60 38 60 41 41 46 46 7 7 7 7 5 5 5 54 54 44 54 172 173 165 122 72 72 72 72 26 25 26 55 52 55 2 2 2 2 2 26 25 26 26 26 26 26 15 15 15 15 15 4 15 14 15 15 15 15 26 11 26 25 26 11 1 10 1 1 1 1 1 1 1 1 1 55 55 55 6 55 3 6 10 6 10 14 14 14 14 11 6 14 10 3 14 14 2 2 2 2 17 17 10 17 8 6 10 17 6 6 5 6 13 13 7 13 4 6 4 11 1 1 1 1 1 49 50 50 36 36 5 1 1 3 3 25 6 5 6 6 26 13 26 26 579 584 573 16 25 14 4 13 301 25 25 25 25 25 5 25 25 25 25 24 25 25 25 25 25 25 1 1 1 1 1 1 11 8 8 4 4 4 4 1 1 1 4 11 11 8 4 4 8 11 2 6 2 6 6 6 15 16 16 16 16 16 16 16 16 16 1 1 1 1 1 1 1 1 1 1 1 1 1 321 322 325 320 1 64 2 41 289 15 14 2 12 13 13 13 313 9 319 317 316 1 325 2 2 320 41 289 325 301 24 316 323 323 323 322 321 323 322 315 317 1 4 60 4 56 60 321 1 318 325 322 6 5 5 317 319 60 60 60 60 320 320 67 67 67 67 66 66 326 15 15 9 8 15 6 6 6 15 5 15 21 35 79 80 80 47 46 45 47 46 46 75 35 35 35 35 21 35 35 35 34 35 15 323 330 327 20 20 20 20 20 1 1 13 13 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 325 327 328 3 3 3 323 328 323 325 3 330 330 327 324 324 216 117 71 326 330 330 328 80 275 274 276 276 274 272 274 275 328 324 1 1 1 1 1 1 1 1 1 1 1 1 1 1 137 136 135 137 136 136 114 114 112 114 114 114 112 113 114 114 108 1 114 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 114 115 115 115 115 94 94 94 14 25 13 25 25 14 24 3 3 3 2 3 2 1 1 1 1 590 596 595 119 592 593 589 57 588 589 587 23 6 592 590 13 13 13 593 588 592 56 4 55 55 595 592 113 3 112 594 56 1 54 23 22 22 54 590 593 593 590 588 580 575 13 13 591 587 574 589 3 4 3 3 4 3 3 4 4 4 3 4 4 4 4 593 585 588 4 4 4 4 4 1 1 1 1 1 1 588 593 587 589 593 4 4 4 4 4 4 4 4 4 4 593 593 593 589 3 3 3 3 3 11 11 11 11 11 11 11 11 26 2 26 27 27 27 27 1 1 1 1 1 1 1 1 1 1 1 2 2 15 2 2 2 2 2 1 1 15 15 15 14 15 15 14 15 14 15 2 2 2 2 16 16 16 1 1 1 1 1 1 1 1 6 4 3 4 4 55 55 12 55 4 4 30 30 1 30 6 6 5 6 6 3 6 3 3 6 6 3 6 6 1 1 1 4 4 4 4 4 4 4 3 5 5 5 3 3 3 3 3 5 5 5 5 3 3 3 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 54 13 55 52 6 6 1 6 6 6 6 3 6 6 6 6 6 6 6 6 6 1 1 1 1 1 1 1 1 1 1 6 6 6 6 6 6 6 6 5 6 5 5 6 1 1 1 1 9 9 9 9 9 9 9 1 1 1 13 3 7 6 3 3 6 7 7 7 7 7 3 7 3 3 2 8 7 2 2 8 8 8 8 8 3 8 3 37 35 24 26 26 3 21 3 25 15 23 64 45 41 45 45 44 1 64 17 18 9 18 15 6 12 14 2 2 2 2 15 5 5 15 29 25 28 12 9 6 26 14 7 26 14 12 11 3 3 7 7 1 6 6 6 6 5 5 5 5 3 1 3 2 2 2 2 1 3 2 2 2 2 2 1 2 2 2 54 54 55 54 55 55 56 56 1 1 4 5 5 4 4 5 3 59 59 58 4 4 55 55 4 4 4 4 4 4 4 8 9 8 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 1 4 4 4 5 5 1 5 5 5 5 1 1 4 1 24 25 2 25 25 1 1 1 28 18 28 1 1 28 1 1 27 1 1 28 1 28 27 5 5 28 28 21 28 28 28 28 28 28 15 28 1 28 13 11 2 28 27 13 12 12 12 28 3 5 3 5 8 7 8 7 8 8 2 7 29 29 28 12 12 12 29 29 12 28 28 29 29 1 1 1 25 23 15 1 24 25 26 26 26 24 25 26 1 25 22 24 22 25 25 25 25 25 25 17 25 9 25 2 23 5 25 25 22 24 24 7 24 1 23 21 9 1 1 1 1 1 1 167 2 2 168 168 166 164 38 38 19 19 19 24 19 24 24 55 43 20 7 20 17 7 54 9 9 54 47 47 45 35 12 29 29 28 29 27 29 29 29 28 28 10 29 29 29 29 17 29 28 12 12 12 12 12 12 12 37 31 10 35 11 11 5 5 5 6 12 12 12 11 11 11 11 11 10 11 11 11 11 10 9 9 9 4 3 4 1 4 3 4 3 4 4 4 10 4 3 4 3 4 2 2 2 2 2 2 2 13 2 11 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dahinds@users.sourceforge.net> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * Pekka Riikonen <priikone@poesidon.pspt.fi> * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set * to 2 if register_netdev gets called * before net_dev_init & also removed a * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into * drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before * calling netif_rx. Saves a function * call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() * Dave Miller : 32bit quantity for the device lock to * make it work out on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait * indefinitely on dev->refcnt * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ #include <linux/uaccess.h> #include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/isolation.h> #include <linux/sched/mm.h> #include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/gro.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/tcx.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <net/ip.h> #include <net/mpls.h> #include <linux/ipv6.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> #include <trace/events/qdisc.h> #include <trace/events/xdp.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.h> #include "dev.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; WRITE_ONCE(net->dev_base_seq, val ?: 1); } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } #ifndef CONFIG_PREEMPT_RT static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); static int __init setup_backlog_napi_threads(char *arg) { static_branch_enable(&use_backlog_threads_key); return 0; } early_param("thread_backlog_napi", setup_backlog_napi_threads); static bool use_backlog_threads(void) { return static_branch_unlikely(&use_backlog_threads_key); } #else static bool use_backlog_threads(void) { return true; } #endif static inline void backlog_lock_irq_save(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_save(*flags); } static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); } static inline void backlog_unlock_irq_restore(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); if (!name_node) return NULL; INIT_HLIST_NODE(&name_node->hlist); name_node->dev = dev; name_node->name = name; return name_node; } static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { struct netdev_name_node *name_node; name_node = netdev_name_node_alloc(dev, dev->name); if (!name_node) return NULL; INIT_LIST_HEAD(&name_node->list); return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) { kfree(name_node); } static void netdev_name_node_add(struct net *net, struct netdev_name_node *name_node) { hlist_add_head_rcu(&name_node->hlist, dev_name_hash(net, name_node->name)); } static void netdev_name_node_del(struct netdev_name_node *name_node) { hlist_del_rcu(&name_node->hlist); } static struct netdev_name_node *netdev_name_node_lookup(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry_rcu(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } bool netdev_name_in_use(struct net *net, const char *name) { return netdev_name_node_lookup(net, name); } EXPORT_SYMBOL(netdev_name_in_use); int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (name_node) return -EEXIST; name_node = netdev_name_node_alloc(dev, name); if (!name_node) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } static void netdev_name_node_alt_free(struct rcu_head *head) { struct netdev_name_node *name_node = container_of(head, struct netdev_name_node, rcu); kfree(name_node->name); netdev_name_node_free(name_node); } static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { netdev_name_node_del(name_node); list_del(&name_node->list); call_rcu(&name_node->rcu, netdev_name_node_alt_free); } int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; /* lookup might have found our primary name or a name belonging * to another device. */ if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; __netdev_name_node_alt_destroy(name_node); return 0; } static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) { list_del(&name_node->list); netdev_name_node_alt_free(&name_node->rcu); } } /* Device list insertion */ static void list_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); dev_base_seq_inc(net); } /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ static void unlist_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); netdev_for_each_altname(dev, name_node) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ static DEFINE_PER_CPU(struct page_pool *, system_page_pool); #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ static const unsigned short netdev_lock_type[] = { ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { int i; for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ return ARRAY_SIZE(netdev_lock_type) - 1; } static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { int i; i = netdev_lock_pos(dev_type); lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { int i; i = netdev_lock_pos(dev->type); lockdep_set_class_and_name(&dev->addr_list_lock, &netdev_addr_lock_key[i], netdev_lock_name[i]); } #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif /******************************************************************************* * * Protocol management and registration routines * *******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscuous ptype_all chain in net_bh. * It is true now, do not change it. * Explanation follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** * dev_add_pack - add packet handler * @pt: packet type declaration * * Add a protocol handler to the networking stack. The passed &packet_type * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ void __dev_remove_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); struct packet_type *pt1; spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { list_del_rcu(&pt->list); goto out; } } pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); /** * dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); synchronize_net(); } EXPORT_SYMBOL(dev_remove_pack); /******************************************************************************* * * Device Interface Subroutines * *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface * @dev: targeted interface * * Indicates the ifindex the interface is linked to. * Physical interfaces have the same 'ifindex' and 'iflink' values. */ int dev_get_iflink(const struct net_device *dev) { if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); /** * dev_fill_metadata_dst - Retrieve tunnel egress information. * @dev: targeted interface * @skb: The packet. * * For better visibility of tunnel traffic OVS needs to retrieve * egress tunnel information for a packet. Following API allows * user to get this info. */ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info; if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) return -EINVAL; info = skb_tunnel_info_unclone(skb); if (!info) return -ENOMEM; if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) return -EINVAL; return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) return NULL; return &stack->path[k]; } int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack) { const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, }; struct net_device_path *path; int ret = 0; memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; path = dev_fwd_path(stack); if (!path) return -1; memset(path, 0, sizeof(struct net_device_path)); ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); if (ret < 0) return -1; if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } if (!ctx.dev) return ret; path = dev_fwd_path(stack); if (!path) return -1; path->type = DEV_PATH_ETHERNET; path->dev = ctx.dev; return ret; } EXPORT_SYMBOL_GPL(dev_fill_forward_path); /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name_rcu - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup_rcu(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); /* Deprecated for new users, call netdev_get_by_name() instead */ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); /** * netdev_get_by_name() - find a device by its name * @net: the applicable net namespace * @name: name to find * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Find an interface by name. This can be called from any * context and does its own locking. The returned handle has * the usage count incremented and the caller must use netdev_put() to * release it when it is no longer needed. %NULL is returned if no * matching device is found. */ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_name(net, name); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(__dev_get_by_index); /** * dev_get_by_index_rcu - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(dev_get_by_index_rcu); /* Deprecated for new users, call netdev_get_by_index() instead */ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); /** * netdev_get_by_index() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Search for an interface by index. Returns NULL if the device * is not found or a pointer to the device. The device returned has * had a reference added and the pointer is safe until the user calls * netdev_put() to indicate they have finished with it. */ struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_index); /** * dev_get_by_napi_id - find a device by napi_id * @napi_id: ID of the NAPI struct * * Search for an interface by NAPI ID. Returns %NULL if the device * is not found or a pointer to the device. The device has not had * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); if (napi_id < MIN_NAPI_ID) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } EXPORT_SYMBOL(dev_get_by_napi_id); static DEFINE_SEQLOCK(netdev_rename_lock); void netdev_copy_name(struct net_device *dev, char *name) { unsigned int seq; do { seq = read_seqbegin(&netdev_rename_lock); strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq)); } /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; int ret; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { ret = -ENODEV; goto out; } netdev_copy_name(dev, name); ret = 0; out: rcu_read_unlock(); return ret; } /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. * The caller must hold RCU or RTNL. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * */ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; rcu_read_lock(); for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); ret = dev; break; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); /** * __dev_get_by_flags - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device * is not found or a pointer to the device. Must be called inside * rtnl_lock(), and result refcount is unchanged. */ struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ASSERT_RTNL(); ret = NULL; for_each_netdev(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { ret = dev; break; } } return ret; } EXPORT_SYMBOL(__dev_get_by_flags); /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) { if (*name == '\0') return false; if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; while (*name) { if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } return true; } EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; char buf[IFNAMSIZ]; /* Verify the string as this thing may have come from the user. * There must be one "%d" and no other "%" characters. */ p = strchr(name, '%'); if (!p || p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; /* Use one page as a bit array of possible slots */ inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); bitmap_free(inuse); if (i == max_netdevices) return -ENFILE; /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */ strscpy(buf, name, IFNAMSIZ); snprintf(res, IFNAMSIZ, buf, i); return i; } /* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ static int dev_prep_valid_name(struct net *net, struct net_device *dev, const char *want_name, char *out_name, int dup_errno) { if (!dev_valid_name(want_name)) return -EINVAL; if (strchr(want_name, '%')) return __dev_alloc_name(net, want_name, out_name); if (netdev_name_in_use(net, want_name)) return -dup_errno; if (out_name != want_name) strscpy(out_name, want_name, IFNAMSIZ); return 0; } /** * dev_alloc_name - allocate a name for a device * @dev: device * @name: name format string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ int dev_alloc_name(struct net_device *dev, const char *name) { return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { int ret; ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); return ret < 0 ? ret : 0; } /** * dev_change_name - change name of a device * @dev: device * @newname: name (or format string) must be at least IFNAMSIZ * * Change name of a device, can pass format strings "eth%d". * for wildcarding. */ int dev_change_name(struct net_device *dev, const char *newname) { unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; struct net *net; ASSERT_RTNL(); BUG_ON(!dev_net(dev)); net = dev_net(dev); down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { up_write(&devnet_rename_sem); return 0; } memcpy(oldname, dev->name, IFNAMSIZ); write_seqlock(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); write_sequnlock(&netdev_rename_lock); if (err < 0) { up_write(&devnet_rename_sem); return err; } if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED); rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); up_write(&devnet_rename_sem); return ret; } up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); synchronize_net(); netdev_name_node_add(net, dev->name_node); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); if (ret) { /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; down_write(&devnet_rename_sem); write_seqlock(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; goto rollback; } else { netdev_err(dev, "name change rollback failed: %d\n", ret); } } return err; } /** * dev_set_alias - change ifalias of a device * @dev: device * @alias: name up to IFALIASZ * @len: limit of bytes to copy from info * * Set ifalias for a device, */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; if (len) { new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); if (!new_alias) return -ENOMEM; memcpy(new_alias->ifalias, alias, len); new_alias->ifalias[len] = 0; } mutex_lock(&ifalias_mutex); new_alias = rcu_replace_pointer(dev->ifalias, new_alias, mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) kfree_rcu(new_alias, rcuhead); return len; } EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device * @dev: device * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go * away, e.g. rcu read lock or own a reference count to device. */ int dev_get_alias(const struct net_device *dev, char *name, size_t len) { const struct dev_ifalias *alias; int ret = 0; rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock(); return ret; } /** * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); /** * netdev_state_change - device changes state * @dev: device to cause notification * * Called to indicate a device has changed state. This function calls * the notifier chains for netdev_chain and sends a NEWLINK message * to the routing socket. */ void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { struct netdev_notifier_change_info change_info = { .info.dev = dev, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } EXPORT_SYMBOL(netdev_state_change); /** * __netdev_notify_peers - notify network peers about existence of @dev, * to be called when rtnl lock is already held. * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void __netdev_notify_peers(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); } EXPORT_SYMBOL(__netdev_notify_peers); /** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); static int napi_threaded_poll(void *data); static int napi_kthread_create(struct napi_struct *n) { int err = 0; /* Create and wake up the kthread once to put it in * TASK_INTERRUPTIBLE mode to avoid the blocked task * warning and work with loadavg. */ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", n->dev->name, n->napi_id); if (IS_ERR(n->thread)) { err = PTR_ERR(n->thread); pr_err("kthread_run failed with err %d\n", err); n->thread = NULL; } return err; } static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ if (dev->dev.parent) pm_runtime_resume(dev->dev.parent); if (!netif_device_present(dev)) return -ENODEV; } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ netpoll_poll_disable(dev); ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack); ret = notifier_to_errno(ret); if (ret) return ret; set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { dev->flags |= IFF_UP; dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } /** * dev_open - prepare an interface for use. * @dev: device to open * @extack: netlink extended ack * * Takes a device from down to up state. The device's private open * function is invoked and then the multicast lists are loaded. Finally * the device is moved into the up state and a %NETDEV_UP message is * sent to the netdev notifier chain. * * Calling this function on an active interface is a nop. On a failure * a negative errno code is returned. */ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; if (dev->flags & IFF_UP) return 0; ret = __dev_open(dev, extack); if (ret < 0) return ret; rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } EXPORT_SYMBOL(dev_open); static void __dev_close_many(struct list_head *head) { struct net_device *dev; ASSERT_RTNL(); might_sleep(); list_for_each_entry(dev, head, close_list) { /* Temporarily disable netpoll until the interface is down */ netpoll_poll_disable(dev); call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); /* Synchronize to scheduled poll. We cannot touch poll list, it * can be even on different cpu. So just clear netif_running(). * * dev->stop() will invoke napi_disable() on all of it's * napi_struct instances on this device. */ smp_mb__after_atomic(); /* Commit netif_running(). */ } dev_deactivate_many(head); list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; /* * Call the device specific close. This cannot fail. * Only if device is UP * * We allow it to be called even after a DETACH hot-plug * event. */ if (ops->ndo_stop) ops->ndo_stop(dev); dev->flags &= ~IFF_UP; netpoll_poll_enable(dev); } } static void __dev_close(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); __dev_close_many(&single); list_del(&single); } void dev_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; /* Remove the devices that don't need to be closed */ list_for_each_entry_safe(dev, tmp, head, close_list) if (!(dev->flags & IFF_UP)) list_del_init(&dev->close_list); __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); } } EXPORT_SYMBOL(dev_close_many); /** * dev_close - shutdown an interface. * @dev: device to shutdown * * This function moves an active device into down state. A * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier * chain. */ void dev_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(dev_close); /** * dev_disable_lro - disable Large Receive Offload on a device * @dev: device * * Disable Large Receive Offload (LRO) on a net device. Must be * called under RTNL. This is needed if received packets may be * forwarded to another interface. */ void dev_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; dev->wanted_features &= ~NETIF_F_LRO; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); netdev_for_each_lower_dev(dev, lower_dev, iter) dev_disable_lro(lower_dev); } EXPORT_SYMBOL(dev_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device * @dev: device * * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be * called under RTNL. This is needed if Generic XDP is installed on * the device. */ static void dev_disable_gro_hw(struct net_device *dev) { dev->wanted_features &= ~NETIF_F_GRO_HW; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_GRO_HW)) netdev_WARN(dev, "failed to disable GRO_HW!\n"); } const char *netdev_cmd_to_name(enum netdev_cmd cmd) { #define N(val) \ case NETDEV_##val: \ return "NETDEV_" __stringify(val); switch (cmd) { N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; } EXPORT_SYMBOL_GPL(netdev_cmd_to_name); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { struct netdev_notifier_info info = { .dev = dev, }; return nb->notifier_call(nb, val, &info); } static int call_netdevice_register_notifiers(struct notifier_block *nb, struct net_device *dev) { int err; err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) return err; if (!(dev->flags & IFF_UP)) return 0; call_netdevice_notifier(nb, NETDEV_UP, dev); return 0; } static void call_netdevice_unregister_notifiers(struct notifier_block *nb, struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifier(nb, NETDEV_GOING_DOWN, dev); call_netdevice_notifier(nb, NETDEV_DOWN, dev); } call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } static int call_netdevice_register_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; int err; for_each_netdev(net, dev) { err = call_netdevice_register_notifiers(nb, dev); if (err) goto rollback; } return 0; rollback: for_each_netdev_continue_reverse(net, dev) call_netdevice_unregister_notifiers(nb, dev); return err; } static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; for_each_netdev(net, dev) call_netdevice_unregister_notifiers(nb, dev); } static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { err = call_netdevice_register_net_notifiers(nb, net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) call_netdevice_unregister_net_notifiers(nb, net); raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); if (err) goto unlock; for_each_net(net) call_netdevice_unregister_net_notifiers(nb, net); unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); static int __register_netdevice_notifier_net(struct net *net, struct notifier_block *nb, bool ignore_call_fail) { int err; err = raw_notifier_chain_register(&net->netdev_chain, nb); if (err) return err; if (dev_boot_phase) return 0; err = call_netdevice_register_net_notifiers(nb, net); if (err && !ignore_call_fail) goto chain_unregister; return 0; chain_unregister: raw_notifier_chain_unregister(&net->netdev_chain, nb); return err; } static int __unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; err = raw_notifier_chain_unregister(&net->netdev_chain, nb); if (err) return err; call_netdevice_unregister_net_notifiers(nb, net); return 0; } /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); /** * unregister_netdevice_notifier_net - unregister a per-netns * network notifier block * @net: network namespace * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier_net(). The notifier is unlinked from the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_netdevice_notifier_net(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); static void __move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, struct notifier_block *nb) { __unregister_netdevice_notifier_net(src_net, nb); __register_netdevice_notifier_net(dst_net, nb, true); } int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); static void move_netdevice_notifiers_dev_net(struct net_device *dev, struct net *net) { struct netdev_net_notifier *nn; list_for_each_entry(nn, &dev->net_notifier_list, list) __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); int ret; ASSERT_RTNL(); /* Run per-netns notifier block chain first, then run the global one. * Hopefully, one day, the global one is going to be removed after * all notifier block registrators get converted to be per-netns. */ ret = raw_notifier_call_chain(&net->netdev_chain, val, info); if (ret & NOTIFY_STOP_MASK) return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers_info_robust - call per-netns notifier blocks * for and rollback on error * @val_up: value passed unmodified to notifier function * @val_down: value passed unmodified to the notifier function when * recovering from an error on @val_up * @info: notifier information data * * Call all per-netns network notifier blocks, but not notifier blocks on * the global notifier chain. Parameters and return value are as for * raw_notifier_call_chain_robust(). */ static int call_netdevice_notifiers_info_robust(unsigned long val_up, unsigned long val_down, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); ASSERT_RTNL(); return raw_notifier_call_chain_robust(&net->netdev_chain, val_up, val_down, info); } static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_info info = { .dev = dev, .extack = extack, }; return call_netdevice_notifiers_info(val, &info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { return call_netdevice_notifiers_extack(val, dev, NULL); } EXPORT_SYMBOL(call_netdevice_notifiers); /** * call_netdevice_notifiers_mtu - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * @arg: additional u32 argument passed to the notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_mtu(unsigned long val, struct net_device *dev, u32 arg) { struct netdev_notifier_info_ext info = { .info.dev = dev, .ext.mtu = arg, }; BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); return call_netdevice_notifiers_info(val, &info.info); } #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif #ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); EXPORT_SYMBOL(tcf_bypass_check_needed_key); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); int wanted; wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) static_branch_enable(&netstamp_needed_key); else static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 0) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 1) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; skb->mono_delivery_time = 0; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, bool check_mtu) { int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } return ret; } int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, true); } EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif * * @dev: destination network device * @skb: buffer to forward * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue * of another device. * * The receiving device may be in another namespace, so * we have to clear all information in the skb that could * impact namespace isolation. */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, struct net_device *orig_dev, __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; if (pt_prev) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; } static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) return ptype->id_match(ptype, skb->sk); else if ((struct sock *)ptype->af_packet_priv == skb->sk) return true; return false; } /** * dev_nit_active - return true if any network interface taps are in use * * @dev: network device to check for the presence of taps */ bool dev_nit_active(struct net_device *dev) { return !list_empty(&net_hotdata.ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct list_head *ptype_list = &net_hotdata.ptype_all; struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if (skb_loop_sk(ptype, skb)) continue; if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; } /* need to clone skb, done only once */ skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out_unlock; net_timestamp_set(skb2); /* skb->nh should be correctly * set by sender, so that the second statement is * just protection against buggy protocols. */ skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; pt_prev = ptype; } if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } out_unlock: if (pt_prev) { if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); else kfree_skb(skb2); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); /** * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * * If real_num_tx_queues is changed the tc mappings may no longer be * valid. To resolve this verify the tc mapping remains valid and if * not NULL the mapping. With no priorities mapping to this * offset/count pair it will no longer be used. In the worst case TC0 * is invalid nothing can be done so disable priority mappings. If is * expected that drivers will fix this mapping if they can before * calling netif_set_real_num_tx_queues. */ static void netif_setup_tc(struct net_device *dev, unsigned int txq) { int i; struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } /* Invalidated prio to tc mappings set to TC0 */ for (i = 1; i < TC_BITMASK + 1; i++) { int q = netdev_get_prio_tc_map(dev, i); tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", i, q); netdev_set_prio_tc_map(dev, i, 0); } } } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) { if (dev->num_tc) { struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } /* didn't find it, just return -1 to indicate no match */ return -1; } return 0; } EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static struct static_key xps_needed __read_mostly; static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; for (pos = map->len; pos--;) { if (map->queues[pos] != index) continue; if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; break; } if (old_maps) RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } return true; } static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { int num_tc = dev_maps->num_tc; bool active = false; int tci; for (tci = cpu * num_tc; num_tc--; tci++) { int i, j; for (i = count, j = offset; i--; j++) { if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } active |= i < 0; } return active; } static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, enum xps_map_type type) { static_key_slow_dec_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_dec_cpuslocked(&xps_rxqs_needed); RCU_INIT_POINTER(dev->xps_maps[type], NULL); kfree_rcu(dev_maps, rcu); } static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, u16 offset, u16 count) { struct xps_dev_maps *dev_maps; bool active = false; int i, j; dev_maps = xmap_dereference(dev->xps_maps[type]); if (!dev_maps) return; for (j = 0; j < dev_maps->nr_ids; j++) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) reset_xps_maps(dev, dev_maps, type); if (type == XPS_CPUS) { for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); if (static_key_false(&xps_rxqs_needed)) clean_xps_maps(dev, XPS_RXQS, offset, count); clean_xps_maps(dev, XPS_CPUS, offset, count); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; int i, pos; for (pos = 0; map && pos < map->len; pos++) { if (map->queues[pos] != index) continue; return map; } /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; alloc_len = map->alloc_len * 2; } /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's * map */ if (is_rxqs_map) new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); else new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, cpu_to_node(attr_index)); if (!new_map) return NULL; for (i = 0; i < pos; i++) new_map->queues[i] = map->queues[i]; new_map->alloc_len = alloc_len; new_map->len = pos; return new_map; } /* Copy xps maps at a given index */ static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, struct xps_dev_maps *new_dev_maps, int index, int tc, bool skip_tc) { int i, tci = index * dev_maps->num_tc; struct xps_map *map; /* copy maps belonging to foreign traffic classes */ for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && skip_tc) continue; /* fill in the new device map from the old device map */ map = xmap_dereference(dev_maps->attr_map[tci]); RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; const unsigned long *online_mask = NULL; bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; unsigned int nr_ids; WARN_ON_ONCE(index >= dev->num_tx_queues); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) return -EINVAL; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps[type]); if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; /* The old dev_maps could be larger or smaller than the one we're * setting up now, as dev->num_tc or nr_ids could have been updated in * between. We could try to be smart, but let's be safe instead and only * copy foreign traffic classes if the two map sizes match. */ if (dev_maps && dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) copy = true; /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { if (!new_dev_maps) { new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { mutex_unlock(&xps_map_mutex); return -ENOMEM; } new_dev_maps->nr_ids = nr_ids; new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } for (j = 0; j < nr_ids; j++) { bool skip_tc = false; tci = j * num_tc + tc; if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; skip_tc = true; map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif } if (copy) xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, skip_tc); } rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; for (j = 0; j < dev_maps->nr_ids; j++) { for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) continue; if (copy) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); if (map == new_map) continue; } RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); } } old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ for (j = 0; j < dev_maps->nr_ids; j++) { tci = j * dev_maps->num_tc; for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && netif_attr_test_mask(j, mask, dev_maps->nr_ids) && netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) continue; active |= remove_xps_queue(dev_maps, copy ? old_dev_maps : NULL, tci, index); } } if (old_dev_maps) kfree_rcu(old_dev_maps, rcu); /* free map if not active */ if (!active) reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: /* remove any maps that we added */ for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); } } mutex_unlock(&xps_map_mutex); kfree(new_dev_maps); return -ENOMEM; } EXPORT_SYMBOL_GPL(__netif_set_xps_queue); int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { int ret; cpus_read_lock(); ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(netif_set_xps_queue); #endif static void netdev_unbind_all_sb_channels(struct net_device *dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; /* Unbind any subordinate channels */ while (txq-- != &dev->_tx[0]) { if (txq->sb_dev) netdev_unbind_sb_channel(dev, txq->sb_dev); } } void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } EXPORT_SYMBOL(netdev_reset_tc); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues(dev, offset, count); #endif dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } EXPORT_SYMBOL(netdev_set_tc_queue); int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(sb_dev, 0); #endif memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); while (txq-- != &dev->_tx[0]) { if (txq->sb_dev == sb_dev) txq->sb_dev = NULL; } } EXPORT_SYMBOL(netdev_unbind_sb_channel); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset) { /* Make certain the sb_dev and dev are already configured */ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) return -EINVAL; /* We cannot hand out queues we don't have */ if ((offset + count) > dev->real_num_tx_queues) return -EINVAL; /* Record the mapping */ sb_dev->tc_to_txq[tc].count = count; sb_dev->tc_to_txq[tc].offset = offset; /* Provide a way for Tx queue to find the tc_to_txq map or * XPS map for itself. */ while (count--) netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; return 0; } EXPORT_SYMBOL(netdev_bind_sb_channel_queue); int netdev_set_sb_channel(struct net_device *dev, u16 channel) { /* Do not use a multiqueue device to represent a subordinate channel */ if (netif_is_multiqueue(dev)) return -ENODEV; /* We allow channels 1 - 32767 to be used for subordinate channels. * Channel 0 is meant to be "native" mode and used only to represent * the main root device. We allow writing 0 to reset the device back * to normal mode after being used as a subordinate channel. */ if (channel > S16_MAX) return -EINVAL; dev->num_tc = -channel; return 0; } EXPORT_SYMBOL(netdev_set_sb_channel); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { bool disabling; int rc; disabling = txq < dev->real_num_tx_queues; if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); if (rc) return rc; if (dev->num_tc) netif_setup_tc(dev, txq); dev_qdisc_change_real_num_tx(dev, txq); dev->real_num_tx_queues = txq; if (disabling) { synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } } else { dev->real_num_tx_queues = txq; } return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); #ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device * @rxq: Actual number of RX queues * * This must be called either with the rtnl_lock held or before * registration of the net device. Returns 0 on success, or a * negative error code. If called before registration, it always * succeeds. */ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) { int rc; if (rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); if (rc) return rc; } dev->real_num_rx_queues = rxq; return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif /** * netif_set_real_num_queues - set actual number of RX and TX queues used * @dev: Network device * @txq: Actual number of TX queues * @rxq: Actual number of RX queues * * Set the real number of both TX and RX queues. * Does nothing if the number of queues is already correct. */ int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq) { unsigned int old_rxq = dev->real_num_rx_queues; int err; if (txq < 1 || txq > dev->num_tx_queues || rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; /* Start from increases, so the error path only does decreases - * decreases can't fail. */ if (rxq > dev->real_num_rx_queues) { err = netif_set_real_num_rx_queues(dev, rxq); if (err) return err; } if (txq > dev->real_num_tx_queues) { err = netif_set_real_num_tx_queues(dev, txq); if (err) goto undo_rx; } if (rxq < dev->real_num_rx_queues) WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); if (txq < dev->real_num_tx_queues) WARN_ON(netif_set_real_num_tx_queues(dev, txq)); return 0; undo_rx: WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); return err; } EXPORT_SYMBOL(netif_set_real_num_queues); /** * netif_set_tso_max_size() - set the max size of TSO frames supported * @dev: netdev to update * @size: max skb->len of a TSO frame * * Set the limit on the size of TSO super-frames the device can handle. * Unless explicitly set the stack will assume the value of * %GSO_LEGACY_MAX_SIZE. */ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) { dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); if (size < READ_ONCE(dev->gso_ipv4_max_size)) netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); /** * netif_set_tso_max_segs() - set the max number of segs supported for TSO * @dev: netdev to update * @segs: max number of TCP segments * * Set the limit on the number of TCP segments the device can generate from * a single TSO super-frame. * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. */ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) { dev->tso_max_segs = segs; if (segs < READ_ONCE(dev->gso_max_segs)) netif_set_gso_max_segs(dev, segs); } EXPORT_SYMBOL(netif_set_tso_max_segs); /** * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper * @to: netdev to update * @from: netdev from which to copy the limits */ void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) { netif_set_tso_max_size(to, from->tso_max_size); netif_set_tso_max_segs(to, from->tso_max_segs); } EXPORT_SYMBOL(netif_inherit_tso_max); /** * netif_get_num_default_rss_queues - default number of RSS queues * * Default value is the number of physical cores if there are only 1 or 2, or * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { cpumask_var_t cpus; int cpu, count = 0; if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) return 1; cpumask_copy(cpus, cpu_online_mask); for_each_cpu(cpu, cpus) { ++count; cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); } free_cpumask_var(cpus); return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); q->next_sched = NULL; *sd->output_queue_tailp = q; sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } void __netif_schedule(struct Qdisc *q) { if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); struct dev_kfree_skb_cb { enum skb_drop_reason reason; }; static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { return (struct dev_kfree_skb_cb *)skb->cb; } void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); } rcu_read_unlock(); } EXPORT_SYMBOL(netif_schedule_queue); void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { struct Qdisc *q; rcu_read_lock(); q = rcu_dereference(dev_queue->qdisc); __netif_schedule(q); rcu_read_unlock(); } } EXPORT_SYMBOL(netif_tx_wake_queue); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason) { unsigned long flags; if (unlikely(!skb)) return; if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); refcount_set(&skb->users, 0); } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; local_irq_save(flags); skb->next = __this_cpu_read(softnet_data.completion_queue); __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(dev_kfree_skb_irq_reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (in_hardirq() || irqs_disabled()) dev_kfree_skb_irq_reason(skb, reason); else kfree_skb_reason(skb, reason); } EXPORT_SYMBOL(dev_kfree_skb_any_reason); /** * netif_device_detach - mark device as removed * @dev: network device * * Mark device as removed from system and therefore no longer available. */ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); /** * netif_device_attach - mark device as attached * @dev: network device * * Mark device as attached from system and restart if needed. */ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ static u16 skb_tx_hash(const struct net_device *dev, const struct net_device *sb_dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; if (unlikely(!qcount)) { net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", sb_dev->name, qoffset, tc); qoffset = 0; qcount = dev->real_num_tx_queues; } } if (skb_rx_queue_recorded(skb)) { DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features; struct net_device *dev = skb->dev; const char *name = ""; if (!net_ratelimit()) return; if (dev) { if (dev->dev.parent) name = dev_driver_string(dev->dev.parent); else name = netdev_name(dev); } skb_dump(KERN_WARNING, skb, false); WARN(1, "%s: caps=(%pNF, %pNF)\n", name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ int skb_checksum_help(struct sk_buff *skb) { __wsum csum; int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (skb_has_shared_frag(skb)) { ret = __skb_linearize(skb); if (ret) goto out; } offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; } EXPORT_SYMBOL(skb_checksum_help); int skb_crc32c_csum_help(struct sk_buff *skb) { __le32 crc32c_csum; int ret = 0, offset, start; if (skb->ip_summed != CHECKSUM_PARTIAL) goto out; if (unlikely(skb_is_gso(skb))) goto out; /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (unlikely(skb_has_shared_frag(skb))) { ret = __skb_linearize(skb); if (ret) goto out; } start = skb_checksum_start_offset(skb); offset = start + offsetof(struct sctphdr, checksum); if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { ret = -EINVAL; goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__le32)); if (ret) goto out; crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); *(__le32 *)(skb->data + offset) = crc32c_csum; skb_reset_csum_not_inet(skb); out: return ret; } __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { struct ethhdr *eth; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) return 0; eth = (struct ethhdr *)skb->data; type = eth->h_proto; } return vlan_get_protocol_and_depth(skb, type, depth); } /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif /* XXX: check that highmem exists at all on the given machine. */ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (PageHighMem(skb_frag_page(frag))) return 1; } } #endif return 0; } /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ #if IS_ENABLED(CONFIG_NET_MPLS_GSO) static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { if (eth_p_mpls(type)) features &= skb->dev->mpls_features; return features; } #else static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { return features; } #endif static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { __be16 type; type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (illegal_highdma(skb->dev, skb)) features &= ~NETIF_F_SG; return features; } netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return features; } EXPORT_SYMBOL(passthru_features_check); static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return vlan_features_check(skb, features); } static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { u16 gso_segs = skb_shinfo(skb)->gso_segs; if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; } /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now * and we can pull them back in after we have partially * segmented the frame. */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) features &= ~dev->gso_partial_features; /* Make sure to clear the IPv4 ID mangling feature if the * IPv4 header has the potential to be fragmented. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { struct iphdr *iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); if (!(iph->frag_off & htons(IP_DF))) features &= ~NETIF_F_TSO_MANGLEID; } return features; } netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; if (skb_is_gso(skb)) features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard * features for the netdev */ if (skb->encapsulation) features &= dev->hw_enc_features; if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); else features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { unsigned int len; int rc; if (dev_nit_active(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; } struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; while (skb) { struct sk_buff *next = skb->next; skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; } skb = next; if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } } out: *ret = rc; return skb; } static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); if (features & NETIF_F_HW_CSUM) return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) goto out_null; skb = sk_validate_xmit_skb(skb, dev); if (unlikely(!skb)) goto out_null; if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); if (IS_ERR(segs)) { goto out_kfree_skb; } else if (segs) { consume_skb(skb); skb = segs; } } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb->encapsulation) skb_set_inner_transport_header(skb, skb_checksum_start_offset(skb)); else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } skb = validate_xmit_xfrm(skb, features, again); return skb; out_kfree_skb: kfree_skb(skb); out_null: dev_core_stats_tx_dropped_inc(dev); return NULL; } struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail; for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); if (!skb) continue; if (!head) head = skb; else tail->next = skb; /* If skb was segmented, skb->prev points to * the last segment. If not, it still contains skb. */ tail = skb->prev; } return head; } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size && skb_transport_header_was_set(skb)) { u16 gso_segs = shinfo->gso_segs; unsigned int hdr_len; /* mac layer + network layer */ hdr_len = skb_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (shinfo->gso_type & SKB_GSO_DODGY) gso_segs = DIV_ROUND_UP(skb->len - hdr_len, shinfo->gso_size); qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, struct sk_buff **to_free, struct netdev_queue *txq) { int rc; rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; if (rc == NET_XMIT_SUCCESS) trace_qdisc_enqueue(q, txq, skb); return rc; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); struct sk_buff *to_free = NULL; bool contended; int rc; qdisc_calculate_pkt_len(skb, q); tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP); if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { /* Retest nolock_qdisc_is_empty() within the protection * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); goto no_lock_out; } qdisc_bstats_cpu_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && !nolock_qdisc_is_empty(q)) __qdisc_run(q); qdisc_run_end(q); return NET_XMIT_SUCCESS; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); return rc; } if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); return NET_XMIT_DROP; } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit * and then other tasks will only enqueue packets. The packets will be * sent after the qdisc owner is scheduled again. To prevent this * scenario the task always serialize on the lock. */ contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); } qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); qdisc_run_end(q); } } spin_unlock(root_lock); if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; } #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { const struct netprio_map *map; const struct sock *sk; unsigned int prioidx; if (skb->priority) return; map = rcu_dereference_bh(skb->dev->priomap); if (!map) return; sk = skb_to_full_sk(skb); if (!sk) return; prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) #endif /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS static struct netdev_queue * netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) { int qm = skb_get_queue_mapping(skb); return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); } void netdev_xmit_skip_txqueue(bool skip) { __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, enum skb_drop_reason *drop_reason) { int ret = TC_ACT_UNSPEC; #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq); struct tcf_result res; if (!miniq) return ret; if (static_branch_unlikely(&tcf_bypass_check_needed_key)) { if (tcf_block_bypass_sw(miniq->block)) return ret; } tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); /* Only tcf related quirks below. */ switch (ret) { case TC_ACT_SHOT: *drop_reason = tcf_get_drop_reason(skb); mini_qdisc_qstats_cpu_drop(miniq); break; case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(res.classid); break; } #endif /* CONFIG_NET_CLS_ACT */ return ret; } static DEFINE_STATIC_KEY_FALSE(tcx_needed_key); void tcx_inc(void) { static_branch_inc(&tcx_needed_key); } void tcx_dec(void) { static_branch_dec(&tcx_needed_key); } static __always_inline enum tcx_action_base tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, const bool needs_mac) { const struct bpf_mprog_fp *fp; const struct bpf_prog *prog; int ret = TCX_NEXT; if (needs_mac) __skb_push(skb, skb->mac_len); bpf_mprog_foreach_prog(entry, fp, prog) { bpf_compute_data_pointers(skb); ret = bpf_prog_run(prog, skb); if (ret != TCX_NEXT) break; } if (needs_mac) __skb_pull(skb, skb->mac_len); return tcx_action_code(skb, ret); } static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; int sch_ret; if (!entry) return skb; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } qdisc_skb_cb(skb)->pkt_len = skb->len; tcx_set_ingress(skb, true); if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, true); if (sch_ret != TC_ACT_UNSPEC) goto ingress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); ingress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* skb_mac_header check was done by BPF, so we can safely * push the L2 header back before redirecting to another * netdev. */ __skb_push(skb, skb->mac_len); if (skb_do_redirect(skb) == -EAGAIN) { __skb_pull(skb, skb->mac_len); *another = true; break; } *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; return NULL; } return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; int sch_ret; if (!entry) return skb; /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, false); if (sch_ret != TC_ACT_UNSPEC) goto egress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); egress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; return NULL; } return skb; } #else static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { return skb; } #endif /* CONFIG_NET_XGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) return queue_index; tci *= dev_maps->num_tc; tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; else queue_index = map->queues[reciprocal_scale( skb_get_hash(skb), map->len)]; if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } return queue_index; } #endif static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } } rcu_read_unlock(); return queue_index; #else return -1; #endif } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; } EXPORT_SYMBOL(dev_pick_tx_cpu_id); u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); sb_dev = sb_dev ? : dev; if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); queue_index = new_index; } return queue_index; } EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { int queue_index = 0; #ifdef CONFIG_XPS u32 sender_cpu = skb->sender_cpu - 1; if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } /** * __dev_queue_xmit() - transmit a buffer * @skb: buffer to transmit * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling * this function. The function can be called from an interrupt. * * When calling this method, interrupts MUST be enabled. This is because * the BH enable code must have IRQs enabled so that it will not deadlock. * * Regardless of the return value, the skb is consumed, so it is currently * difficult to retry a send to this method. (You can bump the ref count * before sending to hold a reference for retry if you are careful.) * * Return: * * 0 - buffer successfully transmitted * * positive qdisc return code - NET_XMIT_DROP etc. * * negative errno - other errors */ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); skb_update_prio(skb); qdisc_pkt_len_init(skb); tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { skb = nf_hook_egress(skb, &rc, dev); if (!skb) goto out; } netdev_xmit_skip_txqueue(false); nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); if (netdev_xmit_txqueue_skipped()) txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); else skb_dst_force(skb); if (!txq) txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: * loopback, all the sorts of tunnels... * Really, it is unlikely that netif_tx_lock protection is necessary * here. (f.e. loopback and IP tunnels are clean ignoring statistics * counters.) * However, it is possible, that they rely on protection * made by us here. * Check this and shot the lock. It is not prone from deadlocks. *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ /* Other cpus might concurrently change txq->xmit_lock_owner * to -1 or to their cpu id, but not to our id. */ if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out; HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } } HARD_TX_UNLOCK(dev, txq); net_crit_ratelimited("Virtual device %s asks to queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; bool again = false; if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop; skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop; skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); dev_xmit_recursion_dec(); local_bh_enable(); return ret; drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ static DEFINE_PER_CPU(struct task_struct *, backlog_napi); int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { struct task_struct *thread; lockdep_assert_irqs_disabled(); if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/dev_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); if (thread) { if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) goto use_local_napi; set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } use_local_napi: list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) __raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { if (next_cpu < nr_cpu_ids) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *old_rflow; u32 flow_id, head; u16 rxq_index; int rc; /* Should we steer this flow to a different hardware queue? */ if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || !(dev->features & NETIF_F_NTUPLE)) goto out; rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); if (rxq_index == skb_get_rx_queue(skb)) goto out; rxqueue = dev->_rx + rxq_index; flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; flow_id = skb_get_hash(skb) & flow_table->mask; rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; WRITE_ONCE(rflow->filter, rc); if (old_rflow->filter == rc) WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER); out: #endif head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); rps_input_queue_tail_save(&rflow->last_qtail, head); } WRITE_ONCE(rflow->cpu, next_cpu); return rflow; } /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow **rflowp) { const struct rps_sock_flow_table *sock_flow_table; struct netdev_rx_queue *rxqueue = dev->_rx; struct rps_dev_flow_table *flow_table; struct rps_map *map; int cpu = -1; u32 tcpu; u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue += index; } /* Avoid computing hash if RFS/RPS is not active for this rxqueue */ flow_table = rcu_dereference(rxqueue->rps_flow_table); map = rcu_dereference(rxqueue->rps_map); if (!flow_table && !map) goto done; skb_reset_network_header(skb); hash = skb_get_hash(skb); if (!hash) goto done; sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; u32 ident; /* First check into global flow table if there is a match. * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ rflow = &flow_table->flows[hash & flow_table->mask]; tcpu = rflow->cpu; /* * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. * This guarantees that all previous packets for the flow * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; } } try_rps: if (map) { tcpu = map->cpus[reciprocal_scale(hash, map->len)]; if (cpu_online(tcpu)) { cpu = tcpu; goto done; } } done: return cpu; } #ifdef CONFIG_RFS_ACCEL /** * rps_may_expire_flow - check whether an RFS hardware filter may be removed * @dev: Device on which the filter was set * @rxq_index: RX queue index * @flow_id: Flow ID passed to ndo_rx_flow_steer() * @filter_id: Filter ID returned by ndo_rx_flow_steer() * * Drivers that implement ndo_rx_flow_steer() should periodically call * this function for each installed filter and remove the filters for * which it returns %true. */ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id) { struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids && ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - READ_ONCE(rflow->last_qtail)) < (int)(10 * flow_table->mask))) expire = false; } rcu_read_unlock(); return expire; } EXPORT_SYMBOL(rps_may_expire_flow); #endif /* CONFIG_RFS_ACCEL */ /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; ____napi_schedule(sd, &sd->backlog); sd->received_rps++; } #endif /* CONFIG_RPS */ /* Called from hardirq (IPI) context */ static void trigger_rx_softirq(void *data) { struct softnet_data *sd = data; __raise_softirq_irqoff(NET_RX_SOFTIRQ); smp_store_release(&sd->defer_ipi_scheduled, 0); } /* * After we queued a packet into sd->input_pkt_queue, * we need to make sure this queue is serviced soon. * * - If this is another cpu queue, link it to our rps_ipi_list, * and make sure we will process rps_ipi_list from net_rx_action(). * * - If this is our own queue, NAPI schedule our backlog. * Note that this also raises NET_RX_SOFTIRQ. */ static void napi_schedule_rps(struct softnet_data *sd) { struct softnet_data *mysd = this_cpu_ptr(&softnet_data); #ifdef CONFIG_RPS if (sd != mysd) { if (use_backlog_threads()) { __napi_schedule_irqoff(&sd->backlog); return; } sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; /* If not called from net_rx_action() or napi_threaded_poll() * we have to raise NET_RX_SOFTIRQ. */ if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll) __raise_softirq_irqoff(NET_RX_SOFTIRQ); return; } #endif /* CONFIG_RPS */ __napi_schedule_irqoff(&mysd->backlog); } void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu) { unsigned long flags; if (use_backlog_threads()) { backlog_lock_irq_save(sd, &flags); if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) __napi_schedule_irqoff(&sd->backlog); backlog_unlock_irq_restore(sd, &flags); } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { smp_call_function_single_async(cpu, &sd->defer_csd); } } #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) { #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; struct softnet_data *sd; unsigned int old_flow, new_flow; if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; fl->history_head++; fl->history_head &= FLOW_LIMIT_HISTORY - 1; if (likely(fl->buckets[old_flow])) fl->buckets[old_flow]--; if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { fl->count++; rcu_read_unlock(); return true; } } rcu_read_unlock(); #endif return false; } /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; int max_backlog; u32 tail; reason = SKB_DROP_REASON_DEV_READY; if (!netif_running(skb->dev)) goto bad_dev; reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); qlen = skb_queue_len_lockless(&sd->input_pkt_queue); max_backlog = READ_ONCE(net_hotdata.max_backlog); if (unlikely(qlen > max_backlog)) goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { if (!qlen) { /* Schedule NAPI for backlog device. We can use * non atomic operation as we own the queue lock. */ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) napi_schedule_rps(sd); } __skb_queue_tail(&sd->input_pkt_queue, skb); tail = rps_input_queue_tail_incr(sd); backlog_unlock_irq_restore(sd, &flags); /* save the tail outside of the critical section */ rps_input_queue_tail_save(qtail, tail); return NET_RX_SUCCESS; } backlog_unlock_irq_restore(sd, &flags); cpu_backlog_drop: atomic_inc(&sd->dropped); bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; } static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct netdev_rx_queue *rxqueue; rxqueue = dev->_rx; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); return rxqueue; /* Return first rxqueue */ } rxqueue += index; } return rxqueue; } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; u32 metalen, act; int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = (void *)skb_end_pointer(skb) - hard_start; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rxqueue = netif_get_rxqueue(skb); xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); if (skb_is_nonlinear(skb)) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { xdp_buff_clear_frags_flag(xdp); } orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; if (off) { if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; skb_reset_network_header(skb); } /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); skb->len += off; /* positive on grow, negative on shrink */ } /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. */ if (xdp_buff_has_frags(xdp)) skb->data_len = skb_shinfo(skb)->xdp_frags_size; else skb->data_len = 0; /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || (orig_host != ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull * before calling us again on redirect path. We do not call do_redirect * as we leave that up to the caller. * * Caller is responsible for managing lifetime of skb (i.e. calling * kfree_skb in response to actions it cannot handle/XDP_DROP). */ switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; } return act; } static int netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) return 0; /* In case we have to go down the path and also linearize, * then lets do the pskb_expand_head() work just once here. */ hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); troom = skb->tail + skb->data_len - skb->end; err = pskb_expand_head(skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC); if (err) return err; return skb_linearize(skb); } static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM * bytes. This is the guarantee that also native XDP provides, * thus we need to do it here as well. */ mac_len = skb->data - skb_mac_header(skb); __skb_push(skb, mac_len); if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } __skb_pull(*pskb, mac_len); act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: kfree_skb(*pskb); break; } return act; } /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. This also means * that XDP packets are able to starve other packets going through a qdisc, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; bool free_skb = true; int cpu, rc; txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; } HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) { if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: generic_xdp_tx(*pskb, xdp_prog); break; } return XDP_DROP; } } return XDP_PASS; out_redir: kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); } else #endif { unsigned int qtail; ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** * __netif_rx - Slightly optimized version of netif_rx * @skb: buffer to post * * This behaves as netif_rx except that it does not disable bottom halves. * As a result this function may only be invoked from the interrupt context * (either hard or soft interrupt). */ int __netif_rx(struct sk_buff *skb) { int ret; lockdep_assert_once(hardirq_count() | softirq_count()); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); return ret; } EXPORT_SYMBOL(__netif_rx); /** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for * the upper (protocol) levels to process via the backlog NAPI device. It * always succeeds. The buffer may be dropped during processing for * congestion control or by the protocol layers. * The network buffer is passed via the backlog NAPI device. Modern NIC * driver should use NAPI and GRO. * This function can used from interrupt and from process context. The * caller from process context must not disable interrupts before invoking * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ int netif_rx(struct sk_buff *skb) { bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; if (need_bh_off) local_bh_disable(); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); if (need_bh_off) local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_disable(); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_enable(); while (clist) { struct sk_buff *skb = clist; clist = clist->next; WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED)) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, get_kfree_skb_cb(skb)->reason); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __napi_kfree_skb(skb, get_kfree_skb_cb(skb)->reason); } } if (sd->output_queue) { struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); rcu_read_lock(); while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); if (!(q->flags & TCQ_F_NOLOCK)) { root_lock = qdisc_lock(q); spin_lock(root_lock); } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { /* There is a synchronize_net() between * STATE_DEACTIVATED flag being set and * qdisc_reset()/some_qdisc_is_busy() in * dev_deactivate(), so we can safely bail out * early here to avoid data race between * qdisc_deactivate() and some_qdisc_is_busy() * for lockless qdisc. */ clear_bit(__QDISC_STATE_SCHED, &q->state); continue; } clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } rcu_read_unlock(); } xfrm_dev_backlog(sd); } #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check * * Check if a receive handler is already registered for a given device. * Return true if there one. * * The caller must hold the rtnl_mutex. */ bool netdev_is_rx_handler_busy(struct net_device *dev) { ASSERT_RTNL(); return dev && rtnl_dereference(dev->rx_handler); } EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. * * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { if (netdev_is_rx_handler_busy(dev)) return -EBUSY; if (dev->priv_flags & IFF_NO_RX_HANDLER) return -EINVAL; /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); return 0; } EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); /* a reader seeing a non NULL rx_handler in a rcu_read_lock() * section has a guarantee to see a non NULL rx_handler_data * as well. */ synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); /* * Limit the use of PFMEMALLOC reserves to those protocols that implement * the special handling of PFMEMALLOC skbs. */ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_ARP): case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { if (nf_hook_ingress_active(skb)) { int ingress_retval; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock(); return ingress_retval; } return 0; } static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); orig_dev = skb->dev; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; another_round: skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), &skb); migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; goto out; } } if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } if (skb_skip_tc_classify(skb)) goto skip_classify; if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) goto another_round; if (!skb) goto out; nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; break; case RX_HANDLER_PASS: break; default: BUG(); } } if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. */ __vlan_hwaccel_clear_tag(skb); skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; if (vlan_do_receive(&skb)) /* After stripping off 802.1P header with vlan 0 * vlan dev is found for inner header. */ goto another_round; else if (unlikely(!skb)) goto out; else /* We have stripped outer 802.1P vlan 0 header. * But could not find vlan dev. * check again for vlan id to set OTHERHOST. */ goto check_vlan_id; } /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() * For the time being, just ignore Priority Code Point */ __vlan_hwaccel_clear_tag(skb); } type = skb->protocol; /* deliver only exact match when indicated */ if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &orig_dev->ptype_specific); if (unlikely(skb->dev != orig_dev)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &skb->dev->ptype_specific); } if (pt_prev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ ret = NET_RX_DROP; } out: /* The invariant here is that if *ppt_prev is not NULL * then skb should also be non-NULL. * * Apparently *ppt_prev assignment above holds this invariant due to * skb dereferencing near it. */ *pskb = skb; return ret; } static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; int ret; ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); return ret; } /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb_core(struct sk_buff *skb) { int ret; rcu_read_lock(); ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); static inline void __netif_receive_skb_list_ptype(struct list_head *head, struct packet_type *pt_prev, struct net_device *orig_dev) { struct sk_buff *skb, *next; if (!pt_prev) return; if (list_empty(head)) return; if (pt_prev->list_func != NULL) INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) { /* Fast-path assumptions: * - There is no RX handler. * - Only one packet_type matches. * If either of these fails, we will end up doing some per-packet * processing in-line, then handling the 'last ptype' for the whole * sublist. This can't cause out-of-order delivery to any single ptype, * because the 'last ptype' must be constant across the sublist, and all * other ptypes are handled per-packet. */ /* Current (common) ptype of sublist */ struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; struct list_head sublist; struct sk_buff *skb, *next; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; skb_list_del_init(skb); __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { /* dispatch old sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); /* start new sublist */ INIT_LIST_HEAD(&sublist); pt_curr = pt_prev; od_curr = orig_dev; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); } static int __netif_receive_skb(struct sk_buff *skb) { int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should * - be delivered to SOCK_MEMALLOC sockets only * - stay away from userspace * - have bounded memory usage * * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_one_core(skb, false); return ret; } static void __netif_receive_skb_list(struct list_head *head) { unsigned long noreclaim_flag = 0; struct sk_buff *skb, *next; bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ list_for_each_entry_safe(skb, next, head, list) { if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { struct list_head sublist; /* Handle the previous sublist */ list_cut_before(&sublist, head, &skb->list); if (!list_empty(&sublist)) __netif_receive_skb_list_core(&sublist, pfmemalloc); pfmemalloc = !pfmemalloc; /* See comments in __netif_receive_skb */ if (pfmemalloc) noreclaim_flag = memalloc_noreclaim_save(); else memalloc_noreclaim_restore(noreclaim_flag); } } /* Handle the remaining sublist */ if (!list_empty(head)) __netif_receive_skb_list_core(head, pfmemalloc); /* Restore pflags */ if (pfmemalloc) memalloc_noreclaim_restore(noreclaim_flag); } static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); if (old && !new) { static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); dev_disable_lro(dev); dev_disable_gro_hw(dev); } break; default: ret = -EINVAL; break; } return ret; } static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } } #endif ret = __netif_receive_skb(skb); rcu_read_unlock(); return ret; } void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } list_splice_init(&sublist, head); rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { /* Will be handled, remove from list */ skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } } #endif __netif_receive_skb_list(head); rcu_read_unlock(); } /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process * * netif_receive_skb() is the main receive data processing function. * It always succeeds. The buffer may be dropped during processing * for congestion control or by the protocol layers. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb(struct sk_buff *skb) { int ret; trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret); return ret; } EXPORT_SYMBOL(netif_receive_skb); /** * netif_receive_skb_list - process many receive buffers from network * @head: list of skbs to process. * * Since return value of netif_receive_skb() is normally ignored, and * wouldn't be meaningful for a list, this function returns void. * * This function may only be called from softirq context and interrupts * should be enabled. */ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb; if (list_empty(head)) return; if (trace_netif_receive_skb_list_entry_enabled()) { list_for_each_entry(skb, head, list) trace_netif_receive_skb_list_entry(skb); } netif_receive_skb_list_internal(head); trace_netif_receive_skb_list_exit(0); } EXPORT_SYMBOL(netif_receive_skb_list); static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct softnet_data *sd; local_bh_disable(); sd = this_cpu_ptr(&softnet_data); backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(skb); rps_input_queue_head_incr(sd); } } backlog_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); rps_input_queue_head_incr(sd); } } local_bh_enable(); } static bool flush_required(int cpu) { #if IS_ENABLED(CONFIG_RPS) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); backlog_unlock_irq_enable(sd); return do_flush; #endif /* without RPS we can't safely check input_pkt_queue: during a * concurrent remote skb_queue_splice() we can detect as empty both * input_pkt_queue and process_queue even if the latter could end-up * containing a lot of packets. */ return true; } static void flush_all_backlogs(void) { static cpumask_t flush_cpus; unsigned int cpu; /* since we are under rtnl lock protection we can use static data * for the cpumask and avoid allocating on stack the possibly * large mask */ ASSERT_RTNL(); cpus_read_lock(); cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { queue_work_on(cpu, system_highpri_wq, per_cpu_ptr(&flush_works, cpu)); cpumask_set_cpu(cpu, &flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); cpus_read_unlock(); } static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS while (remsd) { struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) smp_call_function_single_async(remsd->cpu, &remsd->csd); remsd = next; } #endif } /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) { #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif } static int process_backlog(struct napi_struct *napi, int quota) { struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); bool again = true; int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. */ if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sd->process_queue))) { rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); if (++work >= quota) { rps_input_queue_head_add(sd, work); return work; } } backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, * and NAPI_STATE_SCHED is the only possible flag set * on backlog. * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ napi->state &= NAPIF_STATE_THREADED; again = false; } else { skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } backlog_unlock_irq_enable(sd); } if (work) rps_input_queue_head_add(sd, work); return work; } /** * __napi_schedule - schedule for receive * @n: entry to schedule * * The entry's receive function will be scheduled to run. * Consider using __napi_schedule_irqoff() if hard irqs are masked. */ void __napi_schedule(struct napi_struct *n) { unsigned long flags; local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ bool napi_schedule_prep(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); do { if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; /* Sets STATE_MISSED bit if STATE_SCHED was already set * This was suggested by Alexander Duyck, as compiler * emits better code than : * if (val & NAPIF_STATE_SCHED) * new |= NAPIF_STATE_MISSED; */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } EXPORT_SYMBOL(napi_schedule_prep); /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * * Variant of __napi_schedule() assuming hard irqs are masked. * * On PREEMPT_RT enabled kernels this maps to __napi_schedule() * because the interrupt disabled assumption might not be true * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ____napi_schedule(this_cpu_ptr(&softnet_data), n); else __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags, val, new, timeout = 0; bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list * just in case its running on a different cpu. * 2) If we are busy polling, do nothing here, we have * the guarantee we will be called later. */ if (unlikely(n->state & (NAPIF_STATE_NPSVC | NAPIF_STATE_IN_BUSY_POLL))) return false; if (work_done) { if (n->gro_bitmask) timeout = READ_ONCE(n->dev->gro_flush_timeout); n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = READ_ONCE(n->dev->gro_flush_timeout); if (timeout) ret = false; } if (n->gro_bitmask) { /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); } gro_normal_list(n); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); list_del_init(&n->poll_list); local_irq_restore(flags); } WRITE_ONCE(n->list_owner, -1); val = READ_ONCE(n->state); do { WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. * This C code was suggested by Alexander Duyck to help gcc. */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); return false; } if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); return ret; } EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) if (napi->napi_id == napi_id) return napi; return NULL; } static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ if (!READ_ONCE(sd->defer_list)) return; spin_lock(&sd->defer_lock); skb = sd->defer_list; sd->defer_list = NULL; sd->defer_count = 0; spin_unlock(&sd->defer_lock); while (skb != NULL) { next = skb->next; napi_consume_skb(skb, 1); skb = next; } } #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { gro_normal_list(napi); __napi_schedule(napi); return; } if (napi->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(napi, HZ >= 1000); } gro_normal_list(napi); clear_bit(NAPI_STATE_SCHED, &napi->state); } enum { NAPI_F_PREFER_BUSY_POLL = 1, NAPI_F_END_ON_RESCHED = 2, }; static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { bool skip_schedule = false; unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). * Since we are about to call napi->poll() once more, we can safely * clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit() */ clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); timeout = READ_ONCE(napi->dev->gro_flush_timeout); if (napi->defer_hard_irqs_count && timeout) { hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); skip_schedule = true; } } /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); local_bh_enable(); } static void __napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, unsigned flags, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); void *have_poll_lock = NULL; struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); restart: napi_poll = NULL; napi = napi_by_id(napi_id); if (!napi) return; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); for (;;) { int work = 0; local_bh_disable(); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); /* If multiple threads are competing for this napi, * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | NAPIF_STATE_IN_BUSY_POLL)) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | NAPIF_STATE_SCHED) != val) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(this_cpu_ptr(&softnet_data)); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { if (flags & NAPI_F_END_ON_RESCHED) break; if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); if (loop_end(loop_end_arg, start_time)) return; goto restart; } cpu_relax(); } if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = NAPI_F_END_ON_RESCHED; if (prefer_busy_poll) flags |= NAPI_F_PREFER_BUSY_POLL; __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0; rcu_read_lock(); __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); rcu_read_unlock(); } EXPORT_SYMBOL(napi_busy_loop); #endif /* CONFIG_NET_RX_BUSY_POLL */ static void napi_hash_add(struct napi_struct *napi) { if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(++napi_gen_id < MIN_NAPI_ID)) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); napi->napi_id = napi_gen_id; hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); spin_unlock(&napi_hash_lock); } /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ static void napi_hash_del(struct napi_struct *napi) { spin_lock(&napi_hash_lock); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock(&napi_hash_lock); } static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); } return HRTIMER_NORESTART; } static void init_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { INIT_LIST_HEAD(&napi->gro_hash[i].list); napi->gro_hash[i].count = 0; } napi->gro_bitmask = 0; } int dev_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; int err = 0; if (dev->threaded == threaded) return 0; if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = false; break; } } } } WRITE_ONCE(dev->threaded, threaded); /* Make sure kthread is created before THREADED bit * is set. */ smp_mb__before_atomic(); /* Setting/unsetting threaded mode on a napi might not immediately * take effect, if the current napi instance is actively being * polled. In this case, the switch between threaded mode and * softirq mode will happen in the next round of napi_schedule(). * This should not cause hiccups/stalls to the live traffic. */ list_for_each_entry(napi, &dev->napi_list, dev_list) assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); return err; } EXPORT_SYMBOL(dev_set_threaded); /** * netif_queue_set_napi - Associate queue with the napi * @dev: device to which NAPI and queue belong * @queue_index: Index of queue * @type: queue type as RX or TX * @napi: NAPI context, pass NULL to clear previously set NAPI * * Set queue with its corresponding napi context. This should be done after * registering the NAPI handler for the queue-vector and the queues have been * mapped to the corresponding interrupt vector. */ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi) { struct netdev_rx_queue *rxq; struct netdev_queue *txq; if (WARN_ON_ONCE(napi && !napi->dev)) return; if (dev->reg_state >= NETREG_REGISTERED) ASSERT_RTNL(); switch (type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(dev, queue_index); rxq->napi = napi; return; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(dev, queue_index); txq->napi = napi; return; default: return; } } EXPORT_SYMBOL(netif_queue_set_napi); void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif napi->list_owner = -1; set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = false; netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { unsigned long val, new; might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); do { while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); /** * napi_enable - enable NAPI scheduling * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ void napi_enable(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); do { BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable); static void flush_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { struct sk_buff *skb, *n; list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) kfree_skb(skb); napi->gro_hash[i].count = 0; } } /* Must be called in process context */ void __netif_napi_del(struct napi_struct *napi) { if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; napi_hash_del(napi); list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del); static int __napi_poll(struct napi_struct *n, bool *repoll) { int work, weight; weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); xdp_do_check_flushed(n); } if (unlikely(work > weight)) netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", n->poll, work, weight); if (likely(work < weight)) return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code * still "owns" the NAPI instance and therefore can * move the instance around on the list at-will. */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); return work; } /* The NAPI context has more processing work, but busy-polling * is preferred. Exit early. */ if (napi_prefer_busy_poll(n)) { if (napi_complete_done(n, work)) { /* If timeout is not set, we need to make sure * that the NAPI is re-scheduled. */ napi_schedule(n); } return work; } if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(n, HZ >= 1000); } gro_normal_list(n); /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); return work; } *repoll = true; return work; } static int napi_poll(struct napi_struct *n, struct list_head *repoll) { bool do_repoll = false; void *have; int work; list_del_init(&n->poll_list); have = netpoll_poll_lock(n); work = __napi_poll(n, &do_repoll); if (do_repoll) list_add_tail(&n->poll_list, repoll); netpoll_poll_unlock(have); return work; } static int napi_thread_wait(struct napi_struct *napi) { set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { /* Testing SCHED_THREADED bit here to make sure the current * kthread owns this napi and could poll on this napi. * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return -1; } static void napi_threaded_poll_loop(struct napi_struct *napi) { struct softnet_data *sd; unsigned long last_qs = jiffies; for (;;) { bool repoll = false; void *have; local_bh_disable(); sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; have = netpoll_poll_lock(napi); __napi_poll(napi, &repoll); netpoll_poll_unlock(have); sd->in_napi_threaded_poll = false; barrier(); if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(sd); local_bh_enable(); if (!repoll) break; rcu_softirq_qs_periodic(last_qs); cond_resched(); } } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; while (!napi_thread_wait(napi)) napi_threaded_poll_loop(napi); return 0; } static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); start: sd->in_net_rx_action = true; local_irq_disable(); list_splice_init(&sd->poll_list, &list); local_irq_enable(); for (;;) { struct napi_struct *n; skb_defer_free_flush(sd); if (list_empty(&list)) { if (list_empty(&repoll)) { sd->in_net_rx_action = false; barrier(); /* We need to check if ____napi_schedule() * had refilled poll_list while * sd->in_net_rx_action was true. */ if (!list_empty(&sd->poll_list)) goto start; if (!sd_has_rps_ipi_waiting(sd)) goto end; } break; } n = list_first_entry(&list, struct napi_struct, poll_list); budget -= napi_poll(n, &repoll); /* If softirq window is exhausted then punt. * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) { sd->time_squeeze++; break; } } local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) __raise_softirq_irqoff(NET_RX_SOFTIRQ); else sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); end:; } struct netdev_adjacent { struct net_device *dev; netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; /* lookup ignore flag */ bool ignore; /* counter for the number of times this device was added to us */ u16 ref_nr; /* private field for the users */ void *private; struct list_head list; struct rcu_head rcu; }; static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; list_for_each_entry(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } static int ____netdev_has_upper_dev(struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks only immediate upper device, * not through a complete stack of devices. The caller must hold the RTNL lock. */ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks the entire upper device chain. * The caller must hold rcu lock. */ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); /** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RTNL lock. */ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get); static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master) && !upper->ignore) return upper->dev; return NULL; } /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to a lower device and return true in case * it is. The caller must hold the RTNL lock. */ static bool netdev_has_any_lower_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.lower); } void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; adj = list_entry(adj_list, struct netdev_adjacent, list); return adj->private; } EXPORT_SYMBOL(netdev_adjacent_get_private); /** * netdev_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); static struct net_device *__netdev_next_upper_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *upper; upper = list_entry((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; *ignore = upper->ignore; return upper->dev; } static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; if (ignore) continue; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = netdev_next_upper_dev_rcu(now, &iter); if (!udev) break; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = 0, .data = (void *)upper_dev, }; ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, &priv); } /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private); /** * netdev_lower_get_next_private_rcu - Get the next ->private from the * lower neighbour list, RCU * variant * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold RCU read lock. */ void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_lower_get_next - Get the next device from the lower neighbour * list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->dev; } EXPORT_SYMBOL(netdev_lower_get_next); static struct net_device *netdev_next_lower_dev(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } static struct net_device *__netdev_next_lower_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; *ignore = lower->ignore; return lower->dev; } int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = __netdev_next_lower_dev(now, &iter, &ignore); if (!ldev) break; if (ignore) continue; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { struct net_device *udev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.upper, udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } return max_depth; } static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.lower, ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } return max_depth; } static int __netdev_update_upper_level(struct net_device *dev, struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; #ifdef CONFIG_LOCKDEP if (!priv) return 0; if (priv->flags & NESTED_SYNC_IMM) dev->nested_level = dev->lower_level - 1; if (priv->flags & NESTED_SYNC_TODO) net_unlink_todo(dev); #endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant * @dev: device * * Gets the first netdev_adjacent->private from the dev's lower neighbour * list. The caller must hold RCU read lock. */ void *netdev_lower_get_first_private_rcu(struct net_device *dev) { struct netdev_adjacent *lower; lower = list_first_or_null_rcu(&dev->adj_list.lower, struct netdev_adjacent, list); if (lower) return lower->private; return NULL; } EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RCU read lock. */ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); } static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { return (dev_list == &dev->adj_list.upper || dev_list == &dev->adj_list.lower) && net_eq(dev_net(dev), dev_net(adj_dev)); } static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; int ret; adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr += 1; pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", dev->name, adj_dev->name, adj->ref_nr); return 0; } adj = kmalloc(sizeof(*adj), GFP_KERNEL); if (!adj) return -ENOMEM; adj->dev = adj_dev; adj->master = master; adj->ref_nr = 1; adj->private = private; adj->ignore = false; netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } /* Ensure that master link is always the first item in list. */ if (master) { ret = sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), "master"); if (ret) goto remove_symlinks; list_add_rcu(&adj->list, dev_list); } else { list_add_tail_rcu(&adj->list, dev_list); } return 0; remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; } static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", dev->name, adj_dev->name, ref_nr); adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); WARN_ON(1); return; } if (adj->ref_nr > ref_nr) { pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", dev->name, adj_dev->name, ref_nr, adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, .extack = extack, }, .upper_dev = upper_dev, .master = master, .linking = true, .upper_info = upper_info, }; struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); if (dev == upper_dev) return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) return ret; ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) goto rollback; __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); return 0; rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } /** * netdev_upper_dev_link - Add a link to the upper device * @dev: device * @upper_dev: new upper device * @extack: netlink extended ack * * Adds a link to device which is upper to this one. The caller must hold * the RTNL lock. On a failure a negative errno code is returned. * On success the reference counts are adjusted and the function * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); /** * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device * @upper_priv: upper device private * @upper_info: upper info to be passed down via notifier * @extack: netlink extended ack * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices * might be linked as well. The caller must hold the RTNL lock. * On a failure a negative errno code is returned. On success the reference * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, true, upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); static void __netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, }, .upper_dev = upper_dev, .linking = false, }; ASSERT_RTNL(); changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); } /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device * @upper_dev: new upper device * * Removes a link to device which is upper to this one. The caller must hold * the RTNL lock. */ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_TODO, .data = NULL, }; __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); static void __netdev_adjacent_dev_set(struct net_device *upper_dev, struct net_device *lower_dev, bool val) { struct netdev_adjacent *adj; adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); if (adj) adj->ignore = val; adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); if (adj) adj->ignore = val; } static void netdev_adjacent_dev_disable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, true); } static void netdev_adjacent_dev_enable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, false); } int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; int err; if (!new_dev) return 0; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); return err; } return 0; } EXPORT_SYMBOL(netdev_adjacent_change_prepare); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; if (!new_dev || !old_dev) return; if (new_dev == old_dev) return; netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { struct netdev_notifier_bonding_info info = { .info.dev = dev, }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); static int netdev_offload_xstats_enable_l3(struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; int err; int rc; dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), GFP_KERNEL); if (!dev->offload_xstats_l3) return -ENOMEM; rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); err = notifier_to_errno(rc); if (err) goto free_stats; return 0; free_stats: kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; return err; } int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return netdev_offload_xstats_enable_l3(dev, extack); } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_enable); static void netdev_offload_xstats_disable_l3(struct net_device *dev) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; } int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); if (!netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: netdev_offload_xstats_disable_l3(dev); return 0; } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_disable); static void netdev_offload_xstats_disable_all(struct net_device *dev) { netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); } static struct rtnl_hw_stats64 * netdev_offload_xstats_get_ptr(const struct net_device *dev, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return dev->offload_xstats_l3; } WARN_ON(1); return NULL; } bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); return netdev_offload_xstats_get_ptr(dev, type); } EXPORT_SYMBOL(netdev_offload_xstats_enabled); struct netdev_notifier_offload_xstats_ru { bool used; }; struct netdev_notifier_offload_xstats_rd { struct rtnl_hw_stats64 stats; bool used; }; static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, const struct rtnl_hw_stats64 *src) { dest->rx_packets += src->rx_packets; dest->tx_packets += src->tx_packets; dest->rx_bytes += src->rx_bytes; dest->tx_bytes += src->tx_bytes; dest->rx_errors += src->rx_errors; dest->tx_errors += src->tx_errors; dest->rx_dropped += src->rx_dropped; dest->tx_dropped += src->tx_dropped; dest->multicast += src->multicast; } static int netdev_offload_xstats_get_used(struct net_device *dev, enum netdev_offload_xstats_type type, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_ru report_used = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_used = &report_used, }; int rc; WARN_ON(!netdev_offload_xstats_enabled(dev, type)); rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, &info.info); *p_used = report_used.used; return notifier_to_errno(rc); } static int netdev_offload_xstats_get_stats(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_rd report_delta = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_delta = &report_delta, }; struct rtnl_hw_stats64 *stats; int rc; stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return -EINVAL; rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, &info.info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ netdev_hw_stats64_add(stats, &report_delta.stats); if (p_stats) *p_stats = *stats; *p_used = report_delta.used; return notifier_to_errno(rc); } int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (p_stats) return netdev_offload_xstats_get_stats(dev, type, p_stats, p_used, extack); else return netdev_offload_xstats_get_used(dev, type, p_used, extack); } EXPORT_SYMBOL(netdev_offload_xstats_get); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, const struct rtnl_hw_stats64 *stats) { report_delta->used = true; netdev_hw_stats64_add(&report_delta->stats, stats); } EXPORT_SYMBOL(netdev_offload_xstats_report_delta); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) { report_used->used = true; } EXPORT_SYMBOL(netdev_offload_xstats_report_used); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *p_stats) { struct rtnl_hw_stats64 *stats; ASSERT_RTNL(); stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return; netdev_hw_stats64_add(stats, p_stats); } EXPORT_SYMBOL(netdev_offload_xstats_push_delta); /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. * %NULL is returned if no slave is found. */ struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_xmit_slave) return NULL; return ops->ndo_get_xmit_slave(dev, skb, all_slaves); } EXPORT_SYMBOL(netdev_get_xmit_slave); static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_sk_get_lower_dev) return NULL; return ops->ndo_sk_get_lower_dev(dev, sk); } /** * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket * @dev: device * @sk: the socket * * %NULL is returned if no lower device is found. */ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk) { struct net_device *lower; lower = netdev_sk_get_lower_dev(dev, sk); while (lower) { dev = lower; lower = netdev_sk_get_lower_dev(dev, sk); } return dev; } EXPORT_SYMBOL(netdev_sk_get_lowest_dev); static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.lower); } } static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.lower); } } void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); } } void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { struct netdev_adjacent *lower; if (!lower_dev) return NULL; lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; return lower->private; } EXPORT_SYMBOL(netdev_lower_dev_get_private); /** * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { struct netdev_notifier_changelowerstate_info changelowerstate_info = { .info.dev = lower_dev, }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; unsigned int promiscuity, flags; kuid_t uid; kgid_t gid; ASSERT_RTNL(); promiscuity = dev->promiscuity + inc; if (promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_PROMISC; } else { flags = old_flags | IFF_PROMISC; } WRITE_ONCE(dev->promiscuity, promiscuity); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s promiscuous mode\n", dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(audit_context(), GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, uid), from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } /** * dev_set_promiscuity - update promiscuity count on a device * @dev: device * @inc: modifier * * Add or remove promiscuity from a device. While the count in the device * remains above zero the interface remains promiscuous. Once it hits zero * the device reverts back to normal filtering operation. A negative inc * value is used to drop promiscuity on the device. * Return 0 if successful or a negative errno code on error. */ int dev_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) dev_set_rx_mode(dev); return err; } EXPORT_SYMBOL(dev_set_promiscuity); static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; unsigned int allmulti, flags; ASSERT_RTNL(); allmulti = dev->allmulti + inc; if (allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_ALLMULTI; } else { flags = old_flags | IFF_ALLMULTI; } WRITE_ONCE(dev->allmulti, allmulti); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s allmulticast mode\n", dev->flags & IFF_ALLMULTI ? "entered" : "left"); dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, dev->gflags ^ old_gflags, 0, NULL); } return 0; } /** * dev_set_allmulti - update allmulti count on a device * @dev: device * @inc: modifier * * Add or remove reception of all multicast frames to a device. While the * count in the device remains above zero the interface remains listening * to all interfaces. Once it hits zero the device reverts back to normal * filtering operation. A negative @inc value is used to drop the counter * when releasing a resource needing all multicasts. * Return 0 if successful or a negative errno code on error. */ int dev_set_allmulti(struct net_device *dev, int inc) { return __dev_set_allmulti(dev, inc, true); } EXPORT_SYMBOL(dev_set_allmulti); /* * Upload unicast and multicast address lists to device and * configure RX filtering. When the device doesn't support unicast * filtering it is put in promiscuous mode while unicast addresses * are present. */ void __dev_set_rx_mode(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; /* dev_open will call this function so the list will stay sane. */ if (!(dev->flags&IFF_UP)) return; if (!netif_device_present(dev)) return; if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1, false); dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1, false); dev->uc_promisc = false; } } if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) { netif_addr_lock_bh(dev); __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); } /** * dev_get_flags - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int dev_get_flags(const struct net_device *dev) { unsigned int flags; flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { if (netif_oper_up(dev)) flags |= IFF_RUNNING; if (netif_carrier_ok(dev)) flags |= IFF_LOWER_UP; if (netif_dormant(dev)) flags |= IFF_DORMANT; } return flags; } EXPORT_SYMBOL(dev_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { unsigned int old_flags = dev->flags; int ret; ASSERT_RTNL(); /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP | IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL | IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC | IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ if ((old_flags ^ flags) & IFF_MULTICAST) dev_change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags ^ flags) & IFF_UP) { if (old_flags & IFF_UP) __dev_close(dev); else ret = __dev_open(dev, extack); } if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; unsigned int old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; if (__dev_set_promiscuity(dev, inc, false) >= 0) if (dev->flags != old_flags) dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI * is important. Some (broken) drivers set IFF_PROMISC, when * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; __dev_set_allmulti(dev, inc, false); } return ret; } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); else call_netdevice_notifiers(NETDEV_DOWN, dev); } if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { struct netdev_notifier_change_info change_info = { .info = { .dev = dev, }, .flags_changed = changes, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } /** * dev_change_flags - change device settings * @dev: device * @flags: device state flags * @extack: netlink extended ack * * Change settings on device based state flags. The flags are * in the userspace exported format. */ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags, extack); if (ret < 0) return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } EXPORT_SYMBOL(dev_change_flags); int __dev_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); /* Pairs with all the lockless reads of dev->mtu in the stack */ WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } return 0; } /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; if (new_mtu == dev->mtu) return 0; err = dev_validate_mtu(dev, new_mtu, extack); if (err) return err; if (!netif_device_present(dev)) return -ENODEV; err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); err = notifier_to_errno(err); if (err) return err; orig_mtu = dev->mtu; err = __dev_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int dev_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = dev_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } EXPORT_SYMBOL(dev_set_mtu); /** * dev_change_tx_queue_len - Change TX queue length of a netdevice * @dev: device * @new_len: new tx queue length */ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; if (new_len != (unsigned int)new_len) return -ERANGE; if (new_len != orig_len) { WRITE_ONCE(dev->tx_queue_len, new_len); res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) goto err_rollback; res = dev_qdisc_change_tx_queue_len(dev); if (res) goto err_rollback; } return 0; err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); WRITE_ONCE(dev->tx_queue_len, orig_len); return res; } /** * dev_set_group - Change group this device belongs to * @dev: device * @new_group: group this device should belong to */ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack */ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, .info.extack = extack, .dev_addr = addr, }; int rc; rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } EXPORT_SYMBOL(dev_pre_changeaddr_notify); /** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address * @extack: netlink extended ack * * Change the hardware (MAC) address of the device */ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (sa->sa_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack); if (err) return err; if (memcmp(dev->dev_addr, sa->sa_data, dev->addr_len)) { err = ops->ndo_set_mac_address(dev, sa); if (err) return err; } dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } EXPORT_SYMBOL(dev_set_mac_address); DECLARE_RWSEM(dev_addr_sem); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { int ret; down_write(&dev_addr_sem); ret = dev_set_mac_address(dev, sa, extack); up_write(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; down_read(&dev_addr_sem); rcu_read_lock(); dev = dev_get_by_name_rcu(net, dev_name); if (!dev) { ret = -ENODEV; goto unlock; } if (!dev->addr_len) memset(sa->sa_data, 0, size); else memcpy(sa->sa_data, dev->dev_addr, min_t(size_t, size, dev->addr_len)); sa->sa_family = dev->type; unlock: rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_get_mac_address); /** * dev_change_carrier - Change device carrier * @dev: device * @new_carrier: new value * * Change device carrier */ int dev_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_change_carrier) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } /** * dev_get_phys_port_id - Get device physical port ID * @dev: device * @ppid: port ID * * Get device physical port ID */ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_phys_port_id) return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } /** * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name * @len: limit of bytes to copy to name * * Get device physical port name */ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (ops->ndo_get_phys_port_name) { err = ops->ndo_get_phys_port_name(dev, name, len); if (err != -EOPNOTSUPP) return err; } return devlink_compat_phys_port_name_get(dev, name, len); } /** * dev_get_port_parent_id - Get the device's port parent identifier * @dev: network device * @ppid: pointer to a storage for the port's parent identifier * @recurse: allow/disallow recursion to lower devices * * Get the devices's port parent identifier */ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; int err; if (ops->ndo_get_port_parent_id) { err = ops->ndo_get_port_parent_id(dev, ppid); if (err != -EOPNOTSUPP) return err; } err = devlink_compat_switch_id_get(dev, ppid); if (!recurse || err != -EOPNOTSUPP) return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) return -EOPNOTSUPP; } return err; } EXPORT_SYMBOL(dev_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have * the same port parent identifier * @a: first network device * @b: second network device */ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; if (dev_get_port_parent_id(a, &a_id, true) || dev_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); } EXPORT_SYMBOL(netdev_port_same_parent_id); /** * dev_change_proto_down - set carrier according to proto_down. * * @dev: device * @proto_down: new value */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; if (proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); WRITE_ONCE(dev->proto_down, proto_down); return 0; } /** * dev_change_proto_down_reason - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value) { u32 proto_down_reason; int b; if (!mask) { proto_down_reason = value; } else { proto_down_reason = dev->proto_down_reason; for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) proto_down_reason |= BIT(b); else proto_down_reason &= ~BIT(b); } } WRITE_ONCE(dev->proto_down_reason, proto_down_reason); } struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ int flags; }; static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; if (flags & XDP_FLAGS_SKB_MODE) return XDP_MODE_SKB; return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) { switch (mode) { case XDP_MODE_SKB: return generic_xdp_install; case XDP_MODE_DRV: case XDP_MODE_HW: return dev->netdev_ops->ndo_bpf; default: return NULL; } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, enum bpf_xdp_mode mode) { return dev->xdp_state[mode].link; } static struct bpf_prog *dev_xdp_prog(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_xdp_link *link = dev_xdp_link(dev, mode); if (link) return link->link.prog; return dev->xdp_state[mode].prog; } u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog || dev->xdp_state[i].link) count++; return count; } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); return prog ? prog->aux->id : 0; } static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_xdp_link *link) { dev->xdp_state[mode].link = link; dev->xdp_state[mode].prog = NULL; } static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_prog *prog) { dev->xdp_state[mode].link = NULL; dev->xdp_state[mode].prog = prog; } static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_bpf xdp; int err; memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; /* Drivers assume refcnt is already incremented (i.e, prog pointer is * "moved" into driver), so they don't increment it on their own, but * they do decrement refcnt when program is detached or replaced. * Given net_device also owns link/prog, we need to bump refcnt here * to prevent drivers from underflowing it. */ if (prog) bpf_prog_inc(prog); err = bpf_op(dev, &xdp); if (err) { if (prog) bpf_prog_put(prog); return err; } if (mode != XDP_MODE_HW) bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); return 0; } static void dev_xdp_uninstall(struct net_device *dev) { struct bpf_xdp_link *link; struct bpf_prog *prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { prog = dev_xdp_prog(dev, mode); if (!prog) continue; bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) continue; WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); /* auto-detach link from net device */ link = dev_xdp_link(dev, mode); if (link) link->dev = NULL; else bpf_prog_put(prog); dev_xdp_set_link(dev, mode, NULL); } } static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; struct net_device *upper; struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; ASSERT_RTNL(); /* either link or prog attachment, never both */ if (link && (new_prog || old_prog)) return -EINVAL; /* link supports only XDP mode flags */ if (link && (flags & ~XDP_FLAGS_MODES)) { NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ if (!num_modes && dev_xdp_prog_count(dev) > 1) { NL_SET_ERR_MSG(extack, "More than one program loaded, unset mode is ambiguous"); return -EINVAL; } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); return -EINVAL; } mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); return -EBUSY; } /* don't allow if an upper device already has a program */ netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (dev_xdp_prog_count(upper) > 0) { NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } } cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); return -EBUSY; } if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } /* put effective new program into new_prog */ if (link) new_prog = link->link.prog; if (new_prog) { bool offload = mode == XDP_MODE_HW; enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; } if (!offload && bpf_prog_is_offloaded(new_prog->aux)) { NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) { NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } } /* don't call drivers if the effective program didn't change */ if (new_prog != cur_prog) { bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) { NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; } err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); if (err) return err; } if (link) dev_xdp_set_link(dev, mode, link); else dev_xdp_set_prog(dev, mode, new_prog); if (cur_prog) bpf_prog_put(cur_prog); return 0; } static int dev_xdp_attach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); } static int dev_xdp_detach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; bpf_op = dev_xdp_bpf_op(dev, mode); WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); dev_xdp_set_link(dev, mode, NULL); return 0; } static void bpf_xdp_link_release(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); rtnl_lock(); /* if racing with net_device's tear down, xdp_link->dev might be * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); xdp_link->dev = NULL; } rtnl_unlock(); } static int bpf_xdp_link_detach(struct bpf_link *link) { bpf_xdp_link_release(link); return 0; } static void bpf_xdp_link_dealloc(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); kfree(xdp_link); } static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); } static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); info->xdp.ifindex = ifindex; return 0; } static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err = 0; rtnl_lock(); /* link might have been auto-released already, so fail */ if (!xdp_link->dev) { err = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { err = -EPERM; goto out_unlock; } old_prog = link->prog; if (old_prog->type != new_prog->type || old_prog->expected_attach_type != new_prog->expected_attach_type) { err = -EINVAL; goto out_unlock; } if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); goto out_unlock; } mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); if (err) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: rtnl_unlock(); return err; } static const struct bpf_link_ops bpf_xdp_link_lops = { .release = bpf_xdp_link_release, .dealloc = bpf_xdp_link_dealloc, .detach = bpf_xdp_link_detach, .show_fdinfo = bpf_xdp_link_show_fdinfo, .fill_link_info = bpf_xdp_link_fill_link_info, .update_prog = bpf_xdp_link_update, }; int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct netlink_ext_ack extack = {}; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { rtnl_unlock(); return -EINVAL; } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } err = dev_xdp_attach_link(dev, &extack, link); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); trace_bpf_xdp_link_attach_failed(extack._msg); goto out_put_dev; } fd = bpf_link_settle(&link_primer); /* link itself doesn't hold dev's refcnt to not complicate shutdown */ dev_put(dev); return fd; unlock: rtnl_unlock(); out_put_dev: dev_put(dev); return err; } /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; ASSERT_RTNL(); if (fd >= 0) { new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(new_prog)) return PTR_ERR(new_prog); } if (expected_fd >= 0) { old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(old_prog)) { err = PTR_ERR(old_prog); old_prog = NULL; goto err_out; } } err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); err_out: if (err && new_prog) bpf_prog_put(new_prog); if (old_prog) bpf_prog_put(old_prog); return err; } /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace * @ifindex: requested ifindex, pass %0 to get one allocated * * Allocate a ifindex for a new device. Caller must either use the ifindex * to store the device (via list_netdevice()) or call dev_index_release() * to give the index up. * * Return: a suitable unique value for a new device interface number or -errno. */ static int dev_index_reserve(struct net *net, u32 ifindex) { int err; if (ifindex > INT_MAX) { DEBUG_NET_WARN_ON_ONCE(1); return -EINVAL; } if (!ifindex) err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, xa_limit_31b, &net->ifindex, GFP_KERNEL); else err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL); if (err < 0) return err; return ifindex; } static void dev_index_release(struct net *net, int ifindex) { /* Expect only unused indexes, unlist_netdevice() removes the used */ WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", &feature, upper->name); features &= ~feature; } } return features; } static void netdev_sync_lower_features(struct net_device *upper, struct net_device *lower, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); else netdev_features_change(lower); } } } static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IP_CSUM)) { netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; features &= ~NETIF_F_TSO_ECN; } if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IPV6_CSUM)) { netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); features &= ~NETIF_F_TSO6; } /* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */ if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO)) features &= ~NETIF_F_TSO_MANGLEID; /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } /* GSO partial features require GSO partial be set */ if ((features & dev->gso_partial_features) && !(features & NETIF_F_GSO_PARTIAL)) { netdev_dbg(dev, "Dropping partially supported GSO features since no GSO partial.\n"); features &= ~dev->gso_partial_features; } if (!(features & NETIF_F_RXCSUM)) { /* NETIF_F_GRO_HW implies doing RXCSUM since every packet * successfully merged by hardware must also have the * checksum verified by hardware. If the user does not * want to enable RXCSUM, logically, we should disable GRO_HW. */ if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); features &= ~NETIF_F_GRO_HW; } } /* LRO/HW-GRO features cannot be combined with RX-FCS */ if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_GRO_HW; } } if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_HW_TLS_TX) { bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); bool hw_csum = features & NETIF_F_HW_CSUM; if (!ip_csum && !hw_csum) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); features &= ~NETIF_F_HW_TLS_TX; } } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); features &= ~NETIF_F_HW_TLS_RX; } return features; } int __netdev_update_features(struct net_device *dev) { struct net_device *upper, *lower; netdev_features_t features; struct list_head *iter; int err = -1; ASSERT_RTNL(); features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features); /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features) goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); else err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); /* return non-0 since some features might have changed and * it's better to fire a spurious notification than miss it */ return -1; } sync_lower: /* some features must be disabled on lower devices when disabled * on an upper device (think: bonding master or bridge) */ netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) { netdev_features_t diff = features ^ dev->features; if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) { /* udp_tunnel_{get,drop}_rx_info both need * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the * device, or they won't do anything. * Thus we need to update dev->features * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { dev->features = features; err |= vlan_get_rx_ctag_filter_info(dev); } else { vlan_drop_rx_ctag_filter_info(dev); } } if (diff & NETIF_F_HW_VLAN_STAG_FILTER) { if (features & NETIF_F_HW_VLAN_STAG_FILTER) { dev->features = features; err |= vlan_get_rx_stag_filter_info(dev); } else { vlan_drop_rx_stag_filter_info(dev); } } dev->features = features; } return err < 0 ? 0 : 1; } /** * netdev_update_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications if it * has changed. Should be called after driver or hardware dependent * conditions might have changed that influence the features. */ void netdev_update_features(struct net_device *dev) { if (__netdev_update_features(dev)) netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** * netdev_change_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications even * if they have not changed. Should be called instead of * netdev_update_features() if also dev->vlan_features might * have changed to allow the changes to be propagated to stacked * VLAN devices. */ void netdev_change_features(struct net_device *dev) { __netdev_update_features(dev); netdev_features_change(dev); } EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to * * Transfer operational state from root to device. This is normally * called when a stacking relationship exists between the root * device and the device(a leaf device). */ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev) { if (rootdev->operstate == IF_OPER_DORMANT) netif_dormant_on(dev); else netif_dormant_off(dev); if (rootdev->operstate == IF_OPER_TESTING) netif_testing_on(dev); else netif_testing_off(dev); if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else netif_carrier_off(dev); } EXPORT_SYMBOL(netif_stacked_transfer_operstate); static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); int err = 0; BUG_ON(count < 1); rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; dev->_rx = rx; for (i = 0; i < count; i++) { rx[i].dev = dev; /* XDP RX-queue setup */ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } return 0; err_rxq_info: /* Rollback successful reg's and free other resources */ while (i--) xdp_rxq_info_unreg(&rx[i].xdp_rxq); kvfree(dev->_rx); dev->_rx = NULL; return err; } static void netif_free_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ if (!dev->_rx) return; for (i = 0; i < count; i++) xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq); kvfree(dev->_rx); } static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL dql_init(&queue->dql, HZ); #endif } static void netif_free_tx_queues(struct net_device *dev) { kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; size_t sz = count * sizeof(*tx); if (count < 1 || count > 0xffff) return -EINVAL; tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); return 0; } void netif_tx_stop_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_stop_queue(txq); } } EXPORT_SYMBOL(netif_tx_stop_all_queues); static int netdev_do_alloc_pcpu_stats(struct net_device *dev) { void __percpu *v; /* Drivers implementing ndo_get_peer_dev must support tstat * accounting, so that skb_do_redirect() can bump the dev's * RX stats upon network namespace switch. */ if (dev->netdev_ops->ndo_get_peer_dev && dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) return -EOPNOTSUPP; switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return 0; case NETDEV_PCPU_STAT_LSTATS: v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); break; case NETDEV_PCPU_STAT_TSTATS: v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); break; case NETDEV_PCPU_STAT_DSTATS: v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); break; default: return -EINVAL; } return v ? 0 : -ENOMEM; } static void netdev_do_free_pcpu_stats(struct net_device *dev) { switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return; case NETDEV_PCPU_STAT_LSTATS: free_percpu(dev->lstats); break; case NETDEV_PCPU_STAT_TSTATS: free_percpu(dev->tstats); break; case NETDEV_PCPU_STAT_DSTATS: free_percpu(dev->dstats); break; } } /** * register_netdevice() - register a network device * @dev: device to register * * Take a prepared network device structure and make it externally accessible. * A %NETDEV_REGISTER message is sent to the netdev notifier chain. * Callers must hold the rtnl lock - you may want register_netdev() * instead of this. */ int register_netdevice(struct net_device *dev) { int ret; struct net *net = dev_net(dev); BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); might_sleep(); /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); ret = ethtool_check_ops(dev->ethtool_ops); if (ret) return ret; spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; ret = -ENOMEM; dev->name_node = netdev_name_node_head_alloc(dev); if (!dev->name_node) goto out; /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; goto err_free_name; } } if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; goto err_uninit; } ret = netdev_do_alloc_pcpu_stats(dev); if (ret) goto err_uninit; ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } dev->wanted_features = dev->features & dev->hw_features; if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; /* If IPv4 TCP segmentation offload is supported we should also * allow the device to enable segmenting the frame with the option * of ignoring a static IP ID value. This doesn't enable the * feature itself but allows the user to enable it later. */ if (dev->hw_features & NETIF_F_TSO) dev->hw_features |= NETIF_F_TSO_MANGLEID; if (dev->vlan_features & NETIF_F_TSO) dev->vlan_features |= NETIF_F_TSO_MANGLEID; if (dev->mpls_features & NETIF_F_TSO) dev->mpls_features |= NETIF_F_TSO_MANGLEID; if (dev->hw_enc_features & NETIF_F_TSO) dev->hw_enc_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ dev->vlan_features |= NETIF_F_HIGHDMA; /* Make NETIF_F_SG inheritable to tunnel devices. */ dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) goto err_ifindex_release; ret = netdev_register_kobject(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); if (ret) goto err_uninit_notify; __netdev_update_features(dev); /* * Default initial state at registry is that the * device is present. */ set_bit(__LINK_STATE_PRESENT, &dev->state); linkwatch_init_dev(dev); dev_init_scheduler(dev); netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should * set dev_addr and also addr_assign_type should be set to * NET_ADDR_PERM (default value). */ if (dev->addr_assign_type == NET_ADDR_PERM) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; unregister_netdevice_queue(dev, NULL); goto out; } /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); err_free_pcpu: netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); err_free_name: netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. * This is useful if you are calling this function after alloc_netdev(), * since it does not memset the net_device fields. */ static void init_dummy_netdev_core(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* napi_busy_loop stats accounting wants this */ dev_net_set(dev, &init_net); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } /** * init_dummy_netdev - init a dummy network device for NAPI * @dev: device to init * * This takes a network device structure and initializes the minimum * amount of fields so it can be used to schedule NAPI polls without * registering a full blown interface. This is to be used by drivers * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ void init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * as they aren't supposed to be taken by any of the * NAPI code and this dummy netdev is supposed to be * only ever used for NAPI polls */ memset(dev, 0, sizeof(struct net_device)); init_dummy_netdev_core(dev); } EXPORT_SYMBOL_GPL(init_dummy_netdev); /** * register_netdev - register a network device * @dev: device to register * * Take a completed network device structure and add it to the kernel * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ int register_netdev(struct net_device *dev) { int err; if (rtnl_lock_killable()) return -EINTR; err = register_netdevice(dev); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { #ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; #else return refcount_read(&dev->dev_refcnt); #endif } EXPORT_SYMBOL(netdev_refcnt_read); int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs_any - wait until all references are gone. * @list: list of net_devices to wait on * * This is called when unregistering network devices. * * Any protocol or device that holds a reference should register * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly * call dev_put. */ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; struct net_device *dev; int wait = 0; rebroadcast_time = warning_time = jiffies; list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); list_for_each_entry(dev, list, todo_list) if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events * pending on unregister. If this * happens, we simply run the queue * unscheduled, resulting in a noop * for this device. */ linkwatch_run_queue(); break; } __rtnl_unlock(); rebroadcast_time = jiffies; } rcu_barrier(); if (!wait) { wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; if (time_after(jiffies, warning_time + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); ref_tracker_dir_print(&dev->refcnt_tracker, 10); } warning_time = jiffies; } } } /* The sequence is: * * rtnl_lock(); * ... * register_netdevice(x1); * register_netdevice(x2); * ... * unregister_netdevice(y1); * unregister_netdevice(y2); * ... * rtnl_unlock(); * free_netdev(y1); * free_netdev(y2); * * We are invoked by rtnl_unlock(). * This allows us to deal with problems: * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. * * We must not return until all unregister events added during * the interval the lock was held have been completed. */ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { struct net_device *dev = list_first_entry(&unlink_list, struct net_device, unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list); continue; } WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); linkwatch_sync_dev(dev); } cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) wake_up(&netdev_unregistering_wq); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); } EXPORT_SYMBOL(netdev_stats_to_stats64); static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc( struct net_device *dev) { struct net_device_core_stats __percpu *p; p = alloc_percpu_gfp(struct net_device_core_stats, GFP_ATOMIC | __GFP_NOWARN); if (p && cmpxchg(&dev->core_stats, NULL, p)) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ return READ_ONCE(dev->core_stats); } noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); unsigned long __percpu *field; if (unlikely(!p)) { p = netdev_core_stats_alloc(dev); if (!p) return; } field = (__force unsigned long __percpu *)((__force void *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); /** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @storage: place to store stats * * Get network statistics from device. Return @storage. * The device driver may provide its own method by setting * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; * otherwise the internal statistics structure is used. */ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ p = READ_ONCE(dev->core_stats); if (p) { const struct net_device_core_stats *core_stats; int i; for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); } } return storage; } EXPORT_SYMBOL(dev_get_stats); /** * dev_fetch_sw_netstats - get per-cpu network device statistics * @s: place to store stats * @netstats: per-cpu network stats to read from * * Read per-cpu network statistics and populate the related fields in @s. */ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); /** * dev_get_tstats64 - ndo_get_stats64 implementation * @dev: device to get statistics from * @s: place to store stats * * Populate @s from dev->stats and dev->tstats. Can be used as * ndo_get_stats64() callback. */ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_sw_netstats(s, dev->tstats); } EXPORT_SYMBOL_GPL(dev_get_tstats64); struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); #ifdef CONFIG_NET_CLS_ACT if (queue) return queue; queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; } static const struct ethtool_ops default_ethtool_ops; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops) { if (dev->ethtool_ops == &default_ethtool_ops) dev->ethtool_ops = ops; } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); /** * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default * @dev: netdev to enable the IRQ coalescing on * * Sets a conservative default for SW IRQ coalescing. Users can use * sysfs attributes to override the default values. */ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) { WARN_ON(dev->reg_state == NETREG_REGISTERED); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { dev->gro_flush_timeout = 20000; dev->napi_defer_hard_irqs = 1; } } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); void netdev_freemem(struct net_device *dev) { char *addr = (char *)dev - dev->padded; kvfree(addr); } /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @name_assign_type: origin of device name * @setup: callback to initialize device * @txqs: the number of TX subqueues to allocate * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; unsigned int alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); alloc_size += sizeof_priv; } /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!p) return NULL; dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; ref_tracker_dir_init(&dev->refcnt_tracker, 128, name); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif if (dev_addr_init(dev)) goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->xdp_zc_max_segs = 1; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP dev->nested_level = 0; INIT_LIST_HEAD(&dev->unlink_list); #endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; strcpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; nf_hook_netdev_init(dev); return dev; free_all: free_netdev(dev); return NULL; free_pcpu: #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: #endif netdev_freemem(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device * @dev: device * * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. If this * is the last reference then it will be freed.Must be called in process * context. */ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; might_sleep(); /* When called immediately after register_netdevice() failed the unwind * handling may still be dismantling the device. Handle that case by * deferring the free. */ if (dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); dev->needs_free_netdev = true; return; } netif_free_tx_queues(dev); netif_free_rx_queues(dev); kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif free_percpu(dev->core_stats); dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { netdev_freemem(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); } EXPORT_SYMBOL(free_netdev); /** * alloc_netdev_dummy - Allocate and initialize a dummy net device. * @sizeof_priv: size of private data to allocate space for * * Return: the allocated net_device on success, NULL otherwise */ struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, init_dummy_netdev_core); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); /** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. * Does not block later packets from starting. */ void synchronize_net(void) { might_sleep(); if (rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); /** * unregister_netdevice_queue - remove device from the kernel * @dev: device * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); if (head) { list_move_tail(&dev->unreg_list, head); } else { LIST_HEAD(single); list_add(&dev->unreg_list, &single); unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); if (list_empty(head)) return; list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering * for initialization unwind. Remove those * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } /* If device is running, close it first. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ dev_shutdown(dev); dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); netdev_offload_xstats_disable_all(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, portid, nlh); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); #ifdef CONFIG_XPS /* Remove XPS queueing entries */ netif_reset_xps_queues_gt(dev, 0); #endif } synchronize_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); cnt++; } atomic_add(cnt, &dev_unreg_count); list_del(head); } /** * unregister_netdevice_many - unregister many devices * @head: list of devices * * Note: As most callers use a stack allocated list_head, * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { unregister_netdevice_many_notify(head, 0, NULL); } EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel * @dev: device * * This function shuts down a device interface and removes it * from the kernel tables. * * This is just a wrapper for unregister_netdevice that takes * the rtnl semaphore. In general you want to use this and not * unregister_netdevice. */ void unregister_netdev(struct net_device *dev) { rtnl_lock(); unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(unregister_netdev); /** * __dev_change_net_namespace - move device to different nethost namespace * @dev: device * @net: network namespace * @pat: If not NULL name pattern to try if the current device name * is already taken in the destination network namespace. * @new_ifindex: If not zero, specifies device index in the target * namespace. * * This function shuts down a device interface and moves it * to a new network namespace. On success 0 is returned, on * a failure a netagive errno code is returned. * * Callers must hold the rtnl semaphore. */ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); /* Don't allow namespace local devices to be moved. */ err = -EINVAL; if (dev->features & NETIF_F_NETNS_LOCAL) goto out; /* Ensure the device has been registrered */ if (dev->reg_state != NETREG_REGISTERED) goto out; /* Get out if there is nothing todo */ err = 0; if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) goto out; } /* Check that none of the altnames conflicts. */ err = -EEXIST; netdev_for_each_altname(dev, name_node) if (netdev_name_in_use(net, name_node->name)) goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); if (err < 0) goto out; } else { /* If there is an ifindex conflict assign a new one */ err = dev_index_reserve(net, dev->ifindex); if (err == -EBUSY) err = dev_index_reserve(net, 0); if (err < 0) goto out; new_ifindex = err; } /* * And now a mini version of register_netdevice unregister_netdevice. */ /* If device is running close it first. */ dev_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); synchronize_net(); /* Shutdown queueing discipline. */ dev_shutdown(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. * * Note that dev->reg_state stays at NETREG_REGISTERED. * This is wanted because this way 8021q and macvlan know * the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); /* Move per-net netdevice notifiers that are following the netdevice */ move_netdevice_notifiers_dev_net(dev, net); /* Actually switch the network namespace */ dev_net_set(dev, net); dev->ifindex = new_ifindex; if (new_name[0]) { /* Rename the netdev to prepared name */ write_seqlock(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); write_sequnlock(&netdev_rename_lock); } /* Fixup kobjects */ dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ err = netdev_change_owner(dev, net_old, net); WARN_ON(err); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; out: return err; } EXPORT_SYMBOL_GPL(__dev_change_net_namespace); static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); oldsd = &per_cpu(softnet_data, oldcpu); /* Find end of our completion_queue. */ list_skb = &sd->completion_queue; while (*list_skb) list_skb = &(*list_skb)->next; /* Append completion queue from offline CPU. */ *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; /* Append output queue from offline CPU. */ if (oldsd->output_queue) { *sd->output_queue_tailp = oldsd->output_queue; sd->output_queue_tailp = oldsd->output_queue_tailp; oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } /* Append NAPI poll list from offline CPU, with one exception : * process_backlog() must be called by cpu owning percpu backlog. * We properly handle process_queue & input_pkt_queue later. */ while (!list_empty(&oldsd->poll_list)) { struct napi_struct *napi = list_first_entry(&oldsd->poll_list, struct napi_struct, poll_list); list_del_init(&napi->poll_list); if (napi->poll == process_backlog) napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); if (!use_backlog_threads()) { #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; oldsd->rps_ipi_list = NULL; #endif /* send out pending IPI's on offline CPU */ net_rps_send_ipi(remsd); } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } return 0; } /** * netdev_increment_features - increment feature set by one * @all: current feature set * @one: new feature set * @mask: mask feature set * * Computes a new feature set after adding a device with feature set * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_HW_CSUM) mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_HW_CSUM) all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; hash = kmalloc_array(NETDEV_HASHENTRIES, sizeof(*hash), GFP_KERNEL); if (hash != NULL) for (i = 0; i < NETDEV_HASHENTRIES; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) goto err_name; net->dev_index_head = netdev_create_hash(); if (net->dev_index_head == NULL) goto err_idx; xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1); RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; err_idx: kfree(net->dev_name_head); err_name: return -ENOMEM; } /** * netdev_drivername - network driver for the device * @dev: network device * * Determine network driver for device. */ const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; const char *empty = ""; parent = dev->dev.parent; if (!parent) return empty; driver = parent->driver; if (driver && driver->name) return driver->name; return empty; } static void __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { if (dev && dev->dev.parent) { dev_printk_emit(level[1] - '0', dev->dev.parent, "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), netdev_name(dev), netdev_reg_state(dev), vaf); } else if (dev) { printk("%s%s%s: %pV", level, netdev_name(dev), netdev_reg_state(dev), vaf); } else { printk("%s(NULL net_device): %pV", level, vaf); } } void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __netdev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(netdev_printk); #define define_netdev_printk_level(func, level) \ void func(const struct net_device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __netdev_printk(level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_netdev_printk_level(netdev_emerg, KERN_EMERG); define_netdev_printk_level(netdev_alert, KERN_ALERT); define_netdev_printk_level(netdev_crit, KERN_CRIT); define_netdev_printk_level(netdev_err, KERN_ERR); define_netdev_printk_level(netdev_warn, KERN_WARNING); define_netdev_printk_level(netdev_notice, KERN_NOTICE); define_netdev_printk_level(netdev_info, KERN_INFO); static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); xa_destroy(&net->dev_by_index); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; static void __net_exit default_device_exit_net(struct net *net) { struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ if (dev->features & NETIF_F_NETNS_LOCAL) continue; /* Leave virtual devices for the generic cleanup */ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) if (netdev_name_in_use(&init_net, name_node->name)) __netdev_name_node_alt_destroy(name_node); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", __func__, dev->name, err); BUG(); } } } static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ struct net_device *dev; struct net *net; LIST_HEAD(dev_kill_list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { default_device_exit_net(net); cond_resched(); } list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); } } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); #ifdef CONFIG_XPS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); #endif #ifdef CONFIG_NETFILTER_EGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); #ifdef CONFIG_NETPOLL CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104); } /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ /* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */ #define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE) static int net_page_pool_create(int cpuid) { #if IS_ENABLED(CONFIG_PAGE_POOL) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; per_cpu(system_page_pool, cpuid) = pp_ptr; #endif return 0; } static int backlog_napi_should_run(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); } static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); napi_threaded_poll_loop(&sd->backlog); } static void backlog_napi_setup(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; napi->thread = this_cpu_read(backlog_napi); set_bit(NAPI_STATE_THREADED, &napi->state); } static struct smp_hotplug_thread backlog_threads = { .store = &backlog_napi, .thread_should_run = backlog_napi_should_run, .thread_fn = run_backlog_napi, .thread_comm = "backlog_napi/%u", .setup = backlog_napi_setup, }; /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. */ static int __init net_dev_init(void) { int i, rc = -ENOMEM; BUG_ON(!dev_boot_phase); net_dev_struct_check(); if (dev_proc_init()) goto out; if (netdev_kobject_init()) goto out; for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); if (register_pernet_subsys(&netdev_net_ops)) goto out; /* * Initialise the packet receive queues. */ for_each_possible_cpu(i) { struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); INIT_WORK(flush, flush_backlog); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } if (use_backlog_threads()) smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; /* The loopback device is special if any other network devices * is present in a network namespace the loopback device must * be present. Since we now dynamically allocate and free the * loopback device ensure this invariant is maintained by * keeping the loopback device as the first device on the * list of network devices. Ensuring the loopback devices * is the first device that appears and the last network device * that disappears. */ if (register_pernet_device(&loopback_net_ops)) goto out; if (register_pernet_device(&default_device_ops)) goto out; open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; /* avoid static key IPIs to isolated CPUs */ if (housekeeping_enabled(HK_TYPE_MISC)) net_enable_timestamp(); out: if (rc < 0) { for_each_possible_cpu(i) { struct page_pool *pp_ptr; pp_ptr = per_cpu(system_page_pool, i); if (!pp_ptr) continue; page_pool_destroy(pp_ptr); per_cpu(system_page_pool, i) = NULL; } } return rc; } subsys_initcall(net_dev_init); |
| 8 7 7 7 7 7 7 21 20 20 21 21 20 14 7 21 7 7 7 7 7 7 21 1 1 1 1 1 24 23 24 5 18 10 3 3 3 23 1 1 11 17 18 8 2 24 23 24 23 23 8 23 8 8 8 19 23 23 24 23 7 1 23 24 15 14 6 23 24 24 26 26 26 26 25 26 26 24 26 26 26 26 18 17 3 18 15 16 18 18 18 17 1 1 17 3 16 4 26 23 26 26 9 4 9 20 3 3 26 28 28 2 28 23 27 27 28 28 1 1 28 25 26 26 23 18 23 20 24 24 15 14 14 15 22 23 22 22 1 1 13 12 17 10 9 8 17 11 6 6 17 16 8 1 1 9 7 2 1 1 1 1 1 1 1 12 8 11 13 13 13 13 13 13 12 13 11 11 11 11 1 1 1 1 13 13 13 13 13 3 2 13 13 13 5 8 12 10 10 23 22 22 18 18 6 23 16 16 22 23 12 12 1 1 29 29 2 2 30 30 30 28 30 29 4 4 21 20 20 21 21 19 21 21 23 23 21 21 21 20 20 20 20 19 23 10 23 21 23 21 10 23 14 23 23 23 23 23 13 23 23 23 23 23 23 22 23 23 14 21 7 23 23 23 7 22 8 22 22 8 22 23 23 23 21 22 23 23 14 10 2 6 15 15 8 8 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include "internal.h" struct follow_page_context { struct dev_pagemap *pgmap; unsigned int page_mask; }; static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; /* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong. */ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); else /* Either a PTE-mapped or a PMD-mapped THP. */ VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && !PageAnonExclusive(page), page); } } /* * Return the folio with ref appropriately incremented, * or NULL if that failed. */ static inline struct folio *try_get_folio(struct page *page, int refs) { struct folio *folio; retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add_rcu(folio, refs))) return NULL; /* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } return folio; } /** * try_grab_folio() - Attempt to get or pin a folio. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. */ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) { struct folio *folio; if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; if (flags & FOLL_GET) return try_get_folio(page, refs); /* FOLL_PIN is set */ /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return page_folio(page); folio = try_get_folio(page, refs); if (!folio) return NULL; /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } /* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact. */ if (folio_test_large(folio)) atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; } static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } /** * try_grab_page() - elevate a page's refcount by a flag-dependent amount * @page: pointer to page to be grabbed * @flags: gup flags: these are the FOLL_* flag values. * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. Cases: please see the try_grab_folio() documentation, with * "refs=1". * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not * be grabbed. */ int __must_check try_grab_page(struct page *page, unsigned int flags) { struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_inc(folio); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return 0; /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, 1); atomic_add(1, &folio->_pincount); } else { folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); } return 0; } /** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. */ void unpin_user_page(struct page *page) { sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); /** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page. */ void folio_add_pin(struct folio *folio) { if (is_zero_folio(folio)) return; /* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned. */ if (folio_test_large(folio)) { WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); folio_ref_inc(folio); atomic_inc(&folio->_pincount); } else { WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } } static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { struct page *next = nth_page(start, i); struct folio *folio = page_folio(next); unsigned int nr = 1; if (folio_test_large(folio)) nr = min_t(unsigned int, npages - i, folio_nr_pages(folio) - folio_page_idx(folio, next)); *ntails = nr; return folio; } static inline struct folio *gup_folio_next(struct page **list, unsigned long npages, unsigned long i, unsigned int *ntails) { struct folio *folio = page_folio(list[i]); unsigned int nr; for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break; } *ntails = nr - i; return folio; } /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * page_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ if (!folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; for (i = 0; i < npages; i += nr) { folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all. */ for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages); /* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups. */ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) { if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags); } #ifdef CONFIG_MMU #if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_GUP_FAST) static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) { struct page *start_page; int nr; start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) pages[nr] = nth_page(start_page, nr); return nr; } #endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ #ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) { unsigned long __boundary = (addr + sz) & ~(sz-1); return (__boundary - 1 < end - 1) ? __boundary : end; } /* * Returns 1 if succeeded, 0 if failed, -EMLINK if unshare needed. * * NOTE: for the same entry, gup-fast and gup-slow can return different * results (0 v.s. -EMLINK) depending on whether vma is available. This is * the expected behavior, where we simply want gup-fast to fallback to * gup-slow to take the vma reference first. */ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long pte_end; struct page *page; struct folio *folio; pte_t pte; int refs; pte_end = (addr + sz) & ~(sz-1); if (pte_end < end) end = pte_end; pte = huge_ptep_get(ptep); if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); refs = record_subpages(page, sz, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, refs, flags); return 0; } if (!pte_write(pte) && gup_must_unshare(vma, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return -EMLINK; } *nr += refs; folio_set_referenced(folio); return 1; } /* * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file * systems on Power, which does not have issue with folio writeback against * GUP updates. When hugepd will be extended to support non-hugetlbfs or * even anonymous memory, we need to do extra check as what we do with most * of the other folios. See writable_file_mapping_allowed() and * gup_fast_folio_allowed() for more information. */ static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; unsigned long sz = 1UL << hugepd_shift(hugepd); unsigned long next; int ret; ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr); if (ret != 1) return ret; } while (ptep++, addr = next, addr != end); return 1; } static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned int flags, struct follow_page_context *ctx) { struct page *page; struct hstate *h; spinlock_t *ptl; int nr = 0, ret; pte_t *ptep; /* Only hugetlb supports hugepd */ if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) return ERR_PTR(-EFAULT); h = hstate_vma(vma); ptep = hugepte_offset(hugepd, addr, pdshift); ptl = huge_pte_lock(h, vma->vm_mm, ptep); ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, flags, &page, &nr); spin_unlock(ptl); if (ret == 1) { /* GUP succeeded */ WARN_ON_ONCE(nr != 1); ctx->page_mask = (1U << huge_page_order(h)) - 1; return page; } /* ret can be either 0 (translates to NULL) or negative */ return ERR_PTR(ret); } #else /* CONFIG_ARCH_HAS_HUGEPD */ static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_ARCH_HAS_HUGEPD */ static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { if (!(flags & FOLL_DUMP)) return NULL; /* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma); if (!hugetlbfs_pagecache_present(h, vma, address)) return ERR_PTR(-EFAULT); } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); } return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; struct page *page; pud_t pud = *pudp; unsigned long pfn = pud_pfn(pud); int ret; assert_spin_locked(pud_lockptr(mm, pudp)); if ((flags & FOLL_WRITE) && !pud_write(pud)) return NULL; if (!pud_present(pud)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && pud_devmap(pud)) { /* * device mapped pages can only be returned if the caller * will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so * assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); if (flags & FOLL_TOUCH) touch_pud(vma, addr, pudp, flags & FOLL_WRITE); ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); if (!ctx->pgmap) return ERR_PTR(-EFAULT); } page = pfn_to_page(pfn); if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); ret = try_grab_page(page, flags); if (ret) page = ERR_PTR(ret); else ctx->page_mask = HPAGE_PUD_NR - 1; return page; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; pmd_t pmdval = *pmd; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(pmdval); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); ret = try_grab_page(page, flags); if (ret) return ERR_PTR(ret); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; ctx->page_mask = HPAGE_PMD_NR - 1; return page; } #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { return NULL; } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } } /* Proper page table entry exists, but no corresponding struct page */ return -EEXIST; } /* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ static inline bool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) return false; return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; int ret; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_page(page, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, unsigned int flags, struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), address, PMD_SHIFT, flags, ctx); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); pmdval = *pmd; if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); return page; } static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, unsigned int flags, struct follow_page_context *ctx) { pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) return follow_hugepd(vma, __hugepd(pud_val(pud)), address, PUD_SHIFT, flags, ctx); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, unsigned int flags, struct follow_page_context *ctx) { p4d_t *p4dp, p4d; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) return follow_hugepd(vma, __hugepd(p4d_val(p4d)), address, P4D_SHIFT, flags, ctx); if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page; vma_pgtable_walk_begin(vma); ctx->page_mask = 0; pgd = pgd_offset(mm, address); if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd))))) page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)), address, PGDIR_SHIFT, flags, ctx); else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); vma_pgtable_walk_end(vma); return page; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { struct follow_page_context ctx = { NULL }; struct page *page; if (vma_is_secretmem(vma)) return NULL; if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) return NULL; /* * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect * to fail on PROT_NONE-mapped pages. */ page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT; if (address > TASK_SIZE) pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); if (pgd_none(*pgd)) return -EFAULT; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT; pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT; entry = ptep_get(pte); if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; *page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; *page = pte_page(entry); } ret = try_grab_page(*page, gup_flags); if (unlikely(ret)) goto unmap; out: ret = 0; unmap: pte_unmap(pte); return ret; } /* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int *flags, bool unshare, int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; if (*flags & FOLL_NOFAULT) return -EFAULT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (*flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (*flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (*flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (*flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } return 0; } /* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so). */ static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) { vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT; if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; if (vma_is_secretmem(vma)) return -EFAULT; if (write) { if (!vma_anon && !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT; if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ if (is_vm_hugetlb_page(vma)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; } /* * gups are always data accesses, not instruction * fetches, so execute=false here */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0; } /* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code. */ static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsigned long addr) { #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else static volatile unsigned long next_warn; struct vm_area_struct *vma; unsigned long now, next; vma = find_vma(mm, addr); if (!vma || (addr >= vma->vm_start)) return vma; /* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL; /* Let's not warn more than once an hour.. */ now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL; next_warn = now + 60*60*HZ; /* Let people know things may have changed. */ pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", current->comm, task_pid_nr(current), vma->vm_start, vma->vm_end, addr); dump_stack(); return NULL; #endif } /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); do { struct page *page; unsigned int foll_flags = gup_flags; unsigned int page_increm; /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently. */ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } if (!vma) { ret = -EFAULT; goto out; } ret = check_vma_flags(vma, gup_flags); if (ret) goto out; } retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, &foll_flags, PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page. */ if (pages) { ret = PTR_ERR(page); goto out; } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } next_page: page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; if (pages) { struct page *subpage; unsigned int j; /* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages. */ if (page_increm > 1) { struct folio *folio; /* * Since we already hold refcount on the * large folio, this should never fail. */ folio = try_grab_folio(page, page_increm - 1, foll_flags); if (WARN_ON_ONCE(!folio)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ gup_put_folio(page_folio(page), 1, foll_flags); ret = -EFAULT; goto out; } } for (j = 0; j < page_increm; j++) { subpage = nth_page(page, j); pages[i + j] = subpage; flush_anon_page(vma, subpage, start + j * PAGE_SIZE); flush_dcache_page(subpage); } } i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); out: if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { bool write = !!(fault_flags & FAULT_FLAG_WRITE); bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; if (!(vm_flags & vma->vm_flags)) return false; /* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here: */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return false; return true; } /** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); /* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. */ static bool gup_signal_pending(unsigned int flags) { if (fatal_signal_pending(current)) return true; if (!(flags & FOLL_INTERRUPTIBLE)) return false; return signal_pending(current); } /* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } /* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified). */ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT; return pages_done; } /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0. */ long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; /* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable). */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; else gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; } /* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked) { unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); mmap_assert_locked(mm); /* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, gup_flags); lru_add_drain(); return ret; } /* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held. */ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; bool must_unlock = false; unsigned long vm_flags; long i; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. */ vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) break; if (pages) { pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } start = (start + PAGE_SIZE) & PAGE_MASK; } if (must_unlock && *locked) { mmap_read_unlock(mm); *locked = 0; } return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ /** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_writeable(char __user *uaddr, size_t size) { char __user *start = uaddr, *end; if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_put_user(0, uaddr, out); uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_put_user(0, uaddr, out); uaddr += PAGE_SIZE; } out: user_write_access_end(); if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_writeable); /** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) { size_t faulted_in; /* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this. */ faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in) faulted_in -= probe_subpage_writeable(uaddr, faulted_in); return size - faulted_in; } EXPORT_SYMBOL(fault_in_subpage_writeable); /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; bool unlocked = false; if (unlikely(size == 0)) return 0; end = PAGE_ALIGN(start + size); if (end < start) end = 0; mmap_read_lock(mm); do { if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; start = (start + PAGE_SIZE) & PAGE_MASK; } while (start != end); mmap_read_unlock(mm); if (size > (unsigned long)uaddr - start) return size - ((unsigned long)uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_readable(const char __user *uaddr, size_t size) { const char __user *start = uaddr, *end; volatile char c; if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_get_user(c, uaddr, out); uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out); uaddr += PAGE_SIZE; } out: user_read_access_end(); (void)c; if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_readable); /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION /* * Returns the number of collected pages. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_pages( struct list_head *movable_page_list, unsigned long nr_pages, struct page **pages) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; collected++; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { isolate_hugetlb(folio, movable_page_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_page_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } return collected; } /* * Unpins all pages and migrates device coherent pages and movable_page_list. * Returns -EAGAIN if all pages were successfully migrated or -errno for failure * (or partial success). */ static int migrate_longterm_unpinnable_pages( struct list_head *movable_page_list, unsigned long nr_pages, struct page **pages) { int ret; unsigned long i; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio_is_device_coherent(folio)) { /* * Migration will fail if the page is pinned, so convert * the pin on the source page to a normal reference. */ pages[i] = NULL; folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); if (migrate_device_coherent_page(&folio->page)) { ret = -EBUSY; goto err; } continue; } /* * We can't migrate pages with unexpected references, so drop * the reference obtained by __get_user_pages_locked(). * Migrating pages have been added to movable_page_list after * calling folio_isolate_lru() which takes a reference so the * page won't be freed if it's migrating. */ unpin_user_page(pages[i]); pages[i] = NULL; } if (!list_empty(movable_page_list)) { struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_LONGTERM_PIN, NULL)) { ret = -ENOMEM; goto err; } } putback_movable_pages(movable_page_list); return -EAGAIN; err: for (i = 0; i < nr_pages; i++) if (pages[i]) unpin_user_page(pages[i]); putback_movable_pages(movable_page_list); return ret; } /* * Check whether all pages are *allowed* to be pinned. Rather confusingly, all * pages in the range are required to be pinned via FOLL_PIN, before calling * this routine. * * If any pages in the range are not allowed to be pinned, then this routine * will migrate those pages away, unpin all the pages in the range and return * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then * call this routine again. * * If an error other than -EAGAIN occurs, this indicates a migration failure. * The caller should give up, and propagate the error back up the call stack. * * If everything is OK and all pages in the range are allowed to be pinned, then * this routine leaves all pages pinned and returns zero for success. */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { unsigned long collected; LIST_HEAD(movable_page_list); collected = collect_longterm_unpinnable_pages(&movable_page_list, nr_pages, pages); if (!collected) return 0; return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages, pages); } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { return 0; } #endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int gup_flags) { unsigned int flags; long rc, nr_pinned_pages; if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); flags = memalloc_pin_save(); do { nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); if (nr_pinned_pages <= 0) { rc = nr_pinned_pages; break; } /* FOLL_LONGTERM implies FOLL_PIN */ rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); } while (rc == -EAGAIN); memalloc_pin_restore(flags); return rc ? rc : nr_pinned_pages; } /* * Check that the given flags are valid for the exported gup/pup interface, and * update them with the required flags that the caller must have set. */ static bool is_valid_gup_args(struct page **pages, int *locked, unsigned int *gup_flags_p, unsigned int to_set) { unsigned int gup_flags = *gup_flags_p; /* * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only and used on follow_page() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; if (locked) { /* At the external interface locked must be set */ if (WARN_ON_ONCE(*locked != 1)) return false; gup_flags |= FOLL_UNLOCKABLE; } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return false; /* LONGTERM can only be specified when pinning */ if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; /* Pages input must be given if using GET/PIN */ if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) return false; *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference * to each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * * get_user_pages_remote is typically used for fewer-copy IO operations, * to get a handle on the memory by some means other than accesses * via the user virtual addresses. The pages may be submitted for * DMA to devices or accessed via their kernel linear mapping (via the * kmap APIs). Care should be taken to use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. * * get_user_pages_remote should be phased out in favor of * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { return 0; } #endif /* !CONFIG_MMU */ /** * get_user_pages() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to * the current task, and doesn't allow passing of a locked parameter. We also * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); /* * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be * protected from page table pages being freed from under it, and should * block any THP splits. * * One way to achieve this is to have the walker disable interrupts, and * rely on IPIs from the TLB flushing code blocking before the page table * pages are freed. This is unsuitable for architectures that do not need * to broadcast an IPI when invalidating TLBs. * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * * Before activating this code, please be aware that the following assumptions * are currently made: * * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. * * The last two assumptions can be relaxed by the addition of helper functions. * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * GUP-fast must reject all secretmem folios. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { bool reject_file_backed = false; struct address_space *mapping; bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) reject_file_backed = true; /* We hold a folio reference, so we can safely access folio fields. */ /* secretmem folios are always order-0 folios. */ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) check_secretmem = true; if (!reject_file_backed && !check_secretmem) return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. */ if (check_secretmem && secretmem_mapping(mapping)) return false; /* The only remaining allowed file system is shmem. */ return !reject_file_backed || shmem_mapping(mapping); } static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio); gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio = try_grab_folio(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); return addr == end; } static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } #endif static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, pages, nr); } page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, pages, nr); } page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_leaf(pmd))) { /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { /* * architecture have different format for hugetlbfs * pmd format and THP pmd format */ if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, PMD_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_leaf(pud))) { if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_leaf(pgd))) { if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr) != 1) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } #endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* * Check if it's allowed to use get_user_pages_fast_only() for the range, or * we need to fall back to the slow version: */ static bool gup_fast_permitted(unsigned long start, unsigned long end) { return true; } #endif static unsigned long gup_fast(unsigned long start, unsigned long end, unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; if (gup_flags & FOLL_PIN) { seq = raw_read_seqcount(¤t->mm->write_protect_seq); if (seq & 1) return 0; } /* * Disable interrupts. The nested form is used, in order to allow full, * general purpose use of this routine. * * With interrupts disabled, we block page table pages from being freed * from under us. See struct mmu_table_batch comments in * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock() here as we also want to block IPIs * that come from THPs splitting. */ local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; } static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_unlocked); |
| 7 9 9 9 5 5 5 5 5 5 1 1 1 5 10 10 9 10 10 10 10 10 10 10 10 10 10 4 1 4 10 1 1 10 10 10 10 1 10 2 2 9 2 7 4 3 3 1 3 9 9 9 4 9 9 9 9 9 9 9 9 9 9 5 5 4 4 4 2 5 1 1 10 9 10 7 6 7 1 1 1 7 7 7 4 4 4 9 9 9 8 8 8 8 8 8 7 7 2 9 9 9 8 8 8 9 9 9 9 9 2 7 2 2 7 8 3 3 3 3 3 3 3 3 8 4 3 3 3 3 3 2 1 3 2 3 3 3 1 3 3 3 3 2 3 2 2 3 3 1 3 1 3 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 5 8 7 7 7 7 7 8 8 8 8 8 8 8 8 8 1 1 1 1 1 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 8 8 8 7 7 7 8 7 1 8 8 8 8 8 8 8 8 1 1 8 8 1 8 8 9 9 9 9 4 4 4 4 4 4 4 4 4 5 1 5 5 4 5 5 5 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 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 | /* FUSE: Filesystem in Userspace Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu> This program can be distributed under the terms of the GNU GPL. See the file COPYING. */ #include "fuse_i.h" #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/statfs.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/pid_namespace.h> #include <uapi/linux/magic.h> MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); MODULE_DESCRIPTION("Filesystem in Userspace"); MODULE_LICENSE("GPL"); static struct kmem_cache *fuse_inode_cachep; struct list_head fuse_conn_list; DEFINE_MUTEX(fuse_mutex); static int set_global_limit(const char *val, const struct kernel_param *kp); unsigned max_user_bgreq; module_param_call(max_user_bgreq, set_global_limit, param_get_uint, &max_user_bgreq, 0644); __MODULE_PARM_TYPE(max_user_bgreq, "uint"); MODULE_PARM_DESC(max_user_bgreq, "Global limit for the maximum number of backgrounded requests an " "unprivileged user can set"); unsigned max_user_congthresh; module_param_call(max_user_congthresh, set_global_limit, param_get_uint, &max_user_congthresh, 0644); __MODULE_PARM_TYPE(max_user_congthresh, "uint"); MODULE_PARM_DESC(max_user_congthresh, "Global limit for the maximum congestion threshold an " "unprivileged user can set"); #define FUSE_DEFAULT_BLKSIZE 512 /** Maximum number of outstanding background requests */ #define FUSE_DEFAULT_MAX_BACKGROUND 12 /** Congestion starts at 75% of maximum */ #define FUSE_DEFAULT_CONGESTION_THRESHOLD (FUSE_DEFAULT_MAX_BACKGROUND * 3 / 4) #ifdef CONFIG_BLOCK static struct file_system_type fuseblk_fs_type; #endif struct fuse_forget_link *fuse_alloc_forget(void) { return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) { struct fuse_submount_lookup *sl; sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); if (!sl) return NULL; sl->forget = fuse_alloc_forget(); if (!sl->forget) goto out_free; return sl; out_free: kfree(sl); return NULL; } static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; fi = alloc_inode_sb(sb, fuse_inode_cachep, GFP_KERNEL); if (!fi) return NULL; fi->i_time = 0; fi->inval_mask = ~0; fi->nodeid = 0; fi->nlookup = 0; fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); if (!fi->forget) goto out_free; if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi)) goto out_free_forget; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_inode_backing_set(fi, NULL); return &fi->inode; out_free_forget: kfree(fi->forget); out_free: kmem_cache_free(fuse_inode_cachep, fi); return NULL; } static void fuse_free_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); mutex_destroy(&fi->mutex); kfree(fi->forget); #ifdef CONFIG_FUSE_DAX kfree(fi->dax); #endif if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_put(fuse_inode_backing(fi)); kmem_cache_free(fuse_inode_cachep, fi); } static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, struct fuse_submount_lookup *sl) { if (!refcount_dec_and_test(&sl->count)) return; fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); sl->forget = NULL; kfree(sl); } static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); /* Will write inode on close/munmap and in all other dirtiers */ WARN_ON(inode->i_state & I_DIRTY_INODE); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & SB_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); if (FUSE_IS_DAX(inode)) fuse_dax_inode_cleanup(inode); if (fi->nlookup) { fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup); fi->forget = NULL; } if (fi->submount_lookup) { fuse_cleanup_submount_lookup(fc, fi->submount_lookup); fi->submount_lookup = NULL; } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(fi->iocachectr != 0); WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } } static int fuse_reconfigure(struct fs_context *fsc) { struct super_block *sb = fsc->root->d_sb; sync_filesystem(sb); if (fsc->sb_flags & SB_MANDLOCK) return -EINVAL; return 0; } /* * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down * so that it will fit. */ static ino_t fuse_squash_ino(u64 ino64) { ino_t ino = (ino_t) ino64; if (sizeof(ino_t) < sizeof(u64)) ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8; return ino; } void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, struct fuse_statx *sx, u64 attr_valid, u32 cache_mask) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); lockdep_assert_held(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); fi->i_time = attr_valid; /* Clear basic stats from invalid mask */ set_mask_bits(&fi->inval_mask, STATX_BASIC_STATS, 0); inode->i_ino = fuse_squash_ino(attr->ino); inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); set_nlink(inode, attr->nlink); inode->i_uid = make_kuid(fc->user_ns, attr->uid); inode->i_gid = make_kgid(fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; /* Sanitize nsecs */ attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1); attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1); attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1); inode_set_atime(inode, attr->atime, attr->atimensec); /* mtime from server may be stale due to local buffered write */ if (!(cache_mask & STATX_MTIME)) { inode_set_mtime(inode, attr->mtime, attr->mtimensec); } if (!(cache_mask & STATX_CTIME)) { inode_set_ctime(inode, attr->ctime, attr->ctimensec); } if (sx) { /* Sanitize nsecs */ sx->btime.tv_nsec = min_t(u32, sx->btime.tv_nsec, NSEC_PER_SEC - 1); /* * Btime has been queried, cache is valid (whether or not btime * is available or not) so clear STATX_BTIME from inval_mask. * * Availability of the btime attribute is indicated in * FUSE_I_BTIME */ set_mask_bits(&fi->inval_mask, STATX_BTIME, 0); if (sx->mask & STATX_BTIME) { set_bit(FUSE_I_BTIME, &fi->state); fi->i_btime.tv_sec = sx->btime.tv_sec; fi->i_btime.tv_nsec = sx->btime.tv_nsec; } } if (attr->blksize != 0) inode->i_blkbits = ilog2(attr->blksize); else inode->i_blkbits = inode->i_sb->s_blocksize_bits; /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the * check in may_delete(). */ fi->orig_i_mode = inode->i_mode; if (!fc->default_permissions) inode->i_mode &= ~S_ISVTX; fi->orig_ino = attr->ino; /* * We are refreshing inode data and it is possible that another * client set suid/sgid or security.capability xattr. So clear * S_NOSEC. Ideally, we could have cleared it only if suid/sgid * was set or if security.capability xattr was set. But we don't * know if security.capability has been set or not. So clear it * anyway. Its less efficient but should be safe. */ inode->i_flags &= ~S_NOSEC; } u32 fuse_get_cache_mask(struct inode *inode) { struct fuse_conn *fc = get_fuse_conn(inode); if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) return 0; return STATX_MTIME | STATX_CTIME | STATX_SIZE; } void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct fuse_statx *sx, u64 attr_valid, u64 attr_version) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); u32 cache_mask; loff_t oldsize; struct timespec64 old_mtime; spin_lock(&fi->lock); /* * In case of writeback_cache enabled, writes update mtime, ctime and * may update i_size. In these cases trust the cached value in the * inode. */ cache_mask = fuse_get_cache_mask(inode); if (cache_mask & STATX_SIZE) attr->size = i_size_read(inode); if (cache_mask & STATX_MTIME) { attr->mtime = inode_get_mtime_sec(inode); attr->mtimensec = inode_get_mtime_nsec(inode); } if (cache_mask & STATX_CTIME) { attr->ctime = inode_get_ctime_sec(inode); attr->ctimensec = inode_get_ctime_nsec(inode); } if ((attr_version != 0 && fi->attr_version > attr_version) || test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { spin_unlock(&fi->lock); return; } old_mtime = inode_get_mtime(inode); fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask); oldsize = inode->i_size; /* * In case of writeback_cache enabled, the cached writes beyond EOF * extend local i_size without keeping userspace server in sync. So, * attr->size coming from server can be stale. We cannot trust it. */ if (!(cache_mask & STATX_SIZE)) i_size_write(inode, attr->size); spin_unlock(&fi->lock); if (!cache_mask && S_ISREG(inode->i_mode)) { bool inval = false; if (oldsize != attr->size) { truncate_pagecache(inode, attr->size); if (!fc->explicit_inval_data) inval = true; } else if (fc->auto_inval_data) { struct timespec64 new_mtime = { .tv_sec = attr->mtime, .tv_nsec = attr->mtimensec, }; /* * Auto inval mode also checks and invalidates if mtime * has changed. */ if (!timespec64_equal(&old_mtime, &new_mtime)) inval = true; } if (inval) invalidate_inode_pages2(inode->i_mapping); } if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_dontcache(inode, attr->flags); } static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, u64 nodeid) { sl->nodeid = nodeid; refcount_set(&sl->count, 1); } static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc) { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; inode_set_mtime(inode, attr->mtime, attr->mtimensec); inode_set_ctime(inode, attr->ctime, attr->ctimensec); if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); fuse_init_file_inode(inode, attr->flags); } else if (S_ISDIR(inode->i_mode)) fuse_init_dir(inode); else if (S_ISLNK(inode->i_mode)) fuse_init_symlink(inode); else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { fuse_init_common(inode); init_special_inode(inode, inode->i_mode, new_decode_dev(attr->rdev)); } else BUG(); /* * Ensure that we don't cache acls for daemons without FUSE_POSIX_ACL * so they see the exact same behavior as before. */ if (!fc->posix_acl) inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; } static int fuse_inode_eq(struct inode *inode, void *_nodeidp) { u64 nodeid = *(u64 *) _nodeidp; if (get_node_id(inode) == nodeid) return 1; else return 0; } static int fuse_inode_set(struct inode *inode, void *_nodeidp) { u64 nodeid = *(u64 *) _nodeidp; get_fuse_inode(inode)->nodeid = nodeid; return 0; } struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int generation, struct fuse_attr *attr, u64 attr_valid, u64 attr_version) { struct inode *inode; struct fuse_inode *fi; struct fuse_conn *fc = get_fuse_conn_super(sb); /* * Auto mount points get their node id from the submount root, which is * not a unique identifier within this filesystem. * * To avoid conflicts, do not place submount points into the inode hash * table. */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { struct fuse_inode *fi; inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr, fc); fi = get_fuse_inode(inode); fi->nodeid = nodeid; fi->submount_lookup = fuse_alloc_submount_lookup(); if (!fi->submount_lookup) { iput(inode); return NULL; } /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } retry: inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid); if (!inode) return NULL; if ((inode->i_state & I_NEW)) { inode->i_flags |= S_NOATIME; if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; fuse_init_inode(inode, attr, fc); unlock_new_inode(inode); } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); if (inode != d_inode(sb->s_root)) { remove_inode_hash(inode); iput(inode); goto retry; } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); done: fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version); return inode; } struct inode *fuse_ilookup(struct fuse_conn *fc, u64 nodeid, struct fuse_mount **fm) { struct fuse_mount *fm_iter; struct inode *inode; WARN_ON(!rwsem_is_locked(&fc->killsb)); list_for_each_entry(fm_iter, &fc->mounts, fc_entry) { if (!fm_iter->sb) continue; inode = ilookup5(fm_iter->sb, nodeid, fuse_inode_eq, &nodeid); if (inode) { if (fm) *fm = fm_iter; return inode; } } return NULL; } int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid, loff_t offset, loff_t len) { struct fuse_inode *fi; struct inode *inode; pgoff_t pg_start; pgoff_t pg_end; inode = fuse_ilookup(fc, nodeid, NULL); if (!inode) return -ENOENT; fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); spin_unlock(&fi->lock); fuse_invalidate_attr(inode); forget_all_cached_acls(inode); if (offset >= 0) { pg_start = offset >> PAGE_SHIFT; if (len <= 0) pg_end = -1; else pg_end = (offset + len - 1) >> PAGE_SHIFT; invalidate_inode_pages2_range(inode->i_mapping, pg_start, pg_end); } iput(inode); return 0; } bool fuse_lock_inode(struct inode *inode) { bool locked = false; if (!get_fuse_conn(inode)->parallel_dirops) { mutex_lock(&get_fuse_inode(inode)->mutex); locked = true; } return locked; } void fuse_unlock_inode(struct inode *inode, bool locked) { if (locked) mutex_unlock(&get_fuse_inode(inode)->mutex); } static void fuse_umount_begin(struct super_block *sb) { struct fuse_conn *fc = get_fuse_conn_super(sb); if (fc->no_force_umount) return; fuse_abort_conn(fc); // Only retire block-device-based superblocks. if (sb->s_bdev != NULL) retire_super(sb); } static void fuse_send_destroy(struct fuse_mount *fm) { if (fm->fc->conn_init) { FUSE_ARGS(args); args.opcode = FUSE_DESTROY; args.force = true; args.nocreds = true; fuse_simple_request(fm, &args); } } static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr) { stbuf->f_type = FUSE_SUPER_MAGIC; stbuf->f_bsize = attr->bsize; stbuf->f_frsize = attr->frsize; stbuf->f_blocks = attr->blocks; stbuf->f_bfree = attr->bfree; stbuf->f_bavail = attr->bavail; stbuf->f_files = attr->files; stbuf->f_ffree = attr->ffree; stbuf->f_namelen = attr->namelen; /* fsid is left zero */ } static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct fuse_mount *fm = get_fuse_mount_super(sb); FUSE_ARGS(args); struct fuse_statfs_out outarg; int err; if (!fuse_allow_current_process(fm->fc)) { buf->f_type = FUSE_SUPER_MAGIC; return 0; } memset(&outarg, 0, sizeof(outarg)); args.in_numargs = 0; args.opcode = FUSE_STATFS; args.nodeid = get_node_id(d_inode(dentry)); args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (!err) convert_fuse_statfs(buf, &outarg.st); return err; } static struct fuse_sync_bucket *fuse_sync_bucket_alloc(void) { struct fuse_sync_bucket *bucket; bucket = kzalloc(sizeof(*bucket), GFP_KERNEL | __GFP_NOFAIL); if (bucket) { init_waitqueue_head(&bucket->waitq); /* Initial active count */ atomic_set(&bucket->count, 1); } return bucket; } static void fuse_sync_fs_writes(struct fuse_conn *fc) { struct fuse_sync_bucket *bucket, *new_bucket; int count; new_bucket = fuse_sync_bucket_alloc(); spin_lock(&fc->lock); bucket = rcu_dereference_protected(fc->curr_bucket, 1); count = atomic_read(&bucket->count); WARN_ON(count < 1); /* No outstanding writes? */ if (count == 1) { spin_unlock(&fc->lock); kfree(new_bucket); return; } /* * Completion of new bucket depends on completion of this bucket, so add * one more count. */ atomic_inc(&new_bucket->count); rcu_assign_pointer(fc->curr_bucket, new_bucket); spin_unlock(&fc->lock); /* * Drop initial active count. At this point if all writes in this and * ancestor buckets complete, the count will go to zero and this task * will be woken up. */ atomic_dec(&bucket->count); wait_event(bucket->waitq, atomic_read(&bucket->count) == 0); /* Drop temp count on descendant bucket */ fuse_sync_bucket_dec(new_bucket); kfree_rcu(bucket, rcu); } static int fuse_sync_fs(struct super_block *sb, int wait) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct fuse_syncfs_in inarg; FUSE_ARGS(args); int err; /* * Userspace cannot handle the wait == 0 case. Avoid a * gratuitous roundtrip. */ if (!wait) return 0; /* The filesystem is being unmounted. Nothing to do. */ if (!sb->s_root) return 0; if (!fc->sync_fs) return 0; fuse_sync_fs_writes(fc); memset(&inarg, 0, sizeof(inarg)); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.opcode = FUSE_SYNCFS; args.nodeid = get_node_id(sb->s_root->d_inode); args.out_numargs = 0; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fc->sync_fs = 0; err = 0; } return err; } enum { OPT_SOURCE, OPT_SUBTYPE, OPT_FD, OPT_ROOTMODE, OPT_USER_ID, OPT_GROUP_ID, OPT_DEFAULT_PERMISSIONS, OPT_ALLOW_OTHER, OPT_MAX_READ, OPT_BLKSIZE, OPT_ERR }; static const struct fs_parameter_spec fuse_fs_parameters[] = { fsparam_string ("source", OPT_SOURCE), fsparam_u32 ("fd", OPT_FD), fsparam_u32oct ("rootmode", OPT_ROOTMODE), fsparam_u32 ("user_id", OPT_USER_ID), fsparam_u32 ("group_id", OPT_GROUP_ID), fsparam_flag ("default_permissions", OPT_DEFAULT_PERMISSIONS), fsparam_flag ("allow_other", OPT_ALLOW_OTHER), fsparam_u32 ("max_read", OPT_MAX_READ), fsparam_u32 ("blksize", OPT_BLKSIZE), fsparam_string ("subtype", OPT_SUBTYPE), {} }; static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; struct fuse_fs_context *ctx = fsc->fs_private; int opt; if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { /* * Ignore options coming from mount(MS_REMOUNT) for backward * compatibility. */ if (fsc->oldapi) return 0; return invalfc(fsc, "No changes allowed in reconfigure"); } opt = fs_parse(fsc, fuse_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_SOURCE: if (fsc->source) return invalfc(fsc, "Multiple sources specified"); fsc->source = param->string; param->string = NULL; break; case OPT_SUBTYPE: if (ctx->subtype) return invalfc(fsc, "Multiple subtypes specified"); ctx->subtype = param->string; param->string = NULL; return 0; case OPT_FD: ctx->fd = result.uint_32; ctx->fd_present = true; break; case OPT_ROOTMODE: if (!fuse_valid_type(result.uint_32)) return invalfc(fsc, "Invalid rootmode"); ctx->rootmode = result.uint_32; ctx->rootmode_present = true; break; case OPT_USER_ID: ctx->user_id = make_kuid(fsc->user_ns, result.uint_32); if (!uid_valid(ctx->user_id)) return invalfc(fsc, "Invalid user_id"); ctx->user_id_present = true; break; case OPT_GROUP_ID: ctx->group_id = make_kgid(fsc->user_ns, result.uint_32); if (!gid_valid(ctx->group_id)) return invalfc(fsc, "Invalid group_id"); ctx->group_id_present = true; break; case OPT_DEFAULT_PERMISSIONS: ctx->default_permissions = true; break; case OPT_ALLOW_OTHER: ctx->allow_other = true; break; case OPT_MAX_READ: ctx->max_read = result.uint_32; break; case OPT_BLKSIZE: if (!ctx->is_bdev) return invalfc(fsc, "blksize only supported for fuseblk"); ctx->blksize = result.uint_32; break; default: return -EINVAL; } return 0; } static void fuse_free_fsc(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; if (ctx) { kfree(ctx->subtype); kfree(ctx); } } static int fuse_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; struct fuse_conn *fc = get_fuse_conn_super(sb); if (fc->legacy_opts_show) { seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id)); seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id)); if (fc->default_permissions) seq_puts(m, ",default_permissions"); if (fc->allow_other) seq_puts(m, ",allow_other"); if (fc->max_read != ~0) seq_printf(m, ",max_read=%u", fc->max_read); if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE) seq_printf(m, ",blksize=%lu", sb->s_blocksize); } #ifdef CONFIG_FUSE_DAX if (fc->dax_mode == FUSE_DAX_ALWAYS) seq_puts(m, ",dax=always"); else if (fc->dax_mode == FUSE_DAX_NEVER) seq_puts(m, ",dax=never"); else if (fc->dax_mode == FUSE_DAX_INODE_USER) seq_puts(m, ",dax=inode"); #endif return 0; } static void fuse_iqueue_init(struct fuse_iqueue *fiq, const struct fuse_iqueue_ops *ops, void *priv) { memset(fiq, 0, sizeof(struct fuse_iqueue)); spin_lock_init(&fiq->lock); init_waitqueue_head(&fiq->waitq); INIT_LIST_HEAD(&fiq->pending); INIT_LIST_HEAD(&fiq->interrupts); fiq->forget_list_tail = &fiq->forget_list_head; fiq->connected = 1; fiq->ops = ops; fiq->priv = priv; } static void fuse_pqueue_init(struct fuse_pqueue *fpq) { unsigned int i; spin_lock_init(&fpq->lock); for (i = 0; i < FUSE_PQ_HASH_SIZE; i++) INIT_LIST_HEAD(&fpq->processing[i]); INIT_LIST_HEAD(&fpq->io); fpq->connected = 1; } void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, struct user_namespace *user_ns, const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv) { memset(fc, 0, sizeof(*fc)); spin_lock_init(&fc->lock); spin_lock_init(&fc->bg_lock); init_rwsem(&fc->killsb); refcount_set(&fc->count, 1); atomic_set(&fc->dev_count, 1); init_waitqueue_head(&fc->blocked_waitq); fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv); INIT_LIST_HEAD(&fc->bg_queue); INIT_LIST_HEAD(&fc->entry); INIT_LIST_HEAD(&fc->devices); atomic_set(&fc->num_waiting, 0); fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND; fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD; atomic64_set(&fc->khctr, 0); fc->polled_files = RB_ROOT; fc->blocked = 0; fc->initialized = 0; fc->connected = 1; atomic64_set(&fc->attr_version, 1); get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; fc->max_pages_limit = FUSE_MAX_MAX_PAGES; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_files_init(fc); INIT_LIST_HEAD(&fc->mounts); list_add(&fm->fc_entry, &fc->mounts); fm->fc = fc; } EXPORT_SYMBOL_GPL(fuse_conn_init); static void delayed_release(struct rcu_head *p) { struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu); put_user_ns(fc->user_ns); fc->release(fc); } void fuse_conn_put(struct fuse_conn *fc) { if (refcount_dec_and_test(&fc->count)) { struct fuse_iqueue *fiq = &fc->iq; struct fuse_sync_bucket *bucket; if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_conn_free(fc); if (fiq->ops->release) fiq->ops->release(fiq); put_pid_ns(fc->pid_ns); bucket = rcu_dereference_protected(fc->curr_bucket, 1); if (bucket) { WARN_ON(atomic_read(&bucket->count) != 1); kfree(bucket); } if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_files_free(fc); call_rcu(&fc->rcu, delayed_release); } } EXPORT_SYMBOL_GPL(fuse_conn_put); struct fuse_conn *fuse_conn_get(struct fuse_conn *fc) { refcount_inc(&fc->count); return fc; } EXPORT_SYMBOL_GPL(fuse_conn_get); static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode) { struct fuse_attr attr; memset(&attr, 0, sizeof(attr)); attr.mode = mode; attr.ino = FUSE_ROOT_ID; attr.nlink = 1; return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0); } struct fuse_inode_handle { u64 nodeid; u32 generation; }; static struct dentry *fuse_get_dentry(struct super_block *sb, struct fuse_inode_handle *handle) { struct fuse_conn *fc = get_fuse_conn_super(sb); struct inode *inode; struct dentry *entry; int err = -ESTALE; if (handle->nodeid == 0) goto out_err; inode = ilookup5(sb, handle->nodeid, fuse_inode_eq, &handle->nodeid); if (!inode) { struct fuse_entry_out outarg; const struct qstr name = QSTR_INIT(".", 1); if (!fc->export_support) goto out_err; err = fuse_lookup_name(sb, handle->nodeid, &name, &outarg, &inode); if (err && err != -ENOENT) goto out_err; if (err || !inode) { err = -ESTALE; goto out_err; } err = -EIO; if (get_node_id(inode) != handle->nodeid) goto out_iput; } err = -ESTALE; if (inode->i_generation != handle->generation) goto out_iput; entry = d_obtain_alias(inode); if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) fuse_invalidate_entry_cache(entry); return entry; out_iput: iput(inode); out_err: return ERR_PTR(err); } static int fuse_encode_fh(struct inode *inode, u32 *fh, int *max_len, struct inode *parent) { int len = parent ? 6 : 3; u64 nodeid; u32 generation; if (*max_len < len) { *max_len = len; return FILEID_INVALID; } nodeid = get_fuse_inode(inode)->nodeid; generation = inode->i_generation; fh[0] = (u32)(nodeid >> 32); fh[1] = (u32)(nodeid & 0xffffffff); fh[2] = generation; if (parent) { nodeid = get_fuse_inode(parent)->nodeid; generation = parent->i_generation; fh[3] = (u32)(nodeid >> 32); fh[4] = (u32)(nodeid & 0xffffffff); fh[5] = generation; } *max_len = len; return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN; } static struct dentry *fuse_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct fuse_inode_handle handle; if ((fh_type != FILEID_INO64_GEN && fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3) return NULL; handle.nodeid = (u64) fid->raw[0] << 32; handle.nodeid |= (u64) fid->raw[1]; handle.generation = fid->raw[2]; return fuse_get_dentry(sb, &handle); } static struct dentry *fuse_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct fuse_inode_handle parent; if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6) return NULL; parent.nodeid = (u64) fid->raw[3] << 32; parent.nodeid |= (u64) fid->raw[4]; parent.generation = fid->raw[5]; return fuse_get_dentry(sb, &parent); } static struct dentry *fuse_get_parent(struct dentry *child) { struct inode *child_inode = d_inode(child); struct fuse_conn *fc = get_fuse_conn(child_inode); struct inode *inode; struct dentry *parent; struct fuse_entry_out outarg; int err; if (!fc->export_support) return ERR_PTR(-ESTALE); err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode), &dotdot_name, &outarg, &inode); if (err) { if (err == -ENOENT) return ERR_PTR(-ESTALE); return ERR_PTR(err); } parent = d_obtain_alias(inode); if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID) fuse_invalidate_entry_cache(parent); return parent; } /* only for fid encoding; no support for file handle */ static const struct export_operations fuse_export_fid_operations = { .encode_fh = fuse_encode_fh, }; static const struct export_operations fuse_export_operations = { .fh_to_dentry = fuse_fh_to_dentry, .fh_to_parent = fuse_fh_to_parent, .encode_fh = fuse_encode_fh, .get_parent = fuse_get_parent, }; static const struct super_operations fuse_super_operations = { .alloc_inode = fuse_alloc_inode, .free_inode = fuse_free_inode, .evict_inode = fuse_evict_inode, .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, .umount_begin = fuse_umount_begin, .statfs = fuse_statfs, .sync_fs = fuse_sync_fs, .show_options = fuse_show_options, }; static void sanitize_global_limit(unsigned *limit) { /* * The default maximum number of async requests is calculated to consume * 1/2^13 of the total memory, assuming 392 bytes per request. */ if (*limit == 0) *limit = ((totalram_pages() << PAGE_SHIFT) >> 13) / 392; if (*limit >= 1 << 16) *limit = (1 << 16) - 1; } static int set_global_limit(const char *val, const struct kernel_param *kp) { int rv; rv = param_set_uint(val, kp); if (rv) return rv; sanitize_global_limit((unsigned *)kp->arg); return 0; } static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg) { int cap_sys_admin = capable(CAP_SYS_ADMIN); if (arg->minor < 13) return; sanitize_global_limit(&max_user_bgreq); sanitize_global_limit(&max_user_congthresh); spin_lock(&fc->bg_lock); if (arg->max_background) { fc->max_background = arg->max_background; if (!cap_sys_admin && fc->max_background > max_user_bgreq) fc->max_background = max_user_bgreq; } if (arg->congestion_threshold) { fc->congestion_threshold = arg->congestion_threshold; if (!cap_sys_admin && fc->congestion_threshold > max_user_congthresh) fc->congestion_threshold = max_user_congthresh; } spin_unlock(&fc->bg_lock); } struct fuse_init_args { struct fuse_args args; struct fuse_init_in in; struct fuse_init_out out; }; static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, int error) { struct fuse_conn *fc = fm->fc; struct fuse_init_args *ia = container_of(args, typeof(*ia), args); struct fuse_init_out *arg = &ia->out; bool ok = true; if (error || arg->major != FUSE_KERNEL_VERSION) ok = false; else { unsigned long ra_pages; process_init_limits(fc, arg); if (arg->minor >= 6) { u64 flags = arg->flags; if (flags & FUSE_INIT_EXT) flags |= (u64) arg->flags2 << 32; ra_pages = arg->max_readahead / PAGE_SIZE; if (flags & FUSE_ASYNC_READ) fc->async_read = 1; if (!(flags & FUSE_POSIX_LOCKS)) fc->no_lock = 1; if (arg->minor >= 17) { if (!(flags & FUSE_FLOCK_LOCKS)) fc->no_flock = 1; } else { if (!(flags & FUSE_POSIX_LOCKS)) fc->no_flock = 1; } if (flags & FUSE_ATOMIC_O_TRUNC) fc->atomic_o_trunc = 1; if (arg->minor >= 9) { /* LOOKUP has dependency on proto version */ if (flags & FUSE_EXPORT_SUPPORT) fc->export_support = 1; } if (flags & FUSE_BIG_WRITES) fc->big_writes = 1; if (flags & FUSE_DONT_MASK) fc->dont_mask = 1; if (flags & FUSE_AUTO_INVAL_DATA) fc->auto_inval_data = 1; else if (flags & FUSE_EXPLICIT_INVAL_DATA) fc->explicit_inval_data = 1; if (flags & FUSE_DO_READDIRPLUS) { fc->do_readdirplus = 1; if (flags & FUSE_READDIRPLUS_AUTO) fc->readdirplus_auto = 1; } if (flags & FUSE_ASYNC_DIO) fc->async_dio = 1; if (flags & FUSE_WRITEBACK_CACHE) fc->writeback_cache = 1; if (flags & FUSE_PARALLEL_DIROPS) fc->parallel_dirops = 1; if (flags & FUSE_HANDLE_KILLPRIV) fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fm->sb->s_time_gran = arg->time_gran; if ((flags & FUSE_POSIX_ACL)) { fc->default_permissions = 1; fc->posix_acl = 1; } if (flags & FUSE_CACHE_SYMLINKS) fc->cache_symlinks = 1; if (flags & FUSE_ABORT_ERROR) fc->abort_err = 1; if (flags & FUSE_MAX_PAGES) { fc->max_pages = min_t(unsigned int, fc->max_pages_limit, max_t(unsigned int, arg->max_pages, 1)); } if (IS_ENABLED(CONFIG_FUSE_DAX)) { if (flags & FUSE_MAP_ALIGNMENT && !fuse_dax_check_alignment(fc, arg->map_alignment)) { ok = false; } if (flags & FUSE_HAS_INODE_DAX) fc->inode_dax = 1; } if (flags & FUSE_HANDLE_KILLPRIV_V2) { fc->handle_killpriv_v2 = 1; fm->sb->s_flags |= SB_NOSEC; } if (flags & FUSE_SETXATTR_EXT) fc->setxattr_ext = 1; if (flags & FUSE_SECURITY_CTX) fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) fc->direct_io_allow_mmap = 1; /* * max_stack_depth is the max stack depth of FUSE fs, * so it has to be at least 1 to support passthrough * to backing files. * * with max_stack_depth > 1, the backing files can be * on a stacked fs (e.g. overlayfs) themselves and with * max_stack_depth == 1, FUSE fs can be stacked as the * underlying fs of a stacked fs (e.g. overlayfs). */ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) && (flags & FUSE_PASSTHROUGH) && arg->max_stack_depth > 0 && arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) { fc->passthrough = 1; fc->max_stack_depth = arg->max_stack_depth; fm->sb->s_stack_depth = arg->max_stack_depth; } if (flags & FUSE_NO_EXPORT_SUPPORT) fm->sb->s_export_op = &fuse_export_fid_operations; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; fc->no_flock = 1; } fm->sb->s_bdi->ra_pages = min(fm->sb->s_bdi->ra_pages, ra_pages); fc->minor = arg->minor; fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; fc->max_write = max_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } kfree(ia); if (!ok) { fc->conn_init = 0; fc->conn_error = 1; } fuse_set_initialized(fc); wake_up_all(&fc->blocked_waitq); } void fuse_send_init(struct fuse_mount *fm) { struct fuse_init_args *ia; u64 flags; ia = kzalloc(sizeof(*ia), GFP_KERNEL | __GFP_NOFAIL); ia->in.major = FUSE_KERNEL_VERSION; ia->in.minor = FUSE_KERNEL_MINOR_VERSION; ia->in.max_readahead = fm->sb->s_bdi->ra_pages * PAGE_SIZE; flags = FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; if (fuse_is_inode_dax_mode(fm->fc->dax_mode)) flags |= FUSE_HAS_INODE_DAX; #endif if (fm->fc->auto_submounts) flags |= FUSE_SUBMOUNTS; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) flags |= FUSE_PASSTHROUGH; ia->in.flags = flags; ia->in.flags2 = flags >> 32; ia->args.opcode = FUSE_INIT; ia->args.in_numargs = 1; ia->args.in_args[0].size = sizeof(ia->in); ia->args.in_args[0].value = &ia->in; ia->args.out_numargs = 1; /* Variable length argument used for backward compatibility with interface version < 7.5. Rest of init_out is zeroed by do_get_request(), so a short reply is not a problem */ ia->args.out_argvar = true; ia->args.out_args[0].size = sizeof(ia->out); ia->args.out_args[0].value = &ia->out; ia->args.force = true; ia->args.nocreds = true; ia->args.end = process_init_reply; if (fuse_simple_background(fm, &ia->args, GFP_KERNEL) != 0) process_init_reply(fm, &ia->args, -ENOTCONN); } EXPORT_SYMBOL_GPL(fuse_send_init); void fuse_free_conn(struct fuse_conn *fc) { WARN_ON(!list_empty(&fc->devices)); kfree(fc); } EXPORT_SYMBOL_GPL(fuse_free_conn); static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) { int err; char *suffix = ""; if (sb->s_bdev) { suffix = "-fuseblk"; /* * sb->s_bdi points to blkdev's bdi however we want to redirect * it to our private bdi... */ bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev), MINOR(fc->dev), suffix); if (err) return err; /* fuse does it's own writeback accounting */ sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT; sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT; /* * For a single fuse filesystem use max 1% of dirty + * writeback threshold. * * This gives about 1M of write buffer for memory maps on a * machine with 1G and 10% dirty_ratio, which should be more * than enough. * * Privileged users can raise it by writing to * * /sys/class/bdi/<bdi>/max_ratio */ bdi_set_max_ratio(sb->s_bdi, 1); return 0; } struct fuse_dev *fuse_dev_alloc(void) { struct fuse_dev *fud; struct list_head *pq; fud = kzalloc(sizeof(struct fuse_dev), GFP_KERNEL); if (!fud) return NULL; pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!pq) { kfree(fud); return NULL; } fud->pq.processing = pq; fuse_pqueue_init(&fud->pq); return fud; } EXPORT_SYMBOL_GPL(fuse_dev_alloc); void fuse_dev_install(struct fuse_dev *fud, struct fuse_conn *fc) { fud->fc = fuse_conn_get(fc); spin_lock(&fc->lock); list_add_tail(&fud->entry, &fc->devices); spin_unlock(&fc->lock); } EXPORT_SYMBOL_GPL(fuse_dev_install); struct fuse_dev *fuse_dev_alloc_install(struct fuse_conn *fc) { struct fuse_dev *fud; fud = fuse_dev_alloc(); if (!fud) return NULL; fuse_dev_install(fud, fc); return fud; } EXPORT_SYMBOL_GPL(fuse_dev_alloc_install); void fuse_dev_free(struct fuse_dev *fud) { struct fuse_conn *fc = fud->fc; if (fc) { spin_lock(&fc->lock); list_del(&fud->entry); spin_unlock(&fc->lock); fuse_conn_put(fc); } kfree(fud->pq.processing); kfree(fud); } EXPORT_SYMBOL_GPL(fuse_dev_free); static void fuse_fill_attr_from_inode(struct fuse_attr *attr, const struct fuse_inode *fi) { struct timespec64 atime = inode_get_atime(&fi->inode); struct timespec64 mtime = inode_get_mtime(&fi->inode); struct timespec64 ctime = inode_get_ctime(&fi->inode); *attr = (struct fuse_attr){ .ino = fi->inode.i_ino, .size = fi->inode.i_size, .blocks = fi->inode.i_blocks, .atime = atime.tv_sec, .mtime = mtime.tv_sec, .ctime = ctime.tv_sec, .atimensec = atime.tv_nsec, .mtimensec = mtime.tv_nsec, .ctimensec = ctime.tv_nsec, .mode = fi->inode.i_mode, .nlink = fi->inode.i_nlink, .uid = __kuid_val(fi->inode.i_uid), .gid = __kgid_val(fi->inode.i_gid), .rdev = fi->inode.i_rdev, .blksize = 1u << fi->inode.i_blkbits, }; } static void fuse_sb_defaults(struct super_block *sb) { sb->s_magic = FUSE_SUPER_MAGIC; sb->s_op = &fuse_super_operations; sb->s_xattr = fuse_xattr_handlers; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; sb->s_export_op = &fuse_export_operations; sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE; if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); } static int fuse_fill_super_submount(struct super_block *sb, struct fuse_inode *parent_fi) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; struct fuse_submount_lookup *sl; struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi_get(parent_sb->s_bdi); sb->s_xattr = parent_sb->s_xattr; sb->s_export_op = parent_sb->s_export_op; sb->s_time_gran = parent_sb->s_time_gran; sb->s_blocksize = parent_sb->s_blocksize; sb->s_blocksize_bits = parent_sb->s_blocksize_bits; sb->s_subtype = kstrdup(parent_sb->s_subtype, GFP_KERNEL); if (parent_sb->s_subtype && !sb->s_subtype) return -ENOMEM; fuse_fill_attr_from_inode(&root_attr, parent_fi); root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0); /* * This inode is just a duplicate, so it is not looked up and * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ fi = get_fuse_inode(root); fi->nlookup--; sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; /* * Grab the parent's submount_lookup pointer and take a * reference on the shared nlookup from the parent. This is to * prevent the last forget for this nodeid from getting * triggered until all users have finished with it. */ sl = parent_fi->submount_lookup; WARN_ON(!sl); if (sl) { refcount_inc(&sl->count); fi->submount_lookup = sl; } return 0; } /* Filesystem context private data holds the FUSE inode of the mount point */ static int fuse_get_tree_submount(struct fs_context *fsc) { struct fuse_mount *fm; struct fuse_inode *mp_fi = fsc->fs_private; struct fuse_conn *fc = get_fuse_conn(&mp_fi->inode); struct super_block *sb; int err; fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL); if (!fm) return -ENOMEM; fm->fc = fuse_conn_get(fc); fsc->s_fs_info = fm; sb = sget_fc(fsc, NULL, set_anon_super_fc); if (fsc->s_fs_info) fuse_mount_destroy(fm); if (IS_ERR(sb)) return PTR_ERR(sb); /* Initialize superblock, making @mp_fi its root */ err = fuse_fill_super_submount(sb, mp_fi); if (err) { deactivate_locked_super(sb); return err; } down_write(&fc->killsb); list_add_tail(&fm->fc_entry, &fc->mounts); up_write(&fc->killsb); sb->s_flags |= SB_ACTIVE; fsc->root = dget(sb->s_root); return 0; } static const struct fs_context_operations fuse_context_submount_ops = { .get_tree = fuse_get_tree_submount, }; int fuse_init_fs_context_submount(struct fs_context *fsc) { fsc->ops = &fuse_context_submount_ops; return 0; } EXPORT_SYMBOL_GPL(fuse_init_fs_context_submount); int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) { struct fuse_dev *fud = NULL; struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct inode *root; struct dentry *root_dentry; int err; err = -EINVAL; if (sb->s_flags & SB_MANDLOCK) goto err; rcu_assign_pointer(fc->curr_bucket, fuse_sync_bucket_alloc()); fuse_sb_defaults(sb); if (ctx->is_bdev) { #ifdef CONFIG_BLOCK err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; #endif } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; } sb->s_subtype = ctx->subtype; ctx->subtype = NULL; if (IS_ENABLED(CONFIG_FUSE_DAX)) { err = fuse_dax_conn_alloc(fc, ctx->dax_mode, ctx->dax_dev); if (err) goto err; } if (ctx->fudptr) { err = -ENOMEM; fud = fuse_dev_alloc_install(fc); if (!fud) goto err_free_dax; } fc->dev = sb->s_dev; fm->sb = sb; err = fuse_bdi_init(fc, sb); if (err) goto err_dev_free; /* Handle umasking inside the fuse code */ if (sb->s_flags & SB_POSIXACL) fc->dont_mask = 1; sb->s_flags |= SB_POSIXACL; fc->default_permissions = ctx->default_permissions; fc->allow_other = ctx->allow_other; fc->user_id = ctx->user_id; fc->group_id = ctx->group_id; fc->legacy_opts_show = ctx->legacy_opts_show; fc->max_read = max_t(unsigned int, 4096, ctx->max_read); fc->destroy = ctx->destroy; fc->no_control = ctx->no_control; fc->no_force_umount = ctx->no_force_umount; err = -ENOMEM; root = fuse_get_root_inode(sb, ctx->rootmode); sb->s_d_op = &fuse_root_dentry_operations; root_dentry = d_make_root(root); if (!root_dentry) goto err_dev_free; /* Root dentry doesn't have .d_revalidate */ sb->s_d_op = &fuse_dentry_operations; mutex_lock(&fuse_mutex); err = -EINVAL; if (ctx->fudptr && *ctx->fudptr) goto err_unlock; err = fuse_ctl_add_conn(fc); if (err) goto err_unlock; list_add_tail(&fc->entry, &fuse_conn_list); sb->s_root = root_dentry; if (ctx->fudptr) *ctx->fudptr = fud; mutex_unlock(&fuse_mutex); return 0; err_unlock: mutex_unlock(&fuse_mutex); dput(root_dentry); err_dev_free: if (fud) fuse_dev_free(fud); err_free_dax: if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_conn_free(fc); err: return err; } EXPORT_SYMBOL_GPL(fuse_fill_super_common); static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; int err; if (!ctx->file || !ctx->rootmode_present || !ctx->user_id_present || !ctx->group_id_present) return -EINVAL; /* * Require mount to happen from the same user namespace which * opened /dev/fuse to prevent potential attacks. */ if ((ctx->file->f_op != &fuse_dev_operations) || (ctx->file->f_cred->user_ns != sb->s_user_ns)) return -EINVAL; ctx->fudptr = &ctx->file->private_data; err = fuse_fill_super_common(sb, ctx); if (err) return err; /* file->private_data shall be visible on all CPUs after this */ smp_mb(); fuse_send_init(get_fuse_mount_super(sb)); return 0; } /* * This is the path where user supplied an already initialized fuse dev. In * this case never create a new super if the old one is gone. */ static int fuse_set_no_super(struct super_block *sb, struct fs_context *fsc) { return -ENOTCONN; } static int fuse_test_super(struct super_block *sb, struct fs_context *fsc) { return fsc->sget_key == get_fuse_conn_super(sb); } static int fuse_get_tree(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; struct fuse_dev *fud; struct fuse_conn *fc; struct fuse_mount *fm; struct super_block *sb; int err; fc = kmalloc(sizeof(*fc), GFP_KERNEL); if (!fc) return -ENOMEM; fm = kzalloc(sizeof(*fm), GFP_KERNEL); if (!fm) { kfree(fc); return -ENOMEM; } fuse_conn_init(fc, fm, fsc->user_ns, &fuse_dev_fiq_ops, NULL); fc->release = fuse_free_conn; fsc->s_fs_info = fm; if (ctx->fd_present) ctx->file = fget(ctx->fd); if (IS_ENABLED(CONFIG_BLOCK) && ctx->is_bdev) { err = get_tree_bdev(fsc, fuse_fill_super); goto out; } /* * While block dev mount can be initialized with a dummy device fd * (found by device name), normal fuse mounts can't */ err = -EINVAL; if (!ctx->file) goto out; /* * Allow creating a fuse mount with an already initialized fuse * connection */ fud = READ_ONCE(ctx->file->private_data); if (ctx->file->f_op == &fuse_dev_operations && fud) { fsc->sget_key = fud->fc; sb = sget_fc(fsc, fuse_test_super, fuse_set_no_super); err = PTR_ERR_OR_ZERO(sb); if (!IS_ERR(sb)) fsc->root = dget(sb->s_root); } else { err = get_tree_nodev(fsc, fuse_fill_super); } out: if (fsc->s_fs_info) fuse_mount_destroy(fm); if (ctx->file) fput(ctx->file); return err; } static const struct fs_context_operations fuse_context_ops = { .free = fuse_free_fsc, .parse_param = fuse_parse_param, .reconfigure = fuse_reconfigure, .get_tree = fuse_get_tree, }; /* * Set up the filesystem mount context. */ static int fuse_init_fs_context(struct fs_context *fsc) { struct fuse_fs_context *ctx; ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->max_read = ~0; ctx->blksize = FUSE_DEFAULT_BLKSIZE; ctx->legacy_opts_show = true; #ifdef CONFIG_BLOCK if (fsc->fs_type == &fuseblk_fs_type) { ctx->is_bdev = true; ctx->destroy = true; } #endif fsc->fs_private = ctx; fsc->ops = &fuse_context_ops; return 0; } bool fuse_mount_remove(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; bool last = false; down_write(&fc->killsb); list_del_init(&fm->fc_entry); if (list_empty(&fc->mounts)) last = true; up_write(&fc->killsb); return last; } EXPORT_SYMBOL_GPL(fuse_mount_remove); void fuse_conn_destroy(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; if (fc->destroy) fuse_send_destroy(fm); fuse_abort_conn(fc); fuse_wait_aborted(fc); if (!list_empty(&fc->entry)) { mutex_lock(&fuse_mutex); list_del(&fc->entry); fuse_ctl_remove_conn(fc); mutex_unlock(&fuse_mutex); } } EXPORT_SYMBOL_GPL(fuse_conn_destroy); static void fuse_sb_destroy(struct super_block *sb) { struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; if (sb->s_root) { last = fuse_mount_remove(fm); if (last) fuse_conn_destroy(fm); } } void fuse_mount_destroy(struct fuse_mount *fm) { fuse_conn_put(fm->fc); kfree_rcu(fm, rcu); } EXPORT_SYMBOL(fuse_mount_destroy); static void fuse_kill_sb_anon(struct super_block *sb) { fuse_sb_destroy(sb); kill_anon_super(sb); fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuse_fs_type = { .owner = THIS_MODULE, .name = "fuse", .fs_flags = FS_HAS_SUBTYPE | FS_USERNS_MOUNT, .init_fs_context = fuse_init_fs_context, .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_anon, }; MODULE_ALIAS_FS("fuse"); #ifdef CONFIG_BLOCK static void fuse_kill_sb_blk(struct super_block *sb) { fuse_sb_destroy(sb); kill_block_super(sb); fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuseblk_fs_type = { .owner = THIS_MODULE, .name = "fuseblk", .init_fs_context = fuse_init_fs_context, .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_blk, .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, }; MODULE_ALIAS_FS("fuseblk"); static inline int register_fuseblk(void) { return register_filesystem(&fuseblk_fs_type); } static inline void unregister_fuseblk(void) { unregister_filesystem(&fuseblk_fs_type); } #else static inline int register_fuseblk(void) { return 0; } static inline void unregister_fuseblk(void) { } #endif static void fuse_inode_init_once(void *foo) { struct inode *inode = foo; inode_init_once(inode); } static int __init fuse_fs_init(void) { int err; fuse_inode_cachep = kmem_cache_create("fuse_inode", sizeof(struct fuse_inode), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT, fuse_inode_init_once); err = -ENOMEM; if (!fuse_inode_cachep) goto out; err = register_fuseblk(); if (err) goto out2; err = register_filesystem(&fuse_fs_type); if (err) goto out3; return 0; out3: unregister_fuseblk(); out2: kmem_cache_destroy(fuse_inode_cachep); out: return err; } static void fuse_fs_cleanup(void) { unregister_filesystem(&fuse_fs_type); unregister_fuseblk(); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(fuse_inode_cachep); } static struct kobject *fuse_kobj; static int fuse_sysfs_init(void) { int err; fuse_kobj = kobject_create_and_add("fuse", fs_kobj); if (!fuse_kobj) { err = -ENOMEM; goto out_err; } err = sysfs_create_mount_point(fuse_kobj, "connections"); if (err) goto out_fuse_unregister; return 0; out_fuse_unregister: kobject_put(fuse_kobj); out_err: return err; } static void fuse_sysfs_cleanup(void) { sysfs_remove_mount_point(fuse_kobj, "connections"); kobject_put(fuse_kobj); } static int __init fuse_init(void) { int res; pr_info("init (API version %i.%i)\n", FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION); INIT_LIST_HEAD(&fuse_conn_list); res = fuse_fs_init(); if (res) goto err; res = fuse_dev_init(); if (res) goto err_fs_cleanup; res = fuse_sysfs_init(); if (res) goto err_dev_cleanup; res = fuse_ctl_init(); if (res) goto err_sysfs_cleanup; sanitize_global_limit(&max_user_bgreq); sanitize_global_limit(&max_user_congthresh); return 0; err_sysfs_cleanup: fuse_sysfs_cleanup(); err_dev_cleanup: fuse_dev_cleanup(); err_fs_cleanup: fuse_fs_cleanup(); err: return res; } static void __exit fuse_exit(void) { pr_debug("exit\n"); fuse_ctl_cleanup(); fuse_sysfs_cleanup(); fuse_fs_cleanup(); fuse_dev_cleanup(); } module_init(fuse_init); module_exit(fuse_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * algif_skcipher: User-space interface for skcipher algorithms * * This file provides the user-space API for symmetric key ciphers. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> * * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is * filled by user space with the data submitted via sendmsg. Filling up the TX * SGL does not cause a crypto operation -- the data will only be tracked by * the kernel. Upon receipt of one recvmsg call, the caller must provide a * buffer which is tracked with the RX SGL. * * During the processing of the recvmsg operation, the cipher request is * allocated and prepared. As part of the recvmsg operation, the processed * TX buffers are extracted from the TX SGL into a separate SGL. * * After the completion of the crypto operation, the RX SGL and the cipher * request is released. The extracted TX SGL parts are released together with * the RX SGL release. */ #include <crypto/scatterwalk.h> #include <crypto/skcipher.h> #include <crypto/if_alg.h> #include <linux/init.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/net.h> #include <net/sock.h> static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct crypto_skcipher *tfm = pask->private; unsigned ivsize = crypto_skcipher_ivsize(tfm); return af_alg_sendmsg(sock, msg, size, ivsize); } static int algif_skcipher_export(struct sock *sk, struct skcipher_request *req) { struct alg_sock *ask = alg_sk(sk); struct crypto_skcipher *tfm; struct af_alg_ctx *ctx; struct alg_sock *pask; unsigned statesize; struct sock *psk; int err; if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL)) return 0; ctx = ask->private; psk = ask->parent; pask = alg_sk(psk); tfm = pask->private; statesize = crypto_skcipher_statesize(tfm); ctx->state = sock_kmalloc(sk, statesize, GFP_ATOMIC); if (!ctx->state) return -ENOMEM; err = crypto_skcipher_export(req, ctx->state); if (err) { sock_kzfree_s(sk, ctx->state, statesize); ctx->state = NULL; } return err; } static void algif_skcipher_done(void *data, int err) { struct af_alg_async_req *areq = data; struct sock *sk = areq->sk; if (err) goto out; err = algif_skcipher_export(sk, &areq->cra_u.skcipher_req); out: af_alg_async_cb(data, err); } static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct crypto_skcipher *tfm = pask->private; unsigned int bs = crypto_skcipher_chunksize(tfm); struct af_alg_async_req *areq; unsigned cflags = 0; int err = 0; size_t len = 0; if (!ctx->init || (ctx->more && ctx->used < bs)) { err = af_alg_wait_for_data(sk, flags, bs); if (err) return err; } /* Allocate cipher request for current operation. */ areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) + crypto_skcipher_reqsize(tfm)); if (IS_ERR(areq)) return PTR_ERR(areq); /* convert iovecs of output buffers into RX SGL */ err = af_alg_get_rsgl(sk, msg, flags, areq, ctx->used, &len); if (err) goto free; /* * If more buffers are to be expected to be processed, process only * full block size buffers. */ if (ctx->more || len < ctx->used) { len -= len % bs; cflags |= CRYPTO_SKCIPHER_REQ_NOTFINAL; } /* * Create a per request TX SGL for this request which tracks the * SG entries from the global TX SGL. */ areq->tsgl_entries = af_alg_count_tsgl(sk, len, 0); if (!areq->tsgl_entries) areq->tsgl_entries = 1; areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), areq->tsgl_entries), GFP_KERNEL); if (!areq->tsgl) { err = -ENOMEM; goto free; } sg_init_table(areq->tsgl, areq->tsgl_entries); af_alg_pull_tsgl(sk, len, areq->tsgl, 0); /* Initialize the crypto operation */ skcipher_request_set_tfm(&areq->cra_u.skcipher_req, tfm); skcipher_request_set_crypt(&areq->cra_u.skcipher_req, areq->tsgl, areq->first_rsgl.sgl.sgt.sgl, len, ctx->iv); if (ctx->state) { err = crypto_skcipher_import(&areq->cra_u.skcipher_req, ctx->state); sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm)); ctx->state = NULL; if (err) goto free; cflags |= CRYPTO_SKCIPHER_REQ_CONT; } if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) { /* AIO operation */ sock_hold(sk); areq->iocb = msg->msg_iocb; /* Remember output size that will be generated. */ areq->outlen = len; skcipher_request_set_callback(&areq->cra_u.skcipher_req, cflags | CRYPTO_TFM_REQ_MAY_SLEEP, algif_skcipher_done, areq); err = ctx->enc ? crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) : crypto_skcipher_decrypt(&areq->cra_u.skcipher_req); /* AIO operation in progress */ if (err == -EINPROGRESS) return -EIOCBQUEUED; sock_put(sk); } else { /* Synchronous operation */ skcipher_request_set_callback(&areq->cra_u.skcipher_req, cflags | CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &ctx->wait); err = crypto_wait_req(ctx->enc ? crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) : crypto_skcipher_decrypt(&areq->cra_u.skcipher_req), &ctx->wait); if (!err) err = algif_skcipher_export( sk, &areq->cra_u.skcipher_req); } free: af_alg_free_resources(areq); return err ? err : len; } static int skcipher_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; int ret = 0; lock_sock(sk); while (msg_data_left(msg)) { int err = _skcipher_recvmsg(sock, msg, ignored, flags); /* * This error covers -EIOCBQUEUED which implies that we can * only handle one AIO request. If the caller wants to have * multiple AIO requests in parallel, he must make multiple * separate AIO calls. * * Also return the error if no data has been processed so far. */ if (err <= 0) { if (err == -EIOCBQUEUED || !ret) ret = err; goto out; } ret += err; } out: af_alg_wmem_wakeup(sk); release_sock(sk); return ret; } static struct proto_ops algif_skcipher_ops = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = skcipher_sendmsg, .recvmsg = skcipher_recvmsg, .poll = af_alg_poll, }; static int skcipher_check_key(struct socket *sock) { int err = 0; struct sock *psk; struct alg_sock *pask; struct crypto_skcipher *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); lock_sock(sk); if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) goto unlock; atomic_dec(&pask->nokey_refcnt); atomic_set(&ask->nokey_refcnt, 0); err = 0; unlock: release_sock(psk); unlock_child: release_sock(sk); return err; } static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, size_t size) { int err; err = skcipher_check_key(sock); if (err) return err; return skcipher_sendmsg(sock, msg, size); } static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { int err; err = skcipher_check_key(sock); if (err) return err; return skcipher_recvmsg(sock, msg, ignored, flags); } static struct proto_ops algif_skcipher_ops_nokey = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = skcipher_sendmsg_nokey, .recvmsg = skcipher_recvmsg_nokey, .poll = af_alg_poll, }; static void *skcipher_bind(const char *name, u32 type, u32 mask) { return crypto_alloc_skcipher(name, type, mask); } static void skcipher_release(void *private) { crypto_free_skcipher(private); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { return crypto_skcipher_setkey(private, key, keylen); } static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct crypto_skcipher *tfm = pask->private; af_alg_pull_tsgl(sk, ctx->used, NULL, 0); sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); if (ctx->state) sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm)); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct af_alg_ctx *ctx; struct alg_sock *ask = alg_sk(sk); struct crypto_skcipher *tfm = private; unsigned int len = sizeof(*ctx); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; memset(ctx, 0, len); ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(tfm), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } memset(ctx->iv, 0, crypto_skcipher_ivsize(tfm)); INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; crypto_init_wait(&ctx->wait); ask->private = ctx; sk->sk_destruct = skcipher_sock_destruct; return 0; } static int skcipher_accept_parent(void *private, struct sock *sk) { struct crypto_skcipher *tfm = private; if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return skcipher_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; static int __init algif_skcipher_init(void) { return af_alg_register_type(&algif_type_skcipher); } static void __exit algif_skcipher_exit(void) { int err = af_alg_unregister_type(&algif_type_skcipher); BUG_ON(err); } module_init(algif_skcipher_init); module_exit(algif_skcipher_exit); MODULE_LICENSE("GPL"); |
| 3 3 3 2 2 1 2 2 3 3 3 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation */ #include <linux/kernel.h> #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/printk.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> #include <net/gro.h> #include <net/gso.h> #include "ip6_offload.h" /* All GRO functions are always builtin, except UDP over ipv6, which lays in * ipv6 module, as it depends on UDPv6 lookup function, so we need special care * when ipv6 is built as a module */ #if IS_BUILTIN(CONFIG_IPV6) #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #define indirect_call_gro_receive_l4(f2, f1, cb, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ NAPI_GRO_CB(skb)->flush |= 1, NULL : \ INDIRECT_CALL_L4(cb, f2, f1, head, skb); \ }) static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto) { const struct net_offload *ops = NULL; struct ipv6_opt_hdr *opth; for (;;) { int len; ops = rcu_dereference(inet6_offloads[proto]); if (unlikely(!ops)) break; if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) break; opth = skb_gro_header(skb, off + sizeof(*opth), off); if (unlikely(!opth)) break; len = ipv6_optlen(opth); opth = skb_gro_header(skb, off + len, off); if (unlikely(!opth)) break; proto = opth->nexthdr; off += len; } skb_gro_pull(skb, off - skb_gro_receive_network_offset(skb)); return proto; } static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto) { const struct net_offload *ops = NULL; for (;;) { struct ipv6_opt_hdr *opth; int len; ops = rcu_dereference(inet6_offloads[proto]); if (unlikely(!ops)) break; if (!(ops->flags & INET6_PROTO_GSO_EXTHDR)) break; if (unlikely(!pskb_may_pull(skb, 8))) break; opth = (void *)skb->data; len = ipv6_optlen(opth); if (unlikely(!pskb_may_pull(skb, len))) break; opth = (void *)skb->data; proto = opth->nexthdr; __skb_pull(skb, len); } return proto; } static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; const struct net_offload *ops; int proto, err; struct frag_hdr *fptr; unsigned int payload_len; u8 *prevhdr; int offset = 0; bool encap, udpfrag; int nhoff; bool gso_partial; skb_reset_network_header(skb); err = ipv6_hopopt_jumbo_remove(skb); if (err) return ERR_PTR(err); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); ipv6h = ipv6_hdr(skb); __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6)) udpfrag = proto == IPPROTO_UDP && encap && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); else udpfrag = proto == IPPROTO_UDP && !skb->encapsulation && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); if (gso_partial && skb_is_gso(skb)) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); else payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) { kfree_skb_list(segs); return ERR_PTR(err); } fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) fptr->frag_off |= htons(IP6_MF); offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); } if (encap) skb_reset_inner_headers(skb); } out: return segs; } /* Return the total length of all the extension hdrs, following the same * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs. */ static int ipv6_exthdrs_len(struct ipv6hdr *iph, const struct net_offload **opps) { struct ipv6_opt_hdr *opth = (void *)iph; int len = 0, proto, optlen = sizeof(*iph); proto = iph->nexthdr; for (;;) { *opps = rcu_dereference(inet6_offloads[proto]); if (unlikely(!(*opps))) break; if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR)) break; opth = (void *)opth + optlen; optlen = ipv6_optlen(opth); len += optlen; proto = opth->nexthdr; } return len; } INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; struct ipv6hdr *iph; unsigned int nlen; unsigned int hlen; unsigned int off; u16 flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header(skb, hlen, off); if (unlikely(!iph)) goto out; NAPI_GRO_CB(skb)->inner_network_offset = off; flush += ntohs(iph->payload_len) != skb->len - hlen; proto = iph->nexthdr; ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) { proto = ipv6_gro_pull_exthdrs(skb, hlen, proto); ops = rcu_dereference(inet6_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; iph = skb_gro_network_header(skb); } else { skb_gro_pull(skb, sizeof(*iph)); } skb_set_transport_header(skb, skb_gro_offset(skb)); NAPI_GRO_CB(skb)->proto = proto; flush--; nlen = skb_gro_offset(skb) - off; list_for_each_entry(p, head, list) { const struct ipv6hdr *iph2; __be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */ if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct ipv6hdr *)(p->data + off); first_word = *(__be32 *)iph ^ *(__be32 *)iph2; /* All fields must match except length and Traffic Class. * XXX skbs on the gro_list have all been parsed and pulled * already so we don't need to compare nlen * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops))) * memcmp() alone below is sufficient, right? */ if ((first_word & htonl(0xF00FFFFF)) || !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || iph->nexthdr != iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; } if (unlikely(nlen > sizeof(struct ipv6hdr))) { if (memcmp(iph + 1, iph2 + 1, nlen - sizeof(struct ipv6hdr))) goto not_same_flow; } } NAPI_GRO_CB(skb)->flush |= flush; skb_gro_postpull_rcsum(skb, iph, nlen); pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive, ops->callbacks.gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return ipv6_gro_receive(head, skb); } static struct sk_buff *ip4ip6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Common GRO receive for SIT and IP6IP6 */ if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) { const struct net_offload *ops; struct ipv6hdr *iph; int err = -ENOSYS; u32 payload_len; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6)); skb_set_inner_network_header(skb, nhoff); } payload_len = skb->len - nhoff - sizeof(*iph); if (unlikely(payload_len > IPV6_MAXPLEN)) { struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); /* Move network header left */ memmove(skb_mac_header(skb) - hoplen, skb_mac_header(skb), skb->transport_header - skb->mac_header); skb->data -= hoplen; skb->len += hoplen; skb->mac_header -= hoplen; skb->network_header -= hoplen; iph = (struct ipv6hdr *)(skb->data + nhoff); hop_jumbo = (struct hop_jumbo_hdr *)(iph + 1); /* Build hop-by-hop options */ hop_jumbo->nexthdr = iph->nexthdr; hop_jumbo->hdrlen = 0; hop_jumbo->tlv_type = IPV6_TLV_JUMBO; hop_jumbo->tlv_len = 4; hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen); iph->nexthdr = NEXTHDR_HOP; iph->payload_len = 0; } else { iph = (struct ipv6hdr *)(skb->data + nhoff); iph->payload_len = htons(payload_len); } nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete, udp6_gro_complete, skb, nhoff); out: return err; } static int sit_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return ipv6_gro_complete(skb, nhoff); } static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; return ipv6_gro_complete(skb, nhoff); } static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; return inet_gro_complete(skb, nhoff); } static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return ipv6_gso_segment(skb, features); } static struct sk_buff *ip4ip6_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } static struct sk_buff *ip6ip6_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6)) return ERR_PTR(-EINVAL); return ipv6_gso_segment(skb, features); } static const struct net_offload sit_offload = { .callbacks = { .gso_segment = sit_gso_segment, .gro_receive = sit_ip6ip6_gro_receive, .gro_complete = sit_gro_complete, }, }; static const struct net_offload ip4ip6_offload = { .callbacks = { .gso_segment = ip4ip6_gso_segment, .gro_receive = ip4ip6_gro_receive, .gro_complete = ip4ip6_gro_complete, }, }; static const struct net_offload ip6ip6_offload = { .callbacks = { .gso_segment = ip6ip6_gso_segment, .gro_receive = sit_ip6ip6_gro_receive, .gro_complete = ip6ip6_gro_complete, }, }; static int __init ipv6_offload_init(void) { if (tcpv6_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); net_hotdata.ipv6_packet_offload = (struct packet_offload) { .type = cpu_to_be16(ETH_P_IPV6), .callbacks = { .gso_segment = ipv6_gso_segment, .gro_receive = ipv6_gro_receive, .gro_complete = ipv6_gro_complete, }, }; dev_add_offload(&net_hotdata.ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP); return 0; } fs_initcall(ipv6_offload_init); |
| 61 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * pm_wakeup.h - Power management wakeup interface * * Copyright (C) 2008 Alan Stern * Copyright (C) 2010 Rafael J. Wysocki, Novell Inc. */ #ifndef _LINUX_PM_WAKEUP_H #define _LINUX_PM_WAKEUP_H #ifndef _DEVICE_H_ # error "please don't include this file directly" #endif #include <linux/types.h> struct wake_irq; /** * struct wakeup_source - Representation of wakeup sources * * @name: Name of the wakeup source * @id: Wakeup source id * @entry: Wakeup source list entry * @lock: Wakeup source lock * @wakeirq: Optional device specific wakeirq * @timer: Wakeup timer list * @timer_expires: Wakeup timer expiration * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. * @last_time: Monotonic clock when the wakeup source's was touched last time. * @prevent_sleep_time: Total time this source has been preventing autosleep. * @event_count: Number of signaled wakeup events. * @active_count: Number of times the wakeup source was activated. * @relax_count: Number of times the wakeup source was deactivated. * @expire_count: Number of times the wakeup source's timeout has expired. * @wakeup_count: Number of times the wakeup source might abort suspend. * @dev: Struct device for sysfs statistics about the wakeup source. * @active: Status of the wakeup source. * @autosleep_enabled: Autosleep is active, so update @prevent_sleep_time. */ struct wakeup_source { const char *name; int id; struct list_head entry; spinlock_t lock; struct wake_irq *wakeirq; struct timer_list timer; unsigned long timer_expires; ktime_t total_time; ktime_t max_time; ktime_t last_time; ktime_t start_prevent_time; ktime_t prevent_sleep_time; unsigned long event_count; unsigned long active_count; unsigned long relax_count; unsigned long expire_count; unsigned long wakeup_count; struct device *dev; bool active:1; bool autosleep_enabled:1; }; #define for_each_wakeup_source(ws) \ for ((ws) = wakeup_sources_walk_start(); \ (ws); \ (ws) = wakeup_sources_walk_next((ws))) #ifdef CONFIG_PM_SLEEP /* * Changes to device_may_wakeup take effect on the next pm state change. */ static inline bool device_can_wakeup(struct device *dev) { return dev->power.can_wakeup; } static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && !!dev->power.wakeup; } static inline bool device_wakeup_path(struct device *dev) { return dev->power.wakeup_path; } static inline void device_set_wakeup_path(struct device *dev) { dev->power.wakeup_path = true; } /* drivers/base/power/wakeup.c */ extern struct wakeup_source *wakeup_source_create(const char *name); extern void wakeup_source_destroy(struct wakeup_source *ws); extern void wakeup_source_add(struct wakeup_source *ws); extern void wakeup_source_remove(struct wakeup_source *ws); extern struct wakeup_source *wakeup_source_register(struct device *dev, const char *name); extern void wakeup_source_unregister(struct wakeup_source *ws); extern int wakeup_sources_read_lock(void); extern void wakeup_sources_read_unlock(int idx); extern struct wakeup_source *wakeup_sources_walk_start(void); extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern void device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); extern void pm_stay_awake(struct device *dev); extern void __pm_relax(struct wakeup_source *ws); extern void pm_relax(struct device *dev); extern void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard); extern void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard); #else /* !CONFIG_PM_SLEEP */ static inline void device_set_wakeup_capable(struct device *dev, bool capable) { dev->power.can_wakeup = capable; } static inline bool device_can_wakeup(struct device *dev) { return dev->power.can_wakeup; } static inline struct wakeup_source *wakeup_source_create(const char *name) { return NULL; } static inline void wakeup_source_destroy(struct wakeup_source *ws) {} static inline void wakeup_source_add(struct wakeup_source *ws) {} static inline void wakeup_source_remove(struct wakeup_source *ws) {} static inline struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { return NULL; } static inline void wakeup_source_unregister(struct wakeup_source *ws) {} static inline int device_wakeup_enable(struct device *dev) { dev->power.should_wakeup = true; return 0; } static inline void device_wakeup_disable(struct device *dev) { dev->power.should_wakeup = false; } static inline int device_set_wakeup_enable(struct device *dev, bool enable) { dev->power.should_wakeup = enable; return 0; } static inline bool device_may_wakeup(struct device *dev) { return dev->power.can_wakeup && dev->power.should_wakeup; } static inline bool device_wakeup_path(struct device *dev) { return false; } static inline void device_set_wakeup_path(struct device *dev) {} static inline void __pm_stay_awake(struct wakeup_source *ws) {} static inline void pm_stay_awake(struct device *dev) {} static inline void __pm_relax(struct wakeup_source *ws) {} static inline void pm_relax(struct device *dev) {} static inline void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) {} static inline void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) {} #endif /* !CONFIG_PM_SLEEP */ static inline bool device_awake_path(struct device *dev) { return device_wakeup_path(dev); } static inline void device_set_awake_path(struct device *dev) { device_set_wakeup_path(dev); } static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) { return pm_wakeup_ws_event(ws, msec, false); } static inline void pm_wakeup_event(struct device *dev, unsigned int msec) { return pm_wakeup_dev_event(dev, msec, false); } static inline void pm_wakeup_hard_event(struct device *dev) { return pm_wakeup_dev_event(dev, 0, true); } /** * device_init_wakeup - Device wakeup initialization. * @dev: Device to handle. * @enable: Whether or not to enable @dev as a wakeup device. * * By default, most devices should leave wakeup disabled. The exceptions are * devices that everyone expects to be wakeup sources: keyboards, power buttons, * possibly network interfaces, etc. Also, devices that don't generate their * own wakeup requests but merely forward requests from one bus to another * (like PCI bridges) should have wakeup enabled by default. */ static inline int device_init_wakeup(struct device *dev, bool enable) { if (enable) { device_set_wakeup_capable(dev, true); return device_wakeup_enable(dev); } device_wakeup_disable(dev); device_set_wakeup_capable(dev, false); return 0; } #endif /* _LINUX_PM_WAKEUP_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_RTNETLINK_H #define __NET_RTNETLINK_H #include <linux/rtnetlink.h> #include <net/netlink.h> typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), }; enum rtnl_kinds { RTNL_KIND_NEW, RTNL_KIND_DEL, RTNL_KIND_GET, RTNL_KIND_SET }; #define RTNL_KIND_MASK 0x3 static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) { return msgtype & RTNL_KIND_MASK; } void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_register_module(struct module *owner, int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_unregister(int protocol, int msgtype); void rtnl_unregister_all(int protocol); static inline int rtnl_msg_family(const struct nlmsghdr *nlh) { if (nlmsg_len(nlh) >= sizeof(struct rtgenmsg)) return ((struct rtgenmsg *) nlmsg_data(nlh))->rtgen_family; else return AF_UNSPEC; } /** * struct rtnl_link_ops - rtnetlink link operations * * @list: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters * @alloc: netdev allocation function, can be %NULL and is then used * in place of alloc_netdev_mqs(), in this case @priv_size * and @setup are unused. Returns a netdev or ERR_PTR(). * @priv_size: sizeof net_device private space * @setup: net_device setup function * @newlink: Function for configuring and registering a new device * @changelink: Function for changing parameters of an existing device * @dellink: Function to remove a device * @get_size: Function to calculate required room for dumping device * specific netlink attributes * @fill_info: Function to dump device specific netlink attributes * @get_xstats_size: Function to calculate required room for dumping device * specific statistics * @fill_xstats: Function to dump device specific statistics * @get_num_tx_queues: Function to determine number of transmit queues * to create when creating a new device. * @get_num_rx_queues: Function to determine number of receive queues * to create when creating a new device. * @get_link_net: Function to get the i/o netns of the device * @get_linkxstats_size: Function to calculate the required room for * dumping device-specific extended link stats * @fill_linkxstats: Function to dump device-specific extended link stats */ struct rtnl_link_ops { struct list_head list; const char *kind; size_t priv_size; struct net_device *(*alloc)(struct nlattr *tb[], const char *ifname, unsigned char name_assign_type, unsigned int num_tx_queues, unsigned int num_rx_queues); void (*setup)(struct net_device *dev); bool netns_refund; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); int (*newlink)(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); void (*dellink)(struct net_device *dev, struct list_head *head); size_t (*get_size)(const struct net_device *dev); int (*fill_info)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_xstats_size)(const struct net_device *dev); int (*fill_xstats)(struct sk_buff *skb, const struct net_device *dev); unsigned int (*get_num_tx_queues)(void); unsigned int (*get_num_rx_queues)(void); unsigned int slave_maxtype; const struct nla_policy *slave_policy; int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); size_t (*get_slave_size)(const struct net_device *dev, const struct net_device *slave_dev); int (*fill_slave_info)(struct sk_buff *skb, const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); size_t (*get_linkxstats_size)(const struct net_device *dev, int attr); int (*fill_linkxstats)(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr); }; int __rtnl_link_register(struct rtnl_link_ops *ops); void __rtnl_link_unregister(struct rtnl_link_ops *ops); int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); /** * struct rtnl_af_ops - rtnetlink address family operations * * @list: Used internally * @family: Address family * @fill_link_af: Function to fill IFLA_AF_SPEC with address family * specific netlink attributes. * @get_link_af_size: Function to calculate size of address family specific * netlink attributes. * @validate_link_af: Validate a IFLA_AF_SPEC attribute, must check attr * for invalid configuration settings. * @set_link_af: Function to parse a IFLA_AF_SPEC attribute and modify * net_device accordingly. */ struct rtnl_af_ops { struct list_head list; int family; int (*fill_link_af)(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev, u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*fill_stats_af)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_stats_af_size)(const struct net_device *dev); }; void rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[], struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, u32 portid, const struct nlmsghdr *nlh); int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) #endif |
| 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Hardware dependent layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/major.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <sound/core.h> #include <sound/control.h> #include <sound/minors.h> #include <sound/hwdep.h> #include <sound/info.h> MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("Hardware dependent layer"); MODULE_LICENSE("GPL"); static LIST_HEAD(snd_hwdep_devices); static DEFINE_MUTEX(register_mutex); static int snd_hwdep_dev_free(struct snd_device *device); static int snd_hwdep_dev_register(struct snd_device *device); static int snd_hwdep_dev_disconnect(struct snd_device *device); static struct snd_hwdep *snd_hwdep_search(struct snd_card *card, int device) { struct snd_hwdep *hwdep; list_for_each_entry(hwdep, &snd_hwdep_devices, list) if (hwdep->card == card && hwdep->device == device) return hwdep; return NULL; } static loff_t snd_hwdep_llseek(struct file * file, loff_t offset, int orig) { struct snd_hwdep *hw = file->private_data; if (hw->ops.llseek) return hw->ops.llseek(hw, file, offset, orig); return -ENXIO; } static ssize_t snd_hwdep_read(struct file * file, char __user *buf, size_t count, loff_t *offset) { struct snd_hwdep *hw = file->private_data; if (hw->ops.read) return hw->ops.read(hw, buf, count, offset); return -ENXIO; } static ssize_t snd_hwdep_write(struct file * file, const char __user *buf, size_t count, loff_t *offset) { struct snd_hwdep *hw = file->private_data; if (hw->ops.write) return hw->ops.write(hw, buf, count, offset); return -ENXIO; } static int snd_hwdep_open(struct inode *inode, struct file * file) { int major = imajor(inode); struct snd_hwdep *hw; int err; wait_queue_entry_t wait; if (major == snd_major) { hw = snd_lookup_minor_data(iminor(inode), SNDRV_DEVICE_TYPE_HWDEP); #ifdef CONFIG_SND_OSSEMUL } else if (major == SOUND_MAJOR) { hw = snd_lookup_oss_minor_data(iminor(inode), SNDRV_OSS_DEVICE_TYPE_DMFM); #endif } else return -ENXIO; if (hw == NULL) return -ENODEV; if (!try_module_get(hw->card->module)) { snd_card_unref(hw->card); return -EFAULT; } init_waitqueue_entry(&wait, current); add_wait_queue(&hw->open_wait, &wait); mutex_lock(&hw->open_mutex); while (1) { if (hw->exclusive && hw->used > 0) { err = -EBUSY; break; } if (!hw->ops.open) { err = 0; break; } err = hw->ops.open(hw, file); if (err >= 0) break; if (err == -EAGAIN) { if (file->f_flags & O_NONBLOCK) { err = -EBUSY; break; } } else break; set_current_state(TASK_INTERRUPTIBLE); mutex_unlock(&hw->open_mutex); schedule(); mutex_lock(&hw->open_mutex); if (hw->card->shutdown) { err = -ENODEV; break; } if (signal_pending(current)) { err = -ERESTARTSYS; break; } } remove_wait_queue(&hw->open_wait, &wait); if (err >= 0) { err = snd_card_file_add(hw->card, file); if (err >= 0) { file->private_data = hw; hw->used++; } else { if (hw->ops.release) hw->ops.release(hw, file); } } mutex_unlock(&hw->open_mutex); if (err < 0) module_put(hw->card->module); snd_card_unref(hw->card); return err; } static int snd_hwdep_release(struct inode *inode, struct file * file) { int err = 0; struct snd_hwdep *hw = file->private_data; struct module *mod = hw->card->module; scoped_guard(mutex, &hw->open_mutex) { if (hw->ops.release) err = hw->ops.release(hw, file); if (hw->used > 0) hw->used--; } wake_up(&hw->open_wait); snd_card_file_remove(hw->card, file); module_put(mod); return err; } static __poll_t snd_hwdep_poll(struct file * file, poll_table * wait) { struct snd_hwdep *hw = file->private_data; if (hw->ops.poll) return hw->ops.poll(hw, file, wait); return 0; } static int snd_hwdep_info(struct snd_hwdep *hw, struct snd_hwdep_info __user *_info) { struct snd_hwdep_info info; memset(&info, 0, sizeof(info)); info.card = hw->card->number; strscpy(info.id, hw->id, sizeof(info.id)); strscpy(info.name, hw->name, sizeof(info.name)); info.iface = hw->iface; if (copy_to_user(_info, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_hwdep_dsp_status(struct snd_hwdep *hw, struct snd_hwdep_dsp_status __user *_info) { struct snd_hwdep_dsp_status info; int err; if (! hw->ops.dsp_status) return -ENXIO; memset(&info, 0, sizeof(info)); info.dsp_loaded = hw->dsp_loaded; err = hw->ops.dsp_status(hw, &info); if (err < 0) return err; if (copy_to_user(_info, &info, sizeof(info))) return -EFAULT; return 0; } static int snd_hwdep_dsp_load(struct snd_hwdep *hw, struct snd_hwdep_dsp_image *info) { int err; if (! hw->ops.dsp_load) return -ENXIO; if (info->index >= 32) return -EINVAL; /* check whether the dsp was already loaded */ if (hw->dsp_loaded & (1u << info->index)) return -EBUSY; err = hw->ops.dsp_load(hw, info); if (err < 0) return err; hw->dsp_loaded |= (1u << info->index); return 0; } static int snd_hwdep_dsp_load_user(struct snd_hwdep *hw, struct snd_hwdep_dsp_image __user *_info) { struct snd_hwdep_dsp_image info = {}; if (copy_from_user(&info, _info, sizeof(info))) return -EFAULT; return snd_hwdep_dsp_load(hw, &info); } static long snd_hwdep_ioctl(struct file * file, unsigned int cmd, unsigned long arg) { struct snd_hwdep *hw = file->private_data; void __user *argp = (void __user *)arg; switch (cmd) { case SNDRV_HWDEP_IOCTL_PVERSION: return put_user(SNDRV_HWDEP_VERSION, (int __user *)argp); case SNDRV_HWDEP_IOCTL_INFO: return snd_hwdep_info(hw, argp); case SNDRV_HWDEP_IOCTL_DSP_STATUS: return snd_hwdep_dsp_status(hw, argp); case SNDRV_HWDEP_IOCTL_DSP_LOAD: return snd_hwdep_dsp_load_user(hw, argp); } if (hw->ops.ioctl) return hw->ops.ioctl(hw, file, cmd, arg); return -ENOTTY; } static int snd_hwdep_mmap(struct file * file, struct vm_area_struct * vma) { struct snd_hwdep *hw = file->private_data; if (hw->ops.mmap) return hw->ops.mmap(hw, file, vma); return -ENXIO; } static int snd_hwdep_control_ioctl(struct snd_card *card, struct snd_ctl_file * control, unsigned int cmd, unsigned long arg) { switch (cmd) { case SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE: { int device; if (get_user(device, (int __user *)arg)) return -EFAULT; scoped_guard(mutex, ®ister_mutex) { if (device < 0) device = 0; else if (device < SNDRV_MINOR_HWDEPS) device++; else device = SNDRV_MINOR_HWDEPS; while (device < SNDRV_MINOR_HWDEPS) { if (snd_hwdep_search(card, device)) break; device++; } if (device >= SNDRV_MINOR_HWDEPS) device = -1; } if (put_user(device, (int __user *)arg)) return -EFAULT; return 0; } case SNDRV_CTL_IOCTL_HWDEP_INFO: { struct snd_hwdep_info __user *info = (struct snd_hwdep_info __user *)arg; int device; struct snd_hwdep *hwdep; if (get_user(device, &info->device)) return -EFAULT; scoped_guard(mutex, ®ister_mutex) { hwdep = snd_hwdep_search(card, device); if (!hwdep) return -ENXIO; return snd_hwdep_info(hwdep, info); } break; } } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT #include "hwdep_compat.c" #else #define snd_hwdep_ioctl_compat NULL #endif /* */ static const struct file_operations snd_hwdep_f_ops = { .owner = THIS_MODULE, .llseek = snd_hwdep_llseek, .read = snd_hwdep_read, .write = snd_hwdep_write, .open = snd_hwdep_open, .release = snd_hwdep_release, .poll = snd_hwdep_poll, .unlocked_ioctl = snd_hwdep_ioctl, .compat_ioctl = snd_hwdep_ioctl_compat, .mmap = snd_hwdep_mmap, }; static void snd_hwdep_free(struct snd_hwdep *hwdep) { if (!hwdep) return; if (hwdep->private_free) hwdep->private_free(hwdep); put_device(hwdep->dev); kfree(hwdep); } /** * snd_hwdep_new - create a new hwdep instance * @card: the card instance * @id: the id string * @device: the device index (zero-based) * @rhwdep: the pointer to store the new hwdep instance * * Creates a new hwdep instance with the given index on the card. * The callbacks (hwdep->ops) must be set on the returned instance * after this call manually by the caller. * * Return: Zero if successful, or a negative error code on failure. */ int snd_hwdep_new(struct snd_card *card, char *id, int device, struct snd_hwdep **rhwdep) { struct snd_hwdep *hwdep; int err; static const struct snd_device_ops ops = { .dev_free = snd_hwdep_dev_free, .dev_register = snd_hwdep_dev_register, .dev_disconnect = snd_hwdep_dev_disconnect, }; if (snd_BUG_ON(!card)) return -ENXIO; if (rhwdep) *rhwdep = NULL; hwdep = kzalloc(sizeof(*hwdep), GFP_KERNEL); if (!hwdep) return -ENOMEM; init_waitqueue_head(&hwdep->open_wait); mutex_init(&hwdep->open_mutex); hwdep->card = card; hwdep->device = device; if (id) strscpy(hwdep->id, id, sizeof(hwdep->id)); err = snd_device_alloc(&hwdep->dev, card); if (err < 0) { snd_hwdep_free(hwdep); return err; } dev_set_name(hwdep->dev, "hwC%iD%i", card->number, device); #ifdef CONFIG_SND_OSSEMUL hwdep->oss_type = -1; #endif err = snd_device_new(card, SNDRV_DEV_HWDEP, hwdep, &ops); if (err < 0) { snd_hwdep_free(hwdep); return err; } if (rhwdep) *rhwdep = hwdep; return 0; } EXPORT_SYMBOL(snd_hwdep_new); static int snd_hwdep_dev_free(struct snd_device *device) { snd_hwdep_free(device->device_data); return 0; } static int snd_hwdep_dev_register(struct snd_device *device) { struct snd_hwdep *hwdep = device->device_data; struct snd_card *card = hwdep->card; int err; guard(mutex)(®ister_mutex); if (snd_hwdep_search(card, hwdep->device)) return -EBUSY; list_add_tail(&hwdep->list, &snd_hwdep_devices); err = snd_register_device(SNDRV_DEVICE_TYPE_HWDEP, hwdep->card, hwdep->device, &snd_hwdep_f_ops, hwdep, hwdep->dev); if (err < 0) { dev_err(hwdep->dev, "unable to register\n"); list_del(&hwdep->list); return err; } #ifdef CONFIG_SND_OSSEMUL hwdep->ossreg = 0; if (hwdep->oss_type >= 0) { if (hwdep->oss_type == SNDRV_OSS_DEVICE_TYPE_DMFM && hwdep->device) dev_warn(hwdep->dev, "only hwdep device 0 can be registered as OSS direct FM device!\n"); else if (snd_register_oss_device(hwdep->oss_type, card, hwdep->device, &snd_hwdep_f_ops, hwdep) < 0) dev_warn(hwdep->dev, "unable to register OSS compatibility device\n"); else hwdep->ossreg = 1; } #endif return 0; } static int snd_hwdep_dev_disconnect(struct snd_device *device) { struct snd_hwdep *hwdep = device->device_data; if (snd_BUG_ON(!hwdep)) return -ENXIO; guard(mutex)(®ister_mutex); if (snd_hwdep_search(hwdep->card, hwdep->device) != hwdep) return -EINVAL; guard(mutex)(&hwdep->open_mutex); wake_up(&hwdep->open_wait); #ifdef CONFIG_SND_OSSEMUL if (hwdep->ossreg) snd_unregister_oss_device(hwdep->oss_type, hwdep->card, hwdep->device); #endif snd_unregister_device(hwdep->dev); list_del_init(&hwdep->list); return 0; } #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_hwdep_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_hwdep *hwdep; guard(mutex)(®ister_mutex); list_for_each_entry(hwdep, &snd_hwdep_devices, list) snd_iprintf(buffer, "%02i-%02i: %s\n", hwdep->card->number, hwdep->device, hwdep->name); } static struct snd_info_entry *snd_hwdep_proc_entry; static void __init snd_hwdep_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "hwdep", NULL); if (entry) { entry->c.text.read = snd_hwdep_proc_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_hwdep_proc_entry = entry; } static void __exit snd_hwdep_proc_done(void) { snd_info_free_entry(snd_hwdep_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_hwdep_proc_init() #define snd_hwdep_proc_done() #endif /* CONFIG_SND_PROC_FS */ /* * ENTRY functions */ static int __init alsa_hwdep_init(void) { snd_hwdep_proc_init(); snd_ctl_register_ioctl(snd_hwdep_control_ioctl); snd_ctl_register_ioctl_compat(snd_hwdep_control_ioctl); return 0; } static void __exit alsa_hwdep_exit(void) { snd_ctl_unregister_ioctl(snd_hwdep_control_ioctl); snd_ctl_unregister_ioctl_compat(snd_hwdep_control_ioctl); snd_hwdep_proc_done(); } module_init(alsa_hwdep_init) module_exit(alsa_hwdep_exit) |
| 171 | 1 2 3 4 5 6 7 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 */ #ifndef __ASM_GENERIC_MMIOWB_H #define __ASM_GENERIC_MMIOWB_H /* * Generic implementation of mmiowb() tracking for spinlocks. * * If your architecture doesn't ensure that writes to an I/O peripheral * within two spinlocked sections on two different CPUs are seen by the * peripheral in the order corresponding to the lock handover, then you * need to follow these FIVE easy steps: * * 1. Implement mmiowb() (and arch_mmiowb_state() if you're fancy) * in asm/mmiowb.h, then #include this file * 2. Ensure your I/O write accessors call mmiowb_set_pending() * 3. Select ARCH_HAS_MMIOWB * 4. Untangle the resulting mess of header files * 5. Complain to your architects */ #ifdef CONFIG_MMIOWB #include <linux/compiler.h> #include <asm-generic/mmiowb_types.h> #ifndef arch_mmiowb_state #include <asm/percpu.h> #include <asm/smp.h> DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state); #define __mmiowb_state() raw_cpu_ptr(&__mmiowb_state) #else #define __mmiowb_state() arch_mmiowb_state() #endif /* arch_mmiowb_state */ static inline void mmiowb_set_pending(void) { struct mmiowb_state *ms = __mmiowb_state(); if (likely(ms->nesting_count)) ms->mmiowb_pending = ms->nesting_count; } static inline void mmiowb_spin_lock(void) { struct mmiowb_state *ms = __mmiowb_state(); ms->nesting_count++; } static inline void mmiowb_spin_unlock(void) { struct mmiowb_state *ms = __mmiowb_state(); if (unlikely(ms->mmiowb_pending)) { ms->mmiowb_pending = 0; mmiowb(); } ms->nesting_count--; } #else #define mmiowb_set_pending() do { } while (0) #define mmiowb_spin_lock() do { } while (0) #define mmiowb_spin_unlock() do { } while (0) #endif /* CONFIG_MMIOWB */ #endif /* __ASM_GENERIC_MMIOWB_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 48 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header */ skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *master, unsigned long *interval) { struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (hsr->redbox) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX; dev->features = dev->hw_features; /* Prevent recursive tx locking */ dev->features |= NETIF_F_LLTX; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* Not sure about this. Taken from bridge code. netdev_features.h says * it means "Does not change network namespaces". */ dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 25 25 25 25 25 25 25 25 25 8 8 8 8 7 2 2 27 27 36 36 6 6 55 56 55 56 8 8 8 8 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 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 | // SPDX-License-Identifier: GPL-2.0 /* * Performance events core code: * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ #include <linux/fs.h> #include <linux/mm.h> #include <linux/cpu.h> #include <linux/smp.h> #include <linux/idr.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/tick.h> #include <linux/sysfs.h> #include <linux/dcache.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/reboot.h> #include <linux/vmstat.h> #include <linux/device.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/hardirq.h> #include <linux/hugetlb.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> #include <linux/cgroup.h> #include <linux/perf_event.h> #include <linux/trace_events.h> #include <linux/hw_breakpoint.h> #include <linux/mm_types.h> #include <linux/module.h> #include <linux/mman.h> #include <linux/compat.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/namei.h> #include <linux/parser.h> #include <linux/sched/clock.h> #include <linux/sched/mm.h> #include <linux/proc_ns.h> #include <linux/mount.h> #include <linux/min_heap.h> #include <linux/highmem.h> #include <linux/pgtable.h> #include <linux/buildid.h> #include <linux/task_work.h> #include "internal.h" #include <asm/irq_regs.h> typedef int (*remote_function_f)(void *); struct remote_function_call { struct task_struct *p; remote_function_f func; void *info; int ret; }; static void remote_function(void *data) { struct remote_function_call *tfc = data; struct task_struct *p = tfc->p; if (p) { /* -EAGAIN */ if (task_cpu(p) != smp_processor_id()) return; /* * Now that we're on right CPU with IRQs disabled, we can test * if we hit the right task without races. */ tfc->ret = -ESRCH; /* No such (running) process */ if (p != current) return; } tfc->ret = tfc->func(tfc->info); } /** * task_function_call - call a function on the cpu on which a task runs * @p: the task to evaluate * @func: the function to be called * @info: the function call argument * * Calls the function @func when the task is currently running. This might * be on the current CPU, which just calls the function directly. This will * retry due to any failures in smp_call_function_single(), such as if the * task_cpu() goes offline concurrently. * * returns @func return value or -ESRCH or -ENXIO when the process isn't running */ static int task_function_call(struct task_struct *p, remote_function_f func, void *info) { struct remote_function_call data = { .p = p, .func = func, .info = info, .ret = -EAGAIN, }; int ret; for (;;) { ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); if (!ret) ret = data.ret; if (ret != -EAGAIN) break; cond_resched(); } return ret; } /** * cpu_function_call - call a function on the cpu * @cpu: target cpu to queue this function * @func: the function to be called * @info: the function call argument * * Calls the function @func on the remote cpu. * * returns: @func return value or -ENXIO when the cpu is offline */ static int cpu_function_call(int cpu, remote_function_f func, void *info) { struct remote_function_call data = { .p = NULL, .func = func, .info = info, .ret = -ENXIO, /* No such CPU */ }; smp_call_function_single(cpu, remote_function, &data, 1); return data.ret; } static void perf_ctx_lock(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { raw_spin_lock(&cpuctx->ctx.lock); if (ctx) raw_spin_lock(&ctx->lock); } static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { if (ctx) raw_spin_unlock(&ctx->lock); raw_spin_unlock(&cpuctx->ctx.lock); } #define TASK_TOMBSTONE ((void *)-1L) static bool is_kernel_event(struct perf_event *event) { return READ_ONCE(event->owner) == TASK_TOMBSTONE; } static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context); struct perf_event_context *perf_cpu_task_ctx(void) { lockdep_assert_irqs_disabled(); return this_cpu_ptr(&perf_cpu_context)->task_ctx; } /* * On task ctx scheduling... * * When !ctx->nr_events a task context will not be scheduled. This means * we can disable the scheduler hooks (for performance) without leaving * pending task ctx state. * * This however results in two special cases: * * - removing the last event from a task ctx; this is relatively straight * forward and is done in __perf_remove_from_context. * * - adding the first event to a task ctx; this is tricky because we cannot * rely on ctx->is_active and therefore cannot use event_function_call(). * See perf_install_in_context(). * * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. */ typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *, struct perf_event_context *, void *); struct event_function_struct { struct perf_event *event; event_f func; void *data; }; static int event_function(void *info) { struct event_function_struct *efs = info; struct perf_event *event = efs->event; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_context *task_ctx = cpuctx->task_ctx; int ret = 0; lockdep_assert_irqs_disabled(); perf_ctx_lock(cpuctx, task_ctx); /* * Since we do the IPI call without holding ctx->lock things can have * changed, double check we hit the task we set out to hit. */ if (ctx->task) { if (ctx->task != current) { ret = -ESRCH; goto unlock; } /* * We only use event_function_call() on established contexts, * and event_function() is only ever called when active (or * rather, we'll have bailed in task_function_call() or the * above ctx->task != current test), therefore we must have * ctx->is_active here. */ WARN_ON_ONCE(!ctx->is_active); /* * And since we have ctx->is_active, cpuctx->task_ctx must * match. */ WARN_ON_ONCE(task_ctx != ctx); } else { WARN_ON_ONCE(&cpuctx->ctx != ctx); } efs->func(event, cpuctx, ctx, efs->data); unlock: perf_ctx_unlock(cpuctx, task_ctx); return ret; } static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */ struct event_function_struct efs = { .event = event, .func = func, .data = data, }; if (!event->parent) { /* * If this is a !child event, we must hold ctx::mutex to * stabilize the event->ctx relation. See * perf_event_ctx_lock(). */ lockdep_assert_held(&ctx->mutex); } if (!task) { cpu_function_call(event->cpu, event_function, &efs); return; } if (task == TASK_TOMBSTONE) return; again: if (!task_function_call(task, event_function, &efs)) return; raw_spin_lock_irq(&ctx->lock); /* * Reload the task pointer, it might have been changed by * a concurrent perf_event_context_sched_out(). */ task = ctx->task; if (task == TASK_TOMBSTONE) { raw_spin_unlock_irq(&ctx->lock); return; } if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); goto again; } func(event, NULL, ctx, data); raw_spin_unlock_irq(&ctx->lock); } /* * Similar to event_function_call() + event_function(), but hard assumes IRQs * are already disabled and we're on the right CPU. */ static void event_function_local(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct task_struct *task = READ_ONCE(ctx->task); struct perf_event_context *task_ctx = NULL; lockdep_assert_irqs_disabled(); if (task) { if (task == TASK_TOMBSTONE) return; task_ctx = ctx; } perf_ctx_lock(cpuctx, task_ctx); task = ctx->task; if (task == TASK_TOMBSTONE) goto unlock; if (task) { /* * We must be either inactive or active and the right task, * otherwise we're screwed, since we cannot IPI to somewhere * else. */ if (ctx->is_active) { if (WARN_ON_ONCE(task != current)) goto unlock; if (WARN_ON_ONCE(cpuctx->task_ctx != ctx)) goto unlock; } } else { WARN_ON_ONCE(&cpuctx->ctx != ctx); } func(event, cpuctx, ctx, data); unlock: perf_ctx_unlock(cpuctx, task_ctx); } #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ PERF_FLAG_FD_CLOEXEC) /* * branch priv levels that need permission checks */ #define PERF_SAMPLE_BRANCH_PERM_PLM \ (PERF_SAMPLE_BRANCH_KERNEL |\ PERF_SAMPLE_BRANCH_HV) enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, EVENT_TIME = 0x4, /* see ctx_resched() for details */ EVENT_CPU = 0x8, EVENT_CGROUP = 0x10, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; /* * perf_sched_events : >0 events exist */ static void perf_sched_delayed(struct work_struct *work); DEFINE_STATIC_KEY_FALSE(perf_sched_events); static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); static DEFINE_MUTEX(perf_sched_mutex); static atomic_t perf_sched_count; static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; static atomic_t nr_namespaces_events __read_mostly; static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; static atomic_t nr_switch_events __read_mostly; static atomic_t nr_ksymbol_events __read_mostly; static atomic_t nr_bpf_events __read_mostly; static atomic_t nr_cgroup_events __read_mostly; static atomic_t nr_text_poke_events __read_mostly; static atomic_t nr_build_id_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); static struct srcu_struct pmus_srcu; static cpumask_var_t perf_online_mask; static struct kmem_cache *perf_event_cache; /* * perf event paranoia level: * -1 - not paranoid at all * 0 - disallow raw tracepoint access for unpriv * 1 - disallow cpu events for unpriv * 2 - disallow kernel profiling for unpriv */ int sysctl_perf_event_paranoid __read_mostly = 2; /* Minimum for 512 kiB + 1 user control page */ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ /* * max perf event sample rate */ #define DEFAULT_MAX_SAMPLE_RATE 100000 #define DEFAULT_SAMPLE_PERIOD_NS (NSEC_PER_SEC / DEFAULT_MAX_SAMPLE_RATE) #define DEFAULT_CPU_TIME_MAX_PERCENT 25 int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE; static int max_samples_per_tick __read_mostly = DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ); static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS; static int perf_sample_allowed_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100; static void update_perf_cpu_limits(void) { u64 tmp = perf_sample_period_ns; tmp *= sysctl_perf_cpu_time_max_percent; tmp = div_u64(tmp, 100); if (!tmp) tmp = 1; WRITE_ONCE(perf_sample_allowed_ns, tmp); } static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc); int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; int perf_cpu = sysctl_perf_cpu_time_max_percent; /* * If throttling is disabled don't allow the write: */ if (write && (perf_cpu == 100 || perf_cpu == 0)) return -EINVAL; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; update_perf_cpu_limits(); return 0; } int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT; int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; if (sysctl_perf_cpu_time_max_percent == 100 || sysctl_perf_cpu_time_max_percent == 0) { printk(KERN_WARNING "perf: Dynamic interrupt throttling disabled, can hang your system!\n"); WRITE_ONCE(perf_sample_allowed_ns, 0); } else { update_perf_cpu_limits(); } return 0; } /* * perf samples are done in some very critical code paths (NMIs). * If they take too much CPU time, the system can lock up and not * get any real work done. This will drop the sample rate when * we detect that events are taking too long. */ #define NR_ACCUMULATED_SAMPLES 128 static DEFINE_PER_CPU(u64, running_sample_length); static u64 __report_avg; static u64 __report_allowed; static void perf_duration_warn(struct irq_work *w) { printk_ratelimited(KERN_INFO "perf: interrupt took too long (%lld > %lld), lowering " "kernel.perf_event_max_sample_rate to %d\n", __report_avg, __report_allowed, sysctl_perf_event_sample_rate); } static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn); void perf_sample_event_took(u64 sample_len_ns) { u64 max_len = READ_ONCE(perf_sample_allowed_ns); u64 running_len; u64 avg_len; u32 max; if (max_len == 0) return; /* Decay the counter by 1 average sample. */ running_len = __this_cpu_read(running_sample_length); running_len -= running_len/NR_ACCUMULATED_SAMPLES; running_len += sample_len_ns; __this_cpu_write(running_sample_length, running_len); /* * Note: this will be biased artifically low until we have * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us * from having to maintain a count. */ avg_len = running_len/NR_ACCUMULATED_SAMPLES; if (avg_len <= max_len) return; __report_avg = avg_len; __report_allowed = max_len; /* * Compute a throttle threshold 25% below the current duration. */ avg_len += avg_len / 4; max = (TICK_NSEC / 100) * sysctl_perf_cpu_time_max_percent; if (avg_len < max) max /= (u32)avg_len; else max = 1; WRITE_ONCE(perf_sample_allowed_ns, avg_len); WRITE_ONCE(max_samples_per_tick, max); sysctl_perf_event_sample_rate = max * HZ; perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; if (!irq_work_queue(&perf_duration_work)) { early_printk("perf: interrupt took too long (%lld > %lld), lowering " "kernel.perf_event_max_sample_rate to %d\n", __report_avg, __report_allowed, sysctl_perf_event_sample_rate); } } static atomic64_t perf_event_id; static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); void __weak perf_event_print_debug(void) { } static inline u64 perf_clock(void) { return local_clock(); } static inline u64 perf_event_clock(struct perf_event *event) { return event->clock(); } /* * State based event timekeeping... * * The basic idea is to use event->state to determine which (if any) time * fields to increment with the current delta. This means we only need to * update timestamps when we change state or when they are explicitly requested * (read). * * Event groups make things a little more complicated, but not terribly so. The * rules for a group are that if the group leader is OFF the entire group is * OFF, irrespecive of what the group member states are. This results in * __perf_effective_state(). * * A futher ramification is that when a group leader flips between OFF and * !OFF, we need to update all group member times. * * * NOTE: perf_event_time() is based on the (cgroup) context time, and thus we * need to make sure the relevant context time is updated before we try and * update our timestamps. */ static __always_inline enum perf_event_state __perf_effective_state(struct perf_event *event) { struct perf_event *leader = event->group_leader; if (leader->state <= PERF_EVENT_STATE_OFF) return leader->state; return event->state; } static __always_inline void __perf_update_times(struct perf_event *event, u64 now, u64 *enabled, u64 *running) { enum perf_event_state state = __perf_effective_state(event); u64 delta = now - event->tstamp; *enabled = event->total_time_enabled; if (state >= PERF_EVENT_STATE_INACTIVE) *enabled += delta; *running = event->total_time_running; if (state >= PERF_EVENT_STATE_ACTIVE) *running += delta; } static void perf_event_update_time(struct perf_event *event) { u64 now = perf_event_time(event); __perf_update_times(event, now, &event->total_time_enabled, &event->total_time_running); event->tstamp = now; } static void perf_event_update_sibling_time(struct perf_event *leader) { struct perf_event *sibling; for_each_sibling_event(sibling, leader) perf_event_update_time(sibling); } static void perf_event_set_state(struct perf_event *event, enum perf_event_state state) { if (event->state == state) return; perf_event_update_time(event); /* * If a group leader gets enabled/disabled all its siblings * are affected too. */ if ((event->state < 0) ^ (state < 0)) perf_event_update_sibling_time(event); WRITE_ONCE(event->state, state); } /* * UP store-release, load-acquire */ #define __store_release(ptr, val) \ do { \ barrier(); \ WRITE_ONCE(*(ptr), (val)); \ } while (0) #define __load_acquire(ptr) \ ({ \ __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ barrier(); \ ___p; \ }) static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup) { struct perf_event_pmu_context *pmu_ctx; list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (cgroup && !pmu_ctx->nr_cgroups) continue; perf_pmu_disable(pmu_ctx->pmu); } } static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup) { struct perf_event_pmu_context *pmu_ctx; list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (cgroup && !pmu_ctx->nr_cgroups) continue; perf_pmu_enable(pmu_ctx->pmu); } } static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type); static void ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type); #ifdef CONFIG_CGROUP_PERF static inline bool perf_cgroup_match(struct perf_event *event) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); /* @event doesn't care about cgroup */ if (!event->cgrp) return true; /* wants specific cgroup scope but @cpuctx isn't associated with any */ if (!cpuctx->cgrp) return false; /* * Cgroup scoping is recursive. An event enabled for a cgroup is * also enabled for all its descendant cgroups. If @cpuctx's * cgroup is a descendant of @event's (the test covers identity * case), it's a match. */ return cgroup_is_descendant(cpuctx->cgrp->css.cgroup, event->cgrp->css.cgroup); } static inline void perf_detach_cgroup(struct perf_event *event) { css_put(&event->cgrp->css); event->cgrp = NULL; } static inline int is_cgroup_event(struct perf_event *event) { return event->cgrp != NULL; } static inline u64 perf_cgroup_event_time(struct perf_event *event) { struct perf_cgroup_info *t; t = per_cpu_ptr(event->cgrp->info, event->cpu); return t->time; } static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { struct perf_cgroup_info *t; t = per_cpu_ptr(event->cgrp->info, event->cpu); if (!__load_acquire(&t->active)) return t->time; now += READ_ONCE(t->timeoffset); return now; } static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) { if (adv) info->time += now - info->timestamp; info->timestamp = now; /* * see update_context_time() */ WRITE_ONCE(info->timeoffset, info->time - info->timestamp); } static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; struct perf_cgroup_info *info; if (cgrp) { u64 now = perf_clock(); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); __update_cgrp_time(info, now, true); if (final) __store_release(&info->active, 0); } } } static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; /* * ensure we access cgroup data only when needed and * when we know the cgroup is pinned (css_get) */ if (!is_cgroup_event(event)) return; info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ if (info->active) __update_cgrp_time(info, perf_clock(), true); } static inline void perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { struct perf_event_context *ctx = &cpuctx->ctx; struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; /* * ctx->lock held by caller * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ if (!cgrp) return; WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); __update_cgrp_time(info, ctx->timestamp, false); __store_release(&info->active, 1); } } /* * reschedule events based on the cgroup constraint of task. */ static void perf_cgroup_switch(struct task_struct *task) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_cgroup *cgrp; /* * cpuctx->cgrp is set when the first cgroup event enabled, * and is cleared when the last cgroup event disabled. */ if (READ_ONCE(cpuctx->cgrp) == NULL) return; WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); cgrp = perf_cgroup_from_task(task, NULL); if (READ_ONCE(cpuctx->cgrp) == cgrp) return; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_ctx_disable(&cpuctx->ctx, true); ctx_sched_out(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP); /* * must not be done before ctxswout due * to update_cgrp_time_from_cpuctx() in * ctx_sched_out() */ cpuctx->cgrp = cgrp; /* * set cgrp before ctxsw in to allow * perf_cgroup_set_timestamp() in ctx_sched_in() * to not have to pass task around */ ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP); perf_ctx_enable(&cpuctx->ctx, true); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { struct perf_cpu_context *cpuctx; struct perf_event **storage; int cpu, heap_size, ret = 0; /* * Allow storage to have sufficent space for an iterator for each * possibly nested cgroup plus an iterator for events with no cgroup. */ for (heap_size = 1; css; css = css->parent) heap_size++; for_each_possible_cpu(cpu) { cpuctx = per_cpu_ptr(&perf_cpu_context, cpu); if (heap_size <= cpuctx->heap_size) continue; storage = kmalloc_node(heap_size * sizeof(struct perf_event *), GFP_KERNEL, cpu_to_node(cpu)); if (!storage) { ret = -ENOMEM; break; } raw_spin_lock_irq(&cpuctx->ctx.lock); if (cpuctx->heap_size < heap_size) { swap(cpuctx->heap, storage); if (storage == cpuctx->heap_default) storage = NULL; cpuctx->heap_size = heap_size; } raw_spin_unlock_irq(&cpuctx->ctx.lock); kfree(storage); } return ret; } static inline int perf_cgroup_connect(int fd, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) { struct perf_cgroup *cgrp; struct cgroup_subsys_state *css; struct fd f = fdget(fd); int ret = 0; if (!f.file) return -EBADF; css = css_tryget_online_from_dir(f.file->f_path.dentry, &perf_event_cgrp_subsys); if (IS_ERR(css)) { ret = PTR_ERR(css); goto out; } ret = perf_cgroup_ensure_storage(event, css); if (ret) goto out; cgrp = container_of(css, struct perf_cgroup, css); event->cgrp = cgrp; /* * all events in a group must monitor * the same cgroup because a task belongs * to only one perf cgroup at a time */ if (group_leader && group_leader->cgrp != cgrp) { perf_detach_cgroup(event); ret = -EINVAL; } out: fdput(f); return ret; } static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; if (!is_cgroup_event(event)) return; event->pmu_ctx->nr_cgroups++; /* * Because cgroup events are always per-cpu events, * @ctx == &cpuctx->ctx. */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); if (ctx->nr_cgroups++) return; cpuctx->cgrp = perf_cgroup_from_task(current, ctx); } static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; if (!is_cgroup_event(event)) return; event->pmu_ctx->nr_cgroups--; /* * Because cgroup events are always per-cpu events, * @ctx == &cpuctx->ctx. */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); if (--ctx->nr_cgroups) return; cpuctx->cgrp = NULL; } #else /* !CONFIG_CGROUP_PERF */ static inline bool perf_cgroup_match(struct perf_event *event) { return true; } static inline void perf_detach_cgroup(struct perf_event *event) {} static inline int is_cgroup_event(struct perf_event *event) { return 0; } static inline void update_cgrp_time_from_event(struct perf_event *event) { } static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { } static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) { return -EINVAL; } static inline void perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } static inline u64 perf_cgroup_event_time(struct perf_event *event) { return 0; } static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { } static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } static void perf_cgroup_switch(struct task_struct *task) { } #endif /* * set default to be dependent on timer tick just * like original code */ #define PERF_CPU_HRTIMER (1000 / HZ) /* * function must be called with interrupts disabled */ static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { struct perf_cpu_pmu_context *cpc; bool rotations; lockdep_assert_irqs_disabled(); cpc = container_of(hr, struct perf_cpu_pmu_context, hrtimer); rotations = perf_rotate_context(cpc); raw_spin_lock(&cpc->hrtimer_lock); if (rotations) hrtimer_forward_now(hr, cpc->hrtimer_interval); else cpc->hrtimer_active = 0; raw_spin_unlock(&cpc->hrtimer_lock); return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART; } static void __perf_mux_hrtimer_init(struct perf_cpu_pmu_context *cpc, int cpu) { struct hrtimer *timer = &cpc->hrtimer; struct pmu *pmu = cpc->epc.pmu; u64 interval; /* * check default is sane, if not set then force to * default interval (1/tick) */ interval = pmu->hrtimer_interval_ms; if (interval < 1) interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER; cpc->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); raw_spin_lock_init(&cpc->hrtimer_lock); hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); timer->function = perf_mux_hrtimer_handler; } static int perf_mux_hrtimer_restart(struct perf_cpu_pmu_context *cpc) { struct hrtimer *timer = &cpc->hrtimer; unsigned long flags; raw_spin_lock_irqsave(&cpc->hrtimer_lock, flags); if (!cpc->hrtimer_active) { cpc->hrtimer_active = 1; hrtimer_forward_now(timer, cpc->hrtimer_interval); hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); } raw_spin_unlock_irqrestore(&cpc->hrtimer_lock, flags); return 0; } static int perf_mux_hrtimer_restart_ipi(void *arg) { return perf_mux_hrtimer_restart(arg); } void perf_pmu_disable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); if (!(*count)++) pmu->pmu_disable(pmu); } void perf_pmu_enable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); if (!--(*count)) pmu->pmu_enable(pmu); } static void perf_assert_pmu_disabled(struct pmu *pmu) { WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0); } static void get_ctx(struct perf_event_context *ctx) { refcount_inc(&ctx->refcount); } static void *alloc_task_ctx_data(struct pmu *pmu) { if (pmu->task_ctx_cache) return kmem_cache_zalloc(pmu->task_ctx_cache, GFP_KERNEL); return NULL; } static void free_task_ctx_data(struct pmu *pmu, void *task_ctx_data) { if (pmu->task_ctx_cache && task_ctx_data) kmem_cache_free(pmu->task_ctx_cache, task_ctx_data); } static void free_ctx(struct rcu_head *head) { struct perf_event_context *ctx; ctx = container_of(head, struct perf_event_context, rcu_head); kfree(ctx); } static void put_ctx(struct perf_event_context *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { if (ctx->parent_ctx) put_ctx(ctx->parent_ctx); if (ctx->task && ctx->task != TASK_TOMBSTONE) put_task_struct(ctx->task); call_rcu(&ctx->rcu_head, free_ctx); } } /* * Because of perf_event::ctx migration in sys_perf_event_open::move_group and * perf_pmu_migrate_context() we need some magic. * * Those places that change perf_event::ctx will hold both * perf_event_ctx::mutex of the 'old' and 'new' ctx value. * * Lock ordering is by mutex address. There are two other sites where * perf_event_context::mutex nests and those are: * * - perf_event_exit_task_context() [ child , 0 ] * perf_event_exit_event() * put_event() [ parent, 1 ] * * - perf_event_init_context() [ parent, 0 ] * inherit_task_group() * inherit_group() * inherit_event() * perf_event_alloc() * perf_init_event() * perf_try_init_event() [ child , 1 ] * * While it appears there is an obvious deadlock here -- the parent and child * nesting levels are inverted between the two. This is in fact safe because * life-time rules separate them. That is an exiting task cannot fork, and a * spawning task cannot (yet) exit. * * But remember that these are parent<->child context relations, and * migration does not affect children, therefore these two orderings should not * interact. * * The change in perf_event::ctx does not affect children (as claimed above) * because the sys_perf_event_open() case will install a new event and break * the ctx parent<->child relation, and perf_pmu_migrate_context() is only * concerned with cpuctx and that doesn't have children. * * The places that change perf_event::ctx will issue: * * perf_remove_from_context(); * synchronize_rcu(); * perf_install_in_context(); * * to affect the change. The remove_from_context() + synchronize_rcu() should * quiesce the event, after which we can install it in the new location. This * means that only external vectors (perf_fops, prctl) can perturb the event * while in transit. Therefore all such accessors should also acquire * perf_event_context::mutex to serialize against this. * * However; because event->ctx can change while we're waiting to acquire * ctx->mutex we must be careful and use the below perf_event_ctx_lock() * function. * * Lock order: * exec_update_lock * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; * perf_event_context::lock * perf_event::mmap_mutex * mmap_lock * perf_addr_filters_head::lock * * cpu_hotplug_lock * pmus_lock * cpuctx->mutex / perf_event_context::mutex */ static struct perf_event_context * perf_event_ctx_lock_nested(struct perf_event *event, int nesting) { struct perf_event_context *ctx; again: rcu_read_lock(); ctx = READ_ONCE(event->ctx); if (!refcount_inc_not_zero(&ctx->refcount)) { rcu_read_unlock(); goto again; } rcu_read_unlock(); mutex_lock_nested(&ctx->mutex, nesting); if (event->ctx != ctx) { mutex_unlock(&ctx->mutex); put_ctx(ctx); goto again; } return ctx; } static inline struct perf_event_context * perf_event_ctx_lock(struct perf_event *event) { return perf_event_ctx_lock_nested(event, 0); } static void perf_event_ctx_unlock(struct perf_event *event, struct perf_event_context *ctx) { mutex_unlock(&ctx->mutex); put_ctx(ctx); } /* * This must be done under the ctx->lock, such as to serialize against * context_equiv(), therefore we cannot call put_ctx() since that might end up * calling scheduler related locks and ctx->lock nests inside those. */ static __must_check struct perf_event_context * unclone_ctx(struct perf_event_context *ctx) { struct perf_event_context *parent_ctx = ctx->parent_ctx; lockdep_assert_held(&ctx->lock); if (parent_ctx) ctx->parent_ctx = NULL; ctx->generation++; return parent_ctx; } static u32 perf_event_pid_type(struct perf_event *event, struct task_struct *p, enum pid_type type) { u32 nr; /* * only top level events have the pid namespace they were created in */ if (event->parent) event = event->parent; nr = __task_pid_nr_ns(p, type, event->ns); /* avoid -1 if it is idle thread or runs in another ns */ if (!nr && !pid_alive(p)) nr = -1; return nr; } static u32 perf_event_pid(struct perf_event *event, struct task_struct *p) { return perf_event_pid_type(event, p, PIDTYPE_TGID); } static u32 perf_event_tid(struct perf_event *event, struct task_struct *p) { return perf_event_pid_type(event, p, PIDTYPE_PID); } /* * If we inherit events we want to return the parent event id * to userspace. */ static u64 primary_event_id(struct perf_event *event) { u64 id = event->id; if (event->parent) id = event->parent->id; return id; } /* * Get the perf_event_context for a task and lock it. * * This has to cope with the fact that until it is locked, * the context could get moved to another task. */ static struct perf_event_context * perf_lock_task_context(struct task_struct *task, unsigned long *flags) { struct perf_event_context *ctx; retry: /* * One of the few rules of preemptible RCU is that one cannot do * rcu_read_unlock() while holding a scheduler (or nested) lock when * part of the read side critical section was irqs-enabled -- see * rcu_read_unlock_special(). * * Since ctx->lock nests under rq->lock we must ensure the entire read * side critical section has interrupts disabled. */ local_irq_save(*flags); rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp); if (ctx) { /* * If this context is a clone of another, it might * get swapped for another underneath us by * perf_event_task_sched_out, though the * rcu_read_lock() protects us from any context * getting freed. Lock the context and check if it * got swapped before we could get the lock, and retry * if so. If we locked the right context, then it * can't get swapped on us any more. */ raw_spin_lock(&ctx->lock); if (ctx != rcu_dereference(task->perf_event_ctxp)) { raw_spin_unlock(&ctx->lock); rcu_read_unlock(); local_irq_restore(*flags); goto retry; } if (ctx->task == TASK_TOMBSTONE || !refcount_inc_not_zero(&ctx->refcount)) { raw_spin_unlock(&ctx->lock); ctx = NULL; } else { WARN_ON_ONCE(ctx->task != task); } } rcu_read_unlock(); if (!ctx) local_irq_restore(*flags); return ctx; } /* * Get the context for a task and increment its pin_count so it * can't get swapped to another task. This also increments its * reference count so that the context can't get freed. */ static struct perf_event_context * perf_pin_task_context(struct task_struct *task) { struct perf_event_context *ctx; unsigned long flags; ctx = perf_lock_task_context(task, &flags); if (ctx) { ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); } return ctx; } static void perf_unpin_context(struct perf_event_context *ctx) { unsigned long flags; raw_spin_lock_irqsave(&ctx->lock, flags); --ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); } /* * Update the record of the current time in a context. */ static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock(); lockdep_assert_held(&ctx->lock); if (adv) ctx->time += now - ctx->timestamp; ctx->timestamp = now; /* * The above: time' = time + (now - timestamp), can be re-arranged * into: time` = now + (time - timestamp), which gives a single value * offset to compute future time without locks on. * * See perf_event_time_now(), which can be used from NMI context where * it's (obviously) not possible to acquire ctx->lock in order to read * both the above values in a consistent manner. */ WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); } static void update_context_time(struct perf_event_context *ctx) { __update_context_time(ctx, true); } static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; if (unlikely(!ctx)) return 0; if (is_cgroup_event(event)) return perf_cgroup_event_time(event); return ctx->time; } static u64 perf_event_time_now(struct perf_event *event, u64 now) { struct perf_event_context *ctx = event->ctx; if (unlikely(!ctx)) return 0; if (is_cgroup_event(event)) return perf_cgroup_event_time_now(event, now); if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) return ctx->time; now += READ_ONCE(ctx->timeoffset); return now; } static enum event_type_t get_event_type(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; enum event_type_t event_type; lockdep_assert_held(&ctx->lock); /* * It's 'group type', really, because if our group leader is * pinned, so are we. */ if (event->group_leader != event) event = event->group_leader; event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE; if (!ctx->task) event_type |= EVENT_CPU; return event_type; } /* * Helper function to initialize event group nodes. */ static void init_event_group(struct perf_event *event) { RB_CLEAR_NODE(&event->group_node); event->group_index = 0; } /* * Extract pinned or flexible groups from the context * based on event attrs bits. */ static struct perf_event_groups * get_event_groups(struct perf_event *event, struct perf_event_context *ctx) { if (event->attr.pinned) return &ctx->pinned_groups; else return &ctx->flexible_groups; } /* * Helper function to initializes perf_event_group trees. */ static void perf_event_groups_init(struct perf_event_groups *groups) { groups->tree = RB_ROOT; groups->index = 0; } static inline struct cgroup *event_cgroup(const struct perf_event *event) { struct cgroup *cgroup = NULL; #ifdef CONFIG_CGROUP_PERF if (event->cgrp) cgroup = event->cgrp->css.cgroup; #endif return cgroup; } /* * Compare function for event groups; * * Implements complex key that first sorts by CPU and then by virtual index * which provides ordering when rotating groups for the same CPU. */ static __always_inline int perf_event_groups_cmp(const int left_cpu, const struct pmu *left_pmu, const struct cgroup *left_cgroup, const u64 left_group_index, const struct perf_event *right) { if (left_cpu < right->cpu) return -1; if (left_cpu > right->cpu) return 1; if (left_pmu) { if (left_pmu < right->pmu_ctx->pmu) return -1; if (left_pmu > right->pmu_ctx->pmu) return 1; } #ifdef CONFIG_CGROUP_PERF { const struct cgroup *right_cgroup = event_cgroup(right); if (left_cgroup != right_cgroup) { if (!left_cgroup) { /* * Left has no cgroup but right does, no * cgroups come first. */ return -1; } if (!right_cgroup) { /* * Right has no cgroup but left does, no * cgroups come first. */ return 1; } /* Two dissimilar cgroups, order by id. */ if (cgroup_id(left_cgroup) < cgroup_id(right_cgroup)) return -1; return 1; } } #endif if (left_group_index < right->group_index) return -1; if (left_group_index > right->group_index) return 1; return 0; } #define __node_2_pe(node) \ rb_entry((node), struct perf_event, group_node) static inline bool __group_less(struct rb_node *a, const struct rb_node *b) { struct perf_event *e = __node_2_pe(a); return perf_event_groups_cmp(e->cpu, e->pmu_ctx->pmu, event_cgroup(e), e->group_index, __node_2_pe(b)) < 0; } struct __group_key { int cpu; struct pmu *pmu; struct cgroup *cgroup; }; static inline int __group_cmp(const void *key, const struct rb_node *node) { const struct __group_key *a = key; const struct perf_event *b = __node_2_pe(node); /* partial/subtree match: @cpu, @pmu, @cgroup; ignore: @group_index */ return perf_event_groups_cmp(a->cpu, a->pmu, a->cgroup, b->group_index, b); } static inline int __group_cmp_ignore_cgroup(const void *key, const struct rb_node *node) { const struct __group_key *a = key; const struct perf_event *b = __node_2_pe(node); /* partial/subtree match: @cpu, @pmu, ignore: @cgroup, @group_index */ return perf_event_groups_cmp(a->cpu, a->pmu, event_cgroup(b), b->group_index, b); } /* * Insert @event into @groups' tree; using * {@event->cpu, @event->pmu_ctx->pmu, event_cgroup(@event), ++@groups->index} * as key. This places it last inside the {cpu,pmu,cgroup} subtree. */ static void perf_event_groups_insert(struct perf_event_groups *groups, struct perf_event *event) { event->group_index = ++groups->index; rb_add(&event->group_node, &groups->tree, __group_less); } /* * Helper function to insert event into the pinned or flexible groups. */ static void add_event_to_groups(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event_groups *groups; groups = get_event_groups(event, ctx); perf_event_groups_insert(groups, event); } /* * Delete a group from a tree. */ static void perf_event_groups_delete(struct perf_event_groups *groups, struct perf_event *event) { WARN_ON_ONCE(RB_EMPTY_NODE(&event->group_node) || RB_EMPTY_ROOT(&groups->tree)); rb_erase(&event->group_node, &groups->tree); init_event_group(event); } /* * Helper function to delete event from its groups. */ static void del_event_from_groups(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event_groups *groups; groups = get_event_groups(event, ctx); perf_event_groups_delete(groups, event); } /* * Get the leftmost event in the {cpu,pmu,cgroup} subtree. */ static struct perf_event * perf_event_groups_first(struct perf_event_groups *groups, int cpu, struct pmu *pmu, struct cgroup *cgrp) { struct __group_key key = { .cpu = cpu, .pmu = pmu, .cgroup = cgrp, }; struct rb_node *node; node = rb_find_first(&key, &groups->tree, __group_cmp); if (node) return __node_2_pe(node); return NULL; } static struct perf_event * perf_event_groups_next(struct perf_event *event, struct pmu *pmu) { struct __group_key key = { .cpu = event->cpu, .pmu = pmu, .cgroup = event_cgroup(event), }; struct rb_node *next; next = rb_next_match(&key, &event->group_node, __group_cmp); if (next) return __node_2_pe(next); return NULL; } #define perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) \ for (event = perf_event_groups_first(groups, cpu, pmu, NULL); \ event; event = perf_event_groups_next(event, pmu)) /* * Iterate through the whole groups tree. */ #define perf_event_groups_for_each(event, groups) \ for (event = rb_entry_safe(rb_first(&((groups)->tree)), \ typeof(*event), group_node); event; \ event = rb_entry_safe(rb_next(&event->group_node), \ typeof(*event), group_node)) /* * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); event->attach_state |= PERF_ATTACH_CONTEXT; event->tstamp = perf_event_time(event); /* * If we're a stand alone event or group leader, we go to the context * list, group events are kept attached to the group so that * perf_group_detach can, at all times, locate all siblings. */ if (event->group_leader == event) { event->group_caps = event->event_caps; add_event_to_groups(event, ctx); } list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) ctx->nr_user++; if (event->attr.inherit_stat) ctx->nr_stat++; if (event->state > PERF_EVENT_STATE_OFF) perf_cgroup_event_enable(event, ctx); ctx->generation++; event->pmu_ctx->nr_events++; } /* * Initialize event state based on the perf_event_attr::disabled. */ static inline void perf_event__state_init(struct perf_event *event) { event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF : PERF_EVENT_STATE_INACTIVE; } static int __perf_event_read_size(u64 read_format, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; int nr = 1; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64); if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64); if (read_format & PERF_FORMAT_ID) entry += sizeof(u64); if (read_format & PERF_FORMAT_LOST) entry += sizeof(u64); if (read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); } /* * Since perf_event_validate_size() limits this to 16k and inhibits * adding more siblings, this will never overflow. */ return size + nr * entry; } static void __perf_event_header_size(struct perf_event *event, u64 sample_type) { struct perf_sample_data *data; u16 size = 0; if (sample_type & PERF_SAMPLE_IP) size += sizeof(data->ip); if (sample_type & PERF_SAMPLE_ADDR) size += sizeof(data->addr); if (sample_type & PERF_SAMPLE_PERIOD) size += sizeof(data->period); if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) size += sizeof(data->weight.full); if (sample_type & PERF_SAMPLE_READ) size += event->read_size; if (sample_type & PERF_SAMPLE_DATA_SRC) size += sizeof(data->data_src.val); if (sample_type & PERF_SAMPLE_TRANSACTION) size += sizeof(data->txn); if (sample_type & PERF_SAMPLE_PHYS_ADDR) size += sizeof(data->phys_addr); if (sample_type & PERF_SAMPLE_CGROUP) size += sizeof(data->cgroup); if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) size += sizeof(data->data_page_size); if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE) size += sizeof(data->code_page_size); event->header_size = size; } /* * Called at perf_event creation and when events are attached/detached from a * group. */ static void perf_event__header_size(struct perf_event *event) { event->read_size = __perf_event_read_size(event->attr.read_format, event->group_leader->nr_siblings); __perf_event_header_size(event, event->attr.sample_type); } static void perf_event__id_header_size(struct perf_event *event) { struct perf_sample_data *data; u64 sample_type = event->attr.sample_type; u16 size = 0; if (sample_type & PERF_SAMPLE_TID) size += sizeof(data->tid_entry); if (sample_type & PERF_SAMPLE_TIME) size += sizeof(data->time); if (sample_type & PERF_SAMPLE_IDENTIFIER) size += sizeof(data->id); if (sample_type & PERF_SAMPLE_ID) size += sizeof(data->id); if (sample_type & PERF_SAMPLE_STREAM_ID) size += sizeof(data->stream_id); if (sample_type & PERF_SAMPLE_CPU) size += sizeof(data->cpu_entry); event->id_header_size = size; } /* * Check that adding an event to the group does not result in anybody * overflowing the 64k event limit imposed by the output buffer. * * Specifically, check that the read_size for the event does not exceed 16k, * read_size being the one term that grows with groups size. Since read_size * depends on per-event read_format, also (re)check the existing events. * * This leaves 48k for the constant size fields and things like callchains, * branch stacks and register sets. */ static bool perf_event_validate_size(struct perf_event *event) { struct perf_event *sibling, *group_leader = event->group_leader; if (__perf_event_read_size(event->attr.read_format, group_leader->nr_siblings + 1) > 16*1024) return false; if (__perf_event_read_size(group_leader->attr.read_format, group_leader->nr_siblings + 1) > 16*1024) return false; /* * When creating a new group leader, group_leader->ctx is initialized * after the size has been validated, but we cannot safely use * for_each_sibling_event() until group_leader->ctx is set. A new group * leader cannot have any siblings yet, so we can safely skip checking * the non-existent siblings. */ if (event == group_leader) return true; for_each_sibling_event(sibling, group_leader) { if (__perf_event_read_size(sibling->attr.read_format, group_leader->nr_siblings + 1) > 16*1024) return false; } return true; } static void perf_group_attach(struct perf_event *event) { struct perf_event *group_leader = event->group_leader, *pos; lockdep_assert_held(&event->ctx->lock); /* * We can have double attach due to group movement (move_group) in * perf_event_open(). */ if (event->attach_state & PERF_ATTACH_GROUP) return; event->attach_state |= PERF_ATTACH_GROUP; if (group_leader == event) return; WARN_ON_ONCE(group_leader->ctx != event->ctx); group_leader->group_caps &= event->event_caps; list_add_tail(&event->sibling_list, &group_leader->sibling_list); group_leader->nr_siblings++; group_leader->group_generation++; perf_event__header_size(group_leader); for_each_sibling_event(pos, group_leader) perf_event__header_size(pos); } /* * Remove an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ static void list_del_event(struct perf_event *event, struct perf_event_context *ctx) { WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); /* * We can have double detach due to exit/hot-unplug + close. */ if (!(event->attach_state & PERF_ATTACH_CONTEXT)) return; event->attach_state &= ~PERF_ATTACH_CONTEXT; ctx->nr_events--; if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) ctx->nr_user--; if (event->attr.inherit_stat) ctx->nr_stat--; list_del_rcu(&event->event_entry); if (event->group_leader == event) del_event_from_groups(event, ctx); /* * If event was in error state, then keep it * that way, otherwise bogus counts will be * returned on read(). The only way to get out * of error state is by explicit re-enabling * of the event */ if (event->state > PERF_EVENT_STATE_OFF) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_OFF); } ctx->generation++; event->pmu_ctx->nr_events--; } static int perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event) { if (!has_aux(aux_event)) return 0; if (!event->pmu->aux_output_match) return 0; return event->pmu->aux_output_match(aux_event); } static void put_event(struct perf_event *event); static void event_sched_out(struct perf_event *event, struct perf_event_context *ctx); static void perf_put_aux_event(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct perf_event *iter; /* * If event uses aux_event tear down the link */ if (event->aux_event) { iter = event->aux_event; event->aux_event = NULL; put_event(iter); return; } /* * If the event is an aux_event, tear down all links to * it from other events. */ for_each_sibling_event(iter, event->group_leader) { if (iter->aux_event != event) continue; iter->aux_event = NULL; put_event(event); /* * If it's ACTIVE, schedule it out and put it into ERROR * state so that we don't try to schedule it again. Note * that perf_event_enable() will clear the ERROR status. */ event_sched_out(iter, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); } } static bool perf_need_aux_event(struct perf_event *event) { return !!event->attr.aux_output || !!event->attr.aux_sample_size; } static int perf_get_aux_event(struct perf_event *event, struct perf_event *group_leader) { /* * Our group leader must be an aux event if we want to be * an aux_output. This way, the aux event will precede its * aux_output events in the group, and therefore will always * schedule first. */ if (!group_leader) return 0; /* * aux_output and aux_sample_size are mutually exclusive. */ if (event->attr.aux_output && event->attr.aux_sample_size) return 0; if (event->attr.aux_output && !perf_aux_output_match(event, group_leader)) return 0; if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux) return 0; if (!atomic_long_inc_not_zero(&group_leader->refcount)) return 0; /* * Link aux_outputs to their aux event; this is undone in * perf_group_detach() by perf_put_aux_event(). When the * group in torn down, the aux_output events loose their * link to the aux_event and can't schedule any more. */ event->aux_event = group_leader; return 1; } static inline struct list_head *get_event_list(struct perf_event *event) { return event->attr.pinned ? &event->pmu_ctx->pinned_active : &event->pmu_ctx->flexible_active; } /* * Events that have PERF_EV_CAP_SIBLING require being part of a group and * cannot exist on their own, schedule them out and move them into the ERROR * state. Also see _perf_event_enable(), it will not be able to recover * this ERROR state. */ static inline void perf_remove_sibling_event(struct perf_event *event) { event_sched_out(event, event->ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); } static void perf_group_detach(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct perf_event *sibling, *tmp; struct perf_event_context *ctx = event->ctx; lockdep_assert_held(&ctx->lock); /* * We can have double detach due to exit/hot-unplug + close. */ if (!(event->attach_state & PERF_ATTACH_GROUP)) return; event->attach_state &= ~PERF_ATTACH_GROUP; perf_put_aux_event(event); /* * If this is a sibling, remove it from its group. */ if (leader != event) { list_del_init(&event->sibling_list); event->group_leader->nr_siblings--; event->group_leader->group_generation++; goto out; } /* * If this was a group event with sibling events then * upgrade the siblings to singleton events by adding them * to whatever list we are on. */ list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) { if (sibling->event_caps & PERF_EV_CAP_SIBLING) perf_remove_sibling_event(sibling); sibling->group_leader = sibling; list_del_init(&sibling->sibling_list); /* Inherit group flags from the previous leader */ sibling->group_caps = event->group_caps; if (sibling->attach_state & PERF_ATTACH_CONTEXT) { add_event_to_groups(sibling, event->ctx); if (sibling->state == PERF_EVENT_STATE_ACTIVE) list_add_tail(&sibling->active_list, get_event_list(sibling)); } WARN_ON_ONCE(sibling->ctx != event->ctx); } out: for_each_sibling_event(tmp, leader) perf_event__header_size(tmp); perf_event__header_size(leader); } static void sync_child_event(struct perf_event *child_event); static void perf_child_detach(struct perf_event *event) { struct perf_event *parent_event = event->parent; if (!(event->attach_state & PERF_ATTACH_CHILD)) return; event->attach_state &= ~PERF_ATTACH_CHILD; if (WARN_ON_ONCE(!parent_event)) return; lockdep_assert_held(&parent_event->child_mutex); sync_child_event(event); list_del_init(&event->child_list); } static bool is_orphaned_event(struct perf_event *event) { return event->state == PERF_EVENT_STATE_DEAD; } static inline int event_filter_match(struct perf_event *event) { return (event->cpu == -1 || event->cpu == smp_processor_id()) && perf_cgroup_match(event); } static void event_sched_out(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event_pmu_context *epc = event->pmu_ctx; struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context); enum perf_event_state state = PERF_EVENT_STATE_INACTIVE; // XXX cpc serialization, probably per-cpu IRQ disabled WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); if (event->state != PERF_EVENT_STATE_ACTIVE) return; /* * Asymmetry; we only schedule events _IN_ through ctx_sched_in(), but * we can schedule events _OUT_ individually through things like * __perf_remove_from_context(). */ list_del_init(&event->active_list); perf_pmu_disable(event->pmu); event->pmu->del(event, 0); event->oncpu = -1; if (event->pending_disable) { event->pending_disable = 0; perf_cgroup_event_disable(event, ctx); state = PERF_EVENT_STATE_OFF; } if (event->pending_sigtrap) { bool dec = true; event->pending_sigtrap = 0; if (state != PERF_EVENT_STATE_OFF && !event->pending_work) { event->pending_work = 1; dec = false; WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount)); task_work_add(current, &event->pending_task, TWA_RESUME); } if (dec) local_dec(&event->ctx->nr_pending); } perf_event_set_state(event, state); if (!is_software_event(event)) cpc->active_oncpu--; if (event->attr.freq && event->attr.sample_freq) { ctx->nr_freq--; epc->nr_freq--; } if (event->attr.exclusive || !cpc->active_oncpu) cpc->exclusive = 0; perf_pmu_enable(event->pmu); } static void group_sched_out(struct perf_event *group_event, struct perf_event_context *ctx) { struct perf_event *event; if (group_event->state != PERF_EVENT_STATE_ACTIVE) return; perf_assert_pmu_disabled(group_event->pmu_ctx->pmu); event_sched_out(group_event, ctx); /* * Schedule out siblings (if any): */ for_each_sibling_event(event, group_event) event_sched_out(event, ctx); } #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL #define DETACH_DEAD 0x04UL /* * Cross CPU call to remove a performance event * * We disable the event on the hardware level first. After that we * remove it from the context list. */ static void __perf_remove_from_context(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, void *info) { struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx; unsigned long flags = (unsigned long)info; if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx, false); } /* * Ensure event_sched_out() switches to OFF, at the very least * this avoids raising perf_pending_task() at this time. */ if (flags & DETACH_DEAD) event->pending_disable = 1; event_sched_out(event, ctx); if (flags & DETACH_GROUP) perf_group_detach(event); if (flags & DETACH_CHILD) perf_child_detach(event); list_del_event(event, ctx); if (flags & DETACH_DEAD) event->state = PERF_EVENT_STATE_DEAD; if (!pmu_ctx->nr_events) { pmu_ctx->rotate_necessary = 0; if (ctx->task && ctx->is_active) { struct perf_cpu_pmu_context *cpc; cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context); WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx); cpc->task_epc = NULL; } } if (!ctx->nr_events && ctx->is_active) { if (ctx == &cpuctx->ctx) update_cgrp_time_from_cpuctx(cpuctx, true); ctx->is_active = 0; if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); cpuctx->task_ctx = NULL; } } } /* * Remove the event from a task's (or a CPU's) list of events. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This is OK when called from perf_release since * that only calls us on the top-level context, which can't be a clone. * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { struct perf_event_context *ctx = event->ctx; lockdep_assert_held(&ctx->mutex); /* * Because of perf_event_exit_task(), perf_remove_from_context() ought * to work in the face of TASK_TOMBSTONE, unlike every other * event_function_call() user. */ raw_spin_lock_irq(&ctx->lock); if (!ctx->is_active) { __perf_remove_from_context(event, this_cpu_ptr(&perf_cpu_context), ctx, (void *)flags); raw_spin_unlock_irq(&ctx->lock); return; } raw_spin_unlock_irq(&ctx->lock); event_function_call(event, __perf_remove_from_context, (void *)flags); } /* * Cross CPU call to disable a performance event */ static void __perf_event_disable(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, void *info) { if (event->state < PERF_EVENT_STATE_INACTIVE) return; if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); update_cgrp_time_from_event(event); } perf_pmu_disable(event->pmu_ctx->pmu); if (event == event->group_leader) group_sched_out(event, ctx); else event_sched_out(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_OFF); perf_cgroup_event_disable(event, ctx); perf_pmu_enable(event->pmu_ctx->pmu); } /* * Disable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This condition is satisfied when called through * perf_event_for_each_child or perf_event_for_each because they * hold the top-level event's child_mutex, so any descendant that * goes to exit will block in perf_event_exit_event(). * * When called from perf_pending_irq it's OK because event->ctx * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. */ static void _perf_event_disable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; raw_spin_lock_irq(&ctx->lock); if (event->state <= PERF_EVENT_STATE_OFF) { raw_spin_unlock_irq(&ctx->lock); return; } raw_spin_unlock_irq(&ctx->lock); event_function_call(event, __perf_event_disable, NULL); } void perf_event_disable_local(struct perf_event *event) { event_function_local(event, __perf_event_disable, NULL); } /* * Strictly speaking kernel users cannot create groups and therefore this * interface does not need the perf_event_ctx_lock() magic. */ void perf_event_disable(struct perf_event *event) { struct perf_event_context *ctx; ctx = perf_event_ctx_lock(event); _perf_event_disable(event); perf_event_ctx_unlock(event, ctx); } EXPORT_SYMBOL_GPL(perf_event_disable); void perf_event_disable_inatomic(struct perf_event *event) { event->pending_disable = 1; irq_work_queue(&event->pending_irq); } #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); static void perf_log_itrace_start(struct perf_event *event); static int event_sched_in(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event_pmu_context *epc = event->pmu_ctx; struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context); int ret = 0; WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); if (event->state <= PERF_EVENT_STATE_OFF) return 0; WRITE_ONCE(event->oncpu, smp_processor_id()); /* * Order event::oncpu write to happen before the ACTIVE state is * visible. This allows perf_event_{stop,read}() to observe the correct * ->oncpu if it sees ACTIVE. */ smp_wmb(); perf_event_set_state(event, PERF_EVENT_STATE_ACTIVE); /* * Unthrottle events, since we scheduled we might have missed several * ticks already, also for a heavily scheduling task there is little * guarantee it'll get a tick in a timely manner. */ if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) { perf_log_throttle(event, 1); event->hw.interrupts = 0; } perf_pmu_disable(event->pmu); perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); event->oncpu = -1; ret = -EAGAIN; goto out; } if (!is_software_event(event)) cpc->active_oncpu++; if (event->attr.freq && event->attr.sample_freq) { ctx->nr_freq++; epc->nr_freq++; } if (event->attr.exclusive) cpc->exclusive = 1; out: perf_pmu_enable(event->pmu); return ret; } static int group_sched_in(struct perf_event *group_event, struct perf_event_context *ctx) { struct perf_event *event, *partial_group = NULL; struct pmu *pmu = group_event->pmu_ctx->pmu; if (group_event->state == PERF_EVENT_STATE_OFF) return 0; pmu->start_txn(pmu, PERF_PMU_TXN_ADD); if (event_sched_in(group_event, ctx)) goto error; /* * Schedule in siblings as one group (if any): */ for_each_sibling_event(event, group_event) { if (event_sched_in(event, ctx)) { partial_group = event; goto group_error; } } if (!pmu->commit_txn(pmu)) return 0; group_error: /* * Groups can be scheduled in as one unit only, so undo any * partial group before returning: * The events up to the failed event are scheduled out normally. */ for_each_sibling_event(event, group_event) { if (event == partial_group) break; event_sched_out(event, ctx); } event_sched_out(group_event, ctx); error: pmu->cancel_txn(pmu); return -EAGAIN; } /* * Work out whether we can put this event group on the CPU now. */ static int group_can_go_on(struct perf_event *event, int can_add_hw) { struct perf_event_pmu_context *epc = event->pmu_ctx; struct perf_cpu_pmu_context *cpc = this_cpu_ptr(epc->pmu->cpu_pmu_context); /* * Groups consisting entirely of software events can always go on. */ if (event->group_caps & PERF_EV_CAP_SOFTWARE) return 1; /* * If an exclusive group is already on, no other hardware * events can go on. */ if (cpc->exclusive) return 0; /* * If this group is exclusive and there are already * events on the CPU, it can't go on. */ if (event->attr.exclusive && !list_empty(get_event_list(event))) return 0; /* * Otherwise, try to add it if all previous groups were able * to go on. */ return can_add_hw; } static void add_event_to_ctx(struct perf_event *event, struct perf_event_context *ctx) { list_add_event(event, ctx); perf_group_attach(event); } static void task_ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); if (!cpuctx->task_ctx) return; if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) return; ctx_sched_out(ctx, event_type); } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { ctx_sched_in(&cpuctx->ctx, EVENT_PINNED); if (ctx) ctx_sched_in(ctx, EVENT_PINNED); ctx_sched_in(&cpuctx->ctx, EVENT_FLEXIBLE); if (ctx) ctx_sched_in(ctx, EVENT_FLEXIBLE); } /* * We want to maintain the following priority of scheduling: * - CPU pinned (EVENT_CPU | EVENT_PINNED) * - task pinned (EVENT_PINNED) * - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE) * - task flexible (EVENT_FLEXIBLE). * * In order to avoid unscheduling and scheduling back in everything every * time an event is added, only do it for the groups of equal priority and * below. * * This can be called after a batch operation on task events, in which case * event_type is a bit mask of the types of events involved. For CPU events, * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE. */ /* * XXX: ctx_resched() reschedule entire perf_event_context while adding new * event to the context or enabling existing event in the context. We can * probably optimize it by rescheduling only affected pmu_ctx. */ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, enum event_type_t event_type) { bool cpu_event = !!(event_type & EVENT_CPU); /* * If pinned groups are involved, flexible groups also need to be * scheduled out. */ if (event_type & EVENT_PINNED) event_type |= EVENT_FLEXIBLE; event_type &= EVENT_ALL; perf_ctx_disable(&cpuctx->ctx, false); if (task_ctx) { perf_ctx_disable(task_ctx, false); task_ctx_sched_out(task_ctx, event_type); } /* * Decide which cpu ctx groups to schedule out based on the types * of events that caused rescheduling: * - EVENT_CPU: schedule out corresponding groups; * - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups; * - otherwise, do nothing more. */ if (cpu_event) ctx_sched_out(&cpuctx->ctx, event_type); else if (event_type & EVENT_PINNED) ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE); perf_event_sched_in(cpuctx, task_ctx); perf_ctx_enable(&cpuctx->ctx, false); if (task_ctx) perf_ctx_enable(task_ctx, false); } void perf_pmu_resched(struct pmu *pmu) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_context *task_ctx = cpuctx->task_ctx; perf_ctx_lock(cpuctx, task_ctx); ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); perf_ctx_unlock(cpuctx, task_ctx); } /* * Cross CPU call to install and enable a performance event * * Very similar to remote_function() + event_function() but cannot assume that * things like ctx->is_active and cpuctx->task_ctx are set. */ static int __perf_install_in_context(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_context *task_ctx = cpuctx->task_ctx; bool reprogram = true; int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); if (ctx->task) { raw_spin_lock(&ctx->lock); task_ctx = ctx; reprogram = (ctx->task == current); /* * If the task is running, it must be running on this CPU, * otherwise we cannot reprogram things. * * If its not running, we don't care, ctx->lock will * serialize against it becoming runnable. */ if (task_curr(ctx->task) && !reprogram) { ret = -ESRCH; goto unlock; } WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx); } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } #ifdef CONFIG_CGROUP_PERF if (event->state > PERF_EVENT_STATE_OFF && is_cgroup_event(event)) { /* * If the current cgroup doesn't match the event's * cgroup, we should not try to schedule it. */ struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); reprogram = cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup); } #endif if (reprogram) { ctx_sched_out(ctx, EVENT_TIME); add_event_to_ctx(event, ctx); ctx_resched(cpuctx, task_ctx, get_event_type(event)); } else { add_event_to_ctx(event, ctx); } unlock: perf_ctx_unlock(cpuctx, task_ctx); return ret; } static bool exclusive_event_installable(struct perf_event *event, struct perf_event_context *ctx); /* * Attach a performance event to a context. * * Very similar to event_function_call, see comment there. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { struct task_struct *task = READ_ONCE(ctx->task); lockdep_assert_held(&ctx->mutex); WARN_ON_ONCE(!exclusive_event_installable(event, ctx)); if (event->cpu != -1) WARN_ON_ONCE(event->cpu != cpu); /* * Ensures that if we can observe event->ctx, both the event and ctx * will be 'complete'. See perf_iterate_sb_cpu(). */ smp_store_release(&event->ctx, ctx); /* * perf_event_attr::disabled events will not run and can be initialized * without IPI. Except when this is the first event for the context, in * that case we need the magic of the IPI to set ctx->is_active. * * The IOC_ENABLE that is sure to follow the creation of a disabled * event will issue the IPI and reprogram the hardware. */ if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && ctx->nr_events && !is_cgroup_event(event)) { raw_spin_lock_irq(&ctx->lock); if (ctx->task == TASK_TOMBSTONE) { raw_spin_unlock_irq(&ctx->lock); return; } add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); return; } if (!task) { cpu_function_call(cpu, __perf_install_in_context, event); return; } /* * Should not happen, we validate the ctx is still alive before calling. */ if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) return; /* * Installing events is tricky because we cannot rely on ctx->is_active * to be set in case this is the nr_events 0 -> 1 transition. * * Instead we use task_curr(), which tells us if the task is running. * However, since we use task_curr() outside of rq::lock, we can race * against the actual state. This means the result can be wrong. * * If we get a false positive, we retry, this is harmless. * * If we get a false negative, things are complicated. If we are after * perf_event_context_sched_in() ctx::lock will serialize us, and the * value must be correct. If we're before, it doesn't matter since * perf_event_context_sched_in() will program the counter. * * However, this hinges on the remote context switch having observed * our task->perf_event_ctxp[] store, such that it will in fact take * ctx::lock in perf_event_context_sched_in(). * * We do this by task_function_call(), if the IPI fails to hit the task * we know any future context switch of task must see the * perf_event_ctpx[] store. */ /* * This smp_mb() orders the task->perf_event_ctxp[] store with the * task_cpu() load, such that if the IPI then does not find the task * running, a future context switch of that task must observe the * store. */ smp_mb(); again: if (!task_function_call(task, __perf_install_in_context, event)) return; raw_spin_lock_irq(&ctx->lock); task = ctx->task; if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { /* * Cannot happen because we already checked above (which also * cannot happen), and we hold ctx->mutex, which serializes us * against perf_event_exit_task_context(). */ raw_spin_unlock_irq(&ctx->lock); return; } /* * If the task is not running, ctx->lock will avoid it becoming so, * thus we can safely install the event. */ if (task_curr(task)) { raw_spin_unlock_irq(&ctx->lock); goto again; } add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); } /* * Cross CPU call to enable a performance event */ static void __perf_event_enable(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, void *info) { struct perf_event *leader = event->group_leader; struct perf_event_context *task_ctx; if (event->state >= PERF_EVENT_STATE_INACTIVE || event->state <= PERF_EVENT_STATE_ERROR) return; if (ctx->is_active) ctx_sched_out(ctx, EVENT_TIME); perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); perf_cgroup_event_enable(event, ctx); if (!ctx->is_active) return; if (!event_filter_match(event)) { ctx_sched_in(ctx, EVENT_TIME); return; } /* * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { ctx_sched_in(ctx, EVENT_TIME); return; } task_ctx = cpuctx->task_ctx; if (ctx->task) WARN_ON_ONCE(task_ctx != ctx); ctx_resched(cpuctx, task_ctx, get_event_type(event)); } /* * Enable an event. * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This condition is satisfied when called through * perf_event_for_each_child or perf_event_for_each as described * for perf_event_disable. */ static void _perf_event_enable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; raw_spin_lock_irq(&ctx->lock); if (event->state >= PERF_EVENT_STATE_INACTIVE || event->state < PERF_EVENT_STATE_ERROR) { out: raw_spin_unlock_irq(&ctx->lock); return; } /* * If the event is in error state, clear that first. * * That way, if we see the event in error state below, we know that it * has gone back into error state, as distinct from the task having * been scheduled away before the cross-call arrived. */ if (event->state == PERF_EVENT_STATE_ERROR) { /* * Detached SIBLING events cannot leave ERROR state. */ if (event->event_caps & PERF_EV_CAP_SIBLING && event->group_leader == event) goto out; event->state = PERF_EVENT_STATE_OFF; } raw_spin_unlock_irq(&ctx->lock); event_function_call(event, __perf_event_enable, NULL); } /* * See perf_event_disable(); */ void perf_event_enable(struct perf_event *event) { struct perf_event_context *ctx; ctx = perf_event_ctx_lock(event); _perf_event_enable(event); perf_event_ctx_unlock(event, ctx); } EXPORT_SYMBOL_GPL(perf_event_enable); struct stop_event_data { struct perf_event *event; unsigned int restart; }; static int __perf_event_stop(void *info) { struct stop_event_data *sd = info; struct perf_event *event = sd->event; /* if it's already INACTIVE, do nothing */ if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE) return 0; /* matches smp_wmb() in event_sched_in() */ smp_rmb(); /* * There is a window with interrupts enabled before we get here, * so we need to check again lest we try to stop another CPU's event. */ if (READ_ONCE(event->oncpu) != smp_processor_id()) return -EAGAIN; event->pmu->stop(event, PERF_EF_UPDATE); /* * May race with the actual stop (through perf_pmu_output_stop()), * but it is only used for events with AUX ring buffer, and such * events will refuse to restart because of rb::aux_mmap_count==0, * see comments in perf_aux_output_begin(). * * Since this is happening on an event-local CPU, no trace is lost * while restarting. */ if (sd->restart) event->pmu->start(event, 0); return 0; } static int perf_event_stop(struct perf_event *event, int restart) { struct stop_event_data sd = { .event = event, .restart = restart, }; int ret = 0; do { if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE) return 0; /* matches smp_wmb() in event_sched_in() */ smp_rmb(); /* * We only want to restart ACTIVE events, so if the event goes * inactive here (event->oncpu==-1), there's nothing more to do; * fall through with ret==-ENXIO. */ ret = cpu_function_call(READ_ONCE(event->oncpu), __perf_event_stop, &sd); } while (ret == -EAGAIN); return ret; } /* * In order to contain the amount of racy and tricky in the address filter * configuration management, it is a two part process: * * (p1) when userspace mappings change as a result of (1) or (2) or (3) below, * we update the addresses of corresponding vmas in * event::addr_filter_ranges array and bump the event::addr_filters_gen; * (p2) when an event is scheduled in (pmu::add), it calls * perf_event_addr_filters_sync() which calls pmu::addr_filters_sync() * if the generation has changed since the previous call. * * If (p1) happens while the event is active, we restart it to force (p2). * * (1) perf_addr_filters_apply(): adjusting filters' offsets based on * pre-existing mappings, called once when new filters arrive via SET_FILTER * ioctl; * (2) perf_addr_filters_adjust(): adjusting filters' offsets based on newly * registered mapping, called for every new mmap(), with mm::mmap_lock down * for reading; * (3) perf_event_addr_filters_exec(): clearing filters' offsets in the process * of exec. */ void perf_event_addr_filters_sync(struct perf_event *event) { struct perf_addr_filters_head *ifh = perf_event_addr_filters(event); if (!has_addr_filter(event)) return; raw_spin_lock(&ifh->lock); if (event->addr_filters_gen != event->hw.addr_filters_gen) { event->pmu->addr_filters_sync(event); event->hw.addr_filters_gen = event->addr_filters_gen; } raw_spin_unlock(&ifh->lock); } EXPORT_SYMBOL_GPL(perf_event_addr_filters_sync); static int _perf_event_refresh(struct perf_event *event, int refresh) { /* * not supported on inherited events */ if (event->attr.inherit || !is_sampling_event(event)) return -EINVAL; atomic_add(refresh, &event->event_limit); _perf_event_enable(event); return 0; } /* * See perf_event_disable() */ int perf_event_refresh(struct perf_event *event, int refresh) { struct perf_event_context *ctx; int ret; ctx = perf_event_ctx_lock(event); ret = _perf_event_refresh(event, refresh); perf_event_ctx_unlock(event, ctx); return ret; } EXPORT_SYMBOL_GPL(perf_event_refresh); static int perf_event_modify_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { int err; _perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, true); if (!bp->attr.disabled) _perf_event_enable(bp); return err; } /* * Copy event-type-independent attributes that may be modified. */ static void perf_event_modify_copy_attr(struct perf_event_attr *to, const struct perf_event_attr *from) { to->sig_data = from->sig_data; } static int perf_event_modify_attr(struct perf_event *event, struct perf_event_attr *attr) { int (*func)(struct perf_event *, struct perf_event_attr *); struct perf_event *child; int err; if (event->attr.type != attr->type) return -EINVAL; switch (event->attr.type) { case PERF_TYPE_BREAKPOINT: func = perf_event_modify_breakpoint; break; default: /* Place holder for future additions. */ return -EOPNOTSUPP; } WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->child_mutex); /* * Event-type-independent attributes must be copied before event-type * modification, which will validate that final attributes match the * source attributes after all relevant attributes have been copied. */ perf_event_modify_copy_attr(&event->attr, attr); err = func(event, attr); if (err) goto out; list_for_each_entry(child, &event->child_list, child_list) { perf_event_modify_copy_attr(&child->attr, attr); err = func(child, attr); if (err) goto out; } out: mutex_unlock(&event->child_mutex); return err; } static void __pmu_ctx_sched_out(struct perf_event_pmu_context *pmu_ctx, enum event_type_t event_type) { struct perf_event_context *ctx = pmu_ctx->ctx; struct perf_event *event, *tmp; struct pmu *pmu = pmu_ctx->pmu; if (ctx->task && !ctx->is_active) { struct perf_cpu_pmu_context *cpc; cpc = this_cpu_ptr(pmu->cpu_pmu_context); WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx); cpc->task_epc = NULL; } if (!event_type) return; perf_pmu_disable(pmu); if (event_type & EVENT_PINNED) { list_for_each_entry_safe(event, tmp, &pmu_ctx->pinned_active, active_list) group_sched_out(event, ctx); } if (event_type & EVENT_FLEXIBLE) { list_for_each_entry_safe(event, tmp, &pmu_ctx->flexible_active, active_list) group_sched_out(event, ctx); /* * Since we cleared EVENT_FLEXIBLE, also clear * rotate_necessary, is will be reset by * ctx_flexible_sched_in() when needed. */ pmu_ctx->rotate_necessary = 0; } perf_pmu_enable(pmu); } static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_pmu_context *pmu_ctx; int is_active = ctx->is_active; bool cgroup = event_type & EVENT_CGROUP; event_type &= ~EVENT_CGROUP; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) { /* * See __perf_remove_from_context(). */ WARN_ON_ONCE(ctx->is_active); if (ctx->task) WARN_ON_ONCE(cpuctx->task_ctx); return; } /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last * context we sched out. For example: * * ctx_sched_out(.event_type = EVENT_FLEXIBLE) * ctx_sched_out(.event_type = EVENT_PINNED) * * would only update time for the pinned events. */ if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() */ barrier(); } ctx->is_active &= ~event_type; if (!(ctx->is_active & EVENT_ALL)) ctx->is_active = 0; if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); if (!ctx->is_active) cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (cgroup && !pmu_ctx->nr_cgroups) continue; __pmu_ctx_sched_out(pmu_ctx, is_active); } } /* * Test whether two contexts are equivalent, i.e. whether they have both been * cloned from the same version of the same context. * * Equivalence is measured using a generation number in the context that is * incremented on each modification to it; see unclone_ctx(), list_add_event() * and list_del_event(). */ static int context_equiv(struct perf_event_context *ctx1, struct perf_event_context *ctx2) { lockdep_assert_held(&ctx1->lock); lockdep_assert_held(&ctx2->lock); /* Pinning disables the swap optimization */ if (ctx1->pin_count || ctx2->pin_count) return 0; /* If ctx1 is the parent of ctx2 */ if (ctx1 == ctx2->parent_ctx && ctx1->generation == ctx2->parent_gen) return 1; /* If ctx2 is the parent of ctx1 */ if (ctx1->parent_ctx == ctx2 && ctx1->parent_gen == ctx2->generation) return 1; /* * If ctx1 and ctx2 have the same parent; we flatten the parent * hierarchy, see perf_event_init_context(). */ if (ctx1->parent_ctx && ctx1->parent_ctx == ctx2->parent_ctx && ctx1->parent_gen == ctx2->parent_gen) return 1; /* Unmatched */ return 0; } static void __perf_event_sync_stat(struct perf_event *event, struct perf_event *next_event) { u64 value; if (!event->attr.inherit_stat) return; /* * Update the event value, we cannot use perf_event_read() * because we're in the middle of a context switch and have IRQs * disabled, which upsets smp_call_function_single(), however * we know the event must be on the current CPU, therefore we * don't need to use it. */ if (event->state == PERF_EVENT_STATE_ACTIVE) event->pmu->read(event); perf_event_update_time(event); /* * In order to keep per-task stats reliable we need to flip the event * values when we flip the contexts. */ value = local64_read(&next_event->count); value = local64_xchg(&event->count, value); local64_set(&next_event->count, value); swap(event->total_time_enabled, next_event->total_time_enabled); swap(event->total_time_running, next_event->total_time_running); /* * Since we swizzled the values, update the user visible data too. */ perf_event_update_userpage(event); perf_event_update_userpage(next_event); } static void perf_event_sync_stat(struct perf_event_context *ctx, struct perf_event_context *next_ctx) { struct perf_event *event, *next_event; if (!ctx->nr_stat) return; update_context_time(ctx); event = list_first_entry(&ctx->event_list, struct perf_event, event_entry); next_event = list_first_entry(&next_ctx->event_list, struct perf_event, event_entry); while (&event->event_entry != &ctx->event_list && &next_event->event_entry != &next_ctx->event_list) { __perf_event_sync_stat(event, next_event); event = list_next_entry(event, event_entry); next_event = list_next_entry(next_event, event_entry); } } #define double_list_for_each_entry(pos1, pos2, head1, head2, member) \ for (pos1 = list_first_entry(head1, typeof(*pos1), member), \ pos2 = list_first_entry(head2, typeof(*pos2), member); \ !list_entry_is_head(pos1, head1, member) && \ !list_entry_is_head(pos2, head2, member); \ pos1 = list_next_entry(pos1, member), \ pos2 = list_next_entry(pos2, member)) static void perf_event_swap_task_ctx_data(struct perf_event_context *prev_ctx, struct perf_event_context *next_ctx) { struct perf_event_pmu_context *prev_epc, *next_epc; if (!prev_ctx->nr_task_data) return; double_list_for_each_entry(prev_epc, next_epc, &prev_ctx->pmu_ctx_list, &next_ctx->pmu_ctx_list, pmu_ctx_entry) { if (WARN_ON_ONCE(prev_epc->pmu != next_epc->pmu)) continue; /* * PMU specific parts of task perf context can require * additional synchronization. As an example of such * synchronization see implementation details of Intel * LBR call stack data profiling; */ if (prev_epc->pmu->swap_task_ctx) prev_epc->pmu->swap_task_ctx(prev_epc, next_epc); else swap(prev_epc->task_ctx_data, next_epc->task_ctx_data); } } static void perf_ctx_sched_task_cb(struct perf_event_context *ctx, bool sched_in) { struct perf_event_pmu_context *pmu_ctx; struct perf_cpu_pmu_context *cpc; list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context); if (cpc->sched_cb_usage && pmu_ctx->pmu->sched_task) pmu_ctx->pmu->sched_task(pmu_ctx, sched_in); } } static void perf_event_context_sched_out(struct task_struct *task, struct task_struct *next) { struct perf_event_context *ctx = task->perf_event_ctxp; struct perf_event_context *next_ctx; struct perf_event_context *parent, *next_parent; int do_switch = 1; if (likely(!ctx)) return; rcu_read_lock(); next_ctx = rcu_dereference(next->perf_event_ctxp); if (!next_ctx) goto unlock; parent = rcu_dereference(ctx->parent_ctx); next_parent = rcu_dereference(next_ctx->parent_ctx); /* If neither context have a parent context; they cannot be clones. */ if (!parent && !next_parent) goto unlock; if (next_parent == ctx || next_ctx == parent || next_parent == parent) { /* * Looks like the two contexts are clones, so we might be * able to optimize the context switch. We lock both * contexts and check that they are clones under the * lock (including re-checking that neither has been * uncloned in the meantime). It doesn't matter which * order we take the locks because no other cpu could * be trying to lock both of these tasks. */ raw_spin_lock(&ctx->lock); raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { perf_ctx_disable(ctx, false); /* PMIs are disabled; ctx->nr_pending is stable. */ if (local_read(&ctx->nr_pending) || local_read(&next_ctx->nr_pending)) { /* * Must not swap out ctx when there's pending * events that rely on the ctx->task relation. */ raw_spin_unlock(&next_ctx->lock); rcu_read_unlock(); goto inside_switch; } WRITE_ONCE(ctx->task, next); WRITE_ONCE(next_ctx->task, task); perf_ctx_sched_task_cb(ctx, false); perf_event_swap_task_ctx_data(ctx, next_ctx); perf_ctx_enable(ctx, false); /* * RCU_INIT_POINTER here is safe because we've not * modified the ctx and the above modification of * ctx->task and ctx->task_ctx_data are immaterial * since those values are always verified under * ctx->lock which we're now holding. */ RCU_INIT_POINTER(task->perf_event_ctxp, next_ctx); RCU_INIT_POINTER(next->perf_event_ctxp, ctx); do_switch = 0; perf_event_sync_stat(ctx, next_ctx); } raw_spin_unlock(&next_ctx->lock); raw_spin_unlock(&ctx->lock); } unlock: rcu_read_unlock(); if (do_switch) { raw_spin_lock(&ctx->lock); perf_ctx_disable(ctx, false); inside_switch: perf_ctx_sched_task_cb(ctx, false); task_ctx_sched_out(ctx, EVENT_ALL); perf_ctx_enable(ctx, false); raw_spin_unlock(&ctx->lock); } } static DEFINE_PER_CPU(struct list_head, sched_cb_list); static DEFINE_PER_CPU(int, perf_sched_cb_usages); void perf_sched_cb_dec(struct pmu *pmu) { struct perf_cpu_pmu_context *cpc = this_cpu_ptr(pmu->cpu_pmu_context); this_cpu_dec(perf_sched_cb_usages); barrier(); if (!--cpc->sched_cb_usage) list_del(&cpc->sched_cb_entry); } void perf_sched_cb_inc(struct pmu *pmu) { struct perf_cpu_pmu_context *cpc = this_cpu_ptr(pmu->cpu_pmu_context); if (!cpc->sched_cb_usage++) list_add(&cpc->sched_cb_entry, this_cpu_ptr(&sched_cb_list)); barrier(); this_cpu_inc(perf_sched_cb_usages); } /* * This function provides the context switch callback to the lower code * layer. It is invoked ONLY when the context switch callback is enabled. * * This callback is relevant even to per-cpu events; for example multi event * PEBS requires this to provide PID/TID information. This requires we flush * all queued PEBS records before we context switch to a new task. */ static void __perf_pmu_sched_task(struct perf_cpu_pmu_context *cpc, bool sched_in) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct pmu *pmu; pmu = cpc->epc.pmu; /* software PMUs will not have sched_task */ if (WARN_ON_ONCE(!pmu->sched_task)) return; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(pmu); pmu->sched_task(cpc->task_epc, sched_in); perf_pmu_enable(pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } static void perf_pmu_sched_task(struct task_struct *prev, struct task_struct *next, bool sched_in) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_cpu_pmu_context *cpc; /* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */ if (prev == next || cpuctx->task_ctx) return; list_for_each_entry(cpc, this_cpu_ptr(&sched_cb_list), sched_cb_entry) __perf_pmu_sched_task(cpc, sched_in); } static void perf_event_switch(struct task_struct *task, struct task_struct *next_prev, bool sched_in); /* * Called from scheduler to remove the events of the current task, * with interrupts disabled. * * We stop each event and update the event value in event->count. * * This does not protect us against NMI, but disable() * sets the disabled bit in the control field of event _before_ * accessing the event control register. If a NMI hits, then it will * not restart the event. */ void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next) { if (__this_cpu_read(perf_sched_cb_usages)) perf_pmu_sched_task(task, next, false); if (atomic_read(&nr_switch_events)) perf_event_switch(task, next, false); perf_event_context_sched_out(task, next); /* * if cgroup events exist on this CPU, then we need * to check if we have to switch out PMU state. * cgroup event are system-wide mode only */ perf_cgroup_switch(next); } static bool perf_less_group_idx(const void *l, const void *r) { const struct perf_event *le = *(const struct perf_event **)l; const struct perf_event *re = *(const struct perf_event **)r; return le->group_index < re->group_index; } static void swap_ptr(void *l, void *r) { void **lp = l, **rp = r; swap(*lp, *rp); } static const struct min_heap_callbacks perf_min_heap = { .elem_size = sizeof(struct perf_event *), .less = perf_less_group_idx, .swp = swap_ptr, }; static void __heap_add(struct min_heap *heap, struct perf_event *event) { struct perf_event **itrs = heap->data; if (event) { itrs[heap->nr] = event; heap->nr++; } } static void __link_epc(struct perf_event_pmu_context *pmu_ctx) { struct perf_cpu_pmu_context *cpc; if (!pmu_ctx->ctx->task) return; cpc = this_cpu_ptr(pmu_ctx->pmu->cpu_pmu_context); WARN_ON_ONCE(cpc->task_epc && cpc->task_epc != pmu_ctx); cpc->task_epc = pmu_ctx; } static noinline int visit_groups_merge(struct perf_event_context *ctx, struct perf_event_groups *groups, int cpu, struct pmu *pmu, int (*func)(struct perf_event *, void *), void *data) { #ifdef CONFIG_CGROUP_PERF struct cgroup_subsys_state *css = NULL; #endif struct perf_cpu_context *cpuctx = NULL; /* Space for per CPU and/or any CPU event iterators. */ struct perf_event *itrs[2]; struct min_heap event_heap; struct perf_event **evt; int ret; if (pmu->filter && pmu->filter(pmu, cpu)) return 0; if (!ctx->task) { cpuctx = this_cpu_ptr(&perf_cpu_context); event_heap = (struct min_heap){ .data = cpuctx->heap, .nr = 0, .size = cpuctx->heap_size, }; lockdep_assert_held(&cpuctx->ctx.lock); #ifdef CONFIG_CGROUP_PERF if (cpuctx->cgrp) css = &cpuctx->cgrp->css; #endif } else { event_heap = (struct min_heap){ .data = itrs, .nr = 0, .size = ARRAY_SIZE(itrs), }; /* Events not within a CPU context may be on any CPU. */ __heap_add(&event_heap, perf_event_groups_first(groups, -1, pmu, NULL)); } evt = event_heap.data; __heap_add(&event_heap, perf_event_groups_first(groups, cpu, pmu, NULL)); #ifdef CONFIG_CGROUP_PERF for (; css; css = css->parent) __heap_add(&event_heap, perf_event_groups_first(groups, cpu, pmu, css->cgroup)); #endif if (event_heap.nr) { __link_epc((*evt)->pmu_ctx); perf_assert_pmu_disabled((*evt)->pmu_ctx->pmu); } min_heapify_all(&event_heap, &perf_min_heap); while (event_heap.nr) { ret = func(*evt, data); if (ret) return ret; *evt = perf_event_groups_next(*evt, pmu); if (*evt) min_heapify(&event_heap, 0, &perf_min_heap); else min_heap_pop(&event_heap, &perf_min_heap); } return 0; } /* * Because the userpage is strictly per-event (there is no concept of context, * so there cannot be a context indirection), every userpage must be updated * when context time starts :-( * * IOW, we must not miss EVENT_TIME edges. */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false; perf_event_update_time(event); perf_event_update_userpage(event); return true; } static inline void group_update_userpage(struct perf_event *group_event) { struct perf_event *event; if (!event_update_userpage(group_event)) return; for_each_sibling_event(event, group_event) event_update_userpage(event); } static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; int *can_add_hw = data; if (event->state <= PERF_EVENT_STATE_OFF) return 0; if (!event_filter_match(event)) return 0; if (group_can_go_on(event, *can_add_hw)) { if (!group_sched_in(event, ctx)) list_add_tail(&event->active_list, get_event_list(event)); } if (event->state == PERF_EVENT_STATE_INACTIVE) { *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); } else { struct perf_cpu_pmu_context *cpc; event->pmu_ctx->rotate_necessary = 1; cpc = this_cpu_ptr(event->pmu_ctx->pmu->cpu_pmu_context); perf_mux_hrtimer_restart(cpc); group_update_userpage(event); } } return 0; } static void pmu_groups_sched_in(struct perf_event_context *ctx, struct perf_event_groups *groups, struct pmu *pmu) { int can_add_hw = 1; visit_groups_merge(ctx, groups, smp_processor_id(), pmu, merge_sched_in, &can_add_hw); } static void ctx_groups_sched_in(struct perf_event_context *ctx, struct perf_event_groups *groups, bool cgroup) { struct perf_event_pmu_context *pmu_ctx; list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (cgroup && !pmu_ctx->nr_cgroups) continue; pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu); } } static void __pmu_ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu) { pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu); } static void ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); int is_active = ctx->is_active; bool cgroup = event_type & EVENT_CGROUP; event_type &= ~EVENT_CGROUP; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) return; if (!(is_active & EVENT_TIME)) { /* start ctx time */ __update_context_time(ctx, false); perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() */ barrier(); } ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) cpuctx->task_ctx = ctx; else WARN_ON_ONCE(cpuctx->task_ctx != ctx); } is_active ^= ctx->is_active; /* changed bits */ /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ if (is_active & EVENT_PINNED) ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup); /* Then walk through the lower prio flexible groups */ if (is_active & EVENT_FLEXIBLE) ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup); } static void perf_event_context_sched_in(struct task_struct *task) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_context *ctx; rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp); if (!ctx) goto rcu_unlock; if (cpuctx->task_ctx == ctx) { perf_ctx_lock(cpuctx, ctx); perf_ctx_disable(ctx, false); perf_ctx_sched_task_cb(ctx, true); perf_ctx_enable(ctx, false); perf_ctx_unlock(cpuctx, ctx); goto rcu_unlock; } perf_ctx_lock(cpuctx, ctx); /* * We must check ctx->nr_events while holding ctx->lock, such * that we serialize against perf_install_in_context(). */ if (!ctx->nr_events) goto unlock; perf_ctx_disable(ctx, false); /* * We want to keep the following priority order: * cpu pinned (that don't need to move), task pinned, * cpu flexible, task flexible. * * However, if task's ctx is not carrying any pinned * events, no need to flip the cpuctx's events around. */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) { perf_ctx_disable(&cpuctx->ctx, false); ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE); } perf_event_sched_in(cpuctx, ctx); perf_ctx_sched_task_cb(cpuctx->task_ctx, true); if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) perf_ctx_enable(&cpuctx->ctx, false); perf_ctx_enable(ctx, false); unlock: perf_ctx_unlock(cpuctx, ctx); rcu_unlock: rcu_read_unlock(); } /* * Called from scheduler to add the events of the current task * with interrupts disabled. * * We restore the event value and then enable it. * * This does not protect us against NMI, but enable() * sets the enabled bit in the control field of event _before_ * accessing the event control register. If a NMI hits, then it will * keep the event running. */ void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { perf_event_context_sched_in(task); if (atomic_read(&nr_switch_events)) perf_event_switch(task, prev, true); if (__this_cpu_read(perf_sched_cb_usages)) perf_pmu_sched_task(prev, task, true); } static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) { u64 frequency = event->attr.sample_freq; u64 sec = NSEC_PER_SEC; u64 divisor, dividend; int count_fls, nsec_fls, frequency_fls, sec_fls; count_fls = fls64(count); nsec_fls = fls64(nsec); frequency_fls = fls64(frequency); sec_fls = 30; /* * We got @count in @nsec, with a target of sample_freq HZ * the target period becomes: * * @count * 10^9 * period = ------------------- * @nsec * sample_freq * */ /* * Reduce accuracy by one bit such that @a and @b converge * to a similar magnitude. */ #define REDUCE_FLS(a, b) \ do { \ if (a##_fls > b##_fls) { \ a >>= 1; \ a##_fls--; \ } else { \ b >>= 1; \ b##_fls--; \ } \ } while (0) /* * Reduce accuracy until either term fits in a u64, then proceed with * the other, so that finally we can do a u64/u64 division. */ while (count_fls + sec_fls > 64 && nsec_fls + frequency_fls > 64) { REDUCE_FLS(nsec, frequency); REDUCE_FLS(sec, count); } if (count_fls + sec_fls > 64) { divisor = nsec * frequency; while (count_fls + sec_fls > 64) { REDUCE_FLS(count, sec); divisor >>= 1; } dividend = count * sec; } else { dividend = count * sec; while (nsec_fls + frequency_fls > 64) { REDUCE_FLS(nsec, frequency); dividend >>= 1; } divisor = nsec * frequency; } if (!divisor) return dividend; return div64_u64(dividend, divisor); } static DEFINE_PER_CPU(int, perf_throttled_count); static DEFINE_PER_CPU(u64, perf_throttled_seq); static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count, bool disable) { struct hw_perf_event *hwc = &event->hw; s64 period, sample_period; s64 delta; period = perf_calculate_period(event, nsec, count); delta = (s64)(period - hwc->sample_period); delta = (delta + 7) / 8; /* low pass filter */ sample_period = hwc->sample_period + delta; if (!sample_period) sample_period = 1; hwc->sample_period = sample_period; if (local64_read(&hwc->period_left) > 8*sample_period) { if (disable) event->pmu->stop(event, PERF_EF_UPDATE); local64_set(&hwc->period_left, 0); if (disable) event->pmu->start(event, PERF_EF_RELOAD); } } static void perf_adjust_freq_unthr_events(struct list_head *event_list) { struct perf_event *event; struct hw_perf_event *hwc; u64 now, period = TICK_NSEC; s64 delta; list_for_each_entry(event, event_list, active_list) { if (event->state != PERF_EVENT_STATE_ACTIVE) continue; // XXX use visit thingy to avoid the -1,cpu match if (!event_filter_match(event)) continue; hwc = &event->hw; if (hwc->interrupts == MAX_INTERRUPTS) { hwc->interrupts = 0; perf_log_throttle(event, 1); if (!event->attr.freq || !event->attr.sample_freq) event->pmu->start(event, 0); } if (!event->attr.freq || !event->attr.sample_freq) continue; /* * stop the event and update event->count */ event->pmu->stop(event, PERF_EF_UPDATE); now = local64_read(&event->count); delta = now - hwc->freq_count_stamp; hwc->freq_count_stamp = now; /* * restart the event * reload only if value has changed * we have stopped the event so tell that * to perf_adjust_period() to avoid stopping it * twice. */ if (delta > 0) perf_adjust_period(event, period, delta, false); event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); } } /* * combine freq adjustment with unthrottling to avoid two passes over the * events. At the same time, make sure, having freq events does not change * the rate of unthrottling as that would introduce bias. */ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, bool unthrottle) { struct perf_event_pmu_context *pmu_ctx; /* * only need to iterate over all events iff: * - context have events in frequency mode (needs freq adjust) * - there are events to unthrottle on this cpu */ if (!(ctx->nr_freq || unthrottle)) return; raw_spin_lock(&ctx->lock); list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (!(pmu_ctx->nr_freq || unthrottle)) continue; if (!perf_pmu_ctx_is_active(pmu_ctx)) continue; if (pmu_ctx->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) continue; perf_pmu_disable(pmu_ctx->pmu); perf_adjust_freq_unthr_events(&pmu_ctx->pinned_active); perf_adjust_freq_unthr_events(&pmu_ctx->flexible_active); perf_pmu_enable(pmu_ctx->pmu); } raw_spin_unlock(&ctx->lock); } /* * Move @event to the tail of the @ctx's elegible events. */ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event) { /* * Rotate the first entry last of non-pinned groups. Rotation might be * disabled by the inheritance code. */ if (ctx->rotate_disable) return; perf_event_groups_delete(&ctx->flexible_groups, event); perf_event_groups_insert(&ctx->flexible_groups, event); } /* pick an event from the flexible_groups to rotate */ static inline struct perf_event * ctx_event_to_rotate(struct perf_event_pmu_context *pmu_ctx) { struct perf_event *event; struct rb_node *node; struct rb_root *tree; struct __group_key key = { .pmu = pmu_ctx->pmu, }; /* pick the first active flexible event */ event = list_first_entry_or_null(&pmu_ctx->flexible_active, struct perf_event, active_list); if (event) goto out; /* if no active flexible event, pick the first event */ tree = &pmu_ctx->ctx->flexible_groups.tree; if (!pmu_ctx->ctx->task) { key.cpu = smp_processor_id(); node = rb_find_first(&key, tree, __group_cmp_ignore_cgroup); if (node) event = __node_2_pe(node); goto out; } key.cpu = -1; node = rb_find_first(&key, tree, __group_cmp_ignore_cgroup); if (node) { event = __node_2_pe(node); goto out; } key.cpu = smp_processor_id(); node = rb_find_first(&key, tree, __group_cmp_ignore_cgroup); if (node) event = __node_2_pe(node); out: /* * Unconditionally clear rotate_necessary; if ctx_flexible_sched_in() * finds there are unschedulable events, it will set it again. */ pmu_ctx->rotate_necessary = 0; return event; } static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_pmu_context *cpu_epc, *task_epc = NULL; struct perf_event *cpu_event = NULL, *task_event = NULL; int cpu_rotate, task_rotate; struct pmu *pmu; /* * Since we run this from IRQ context, nobody can install new * events, thus the event count values are stable. */ cpu_epc = &cpc->epc; pmu = cpu_epc->pmu; task_epc = cpc->task_epc; cpu_rotate = cpu_epc->rotate_necessary; task_rotate = task_epc ? task_epc->rotate_necessary : 0; if (!(cpu_rotate || task_rotate)) return false; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(pmu); if (task_rotate) task_event = ctx_event_to_rotate(task_epc); if (cpu_rotate) cpu_event = ctx_event_to_rotate(cpu_epc); /* * As per the order given at ctx_resched() first 'pop' task flexible * and then, if needed CPU flexible. */ if (task_event || (task_epc && cpu_event)) { update_context_time(task_epc->ctx); __pmu_ctx_sched_out(task_epc, EVENT_FLEXIBLE); } if (cpu_event) { update_context_time(&cpuctx->ctx); __pmu_ctx_sched_out(cpu_epc, EVENT_FLEXIBLE); rotate_ctx(&cpuctx->ctx, cpu_event); __pmu_ctx_sched_in(&cpuctx->ctx, pmu); } if (task_event) rotate_ctx(task_epc->ctx, task_event); if (task_event || (task_epc && cpu_event)) __pmu_ctx_sched_in(task_epc->ctx, pmu); perf_pmu_enable(pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); return true; } void perf_event_task_tick(void) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_context *ctx; int throttled; lockdep_assert_irqs_disabled(); __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); perf_adjust_freq_unthr_context(&cpuctx->ctx, !!throttled); rcu_read_lock(); ctx = rcu_dereference(current->perf_event_ctxp); if (ctx) perf_adjust_freq_unthr_context(ctx, !!throttled); rcu_read_unlock(); } static int event_enable_on_exec(struct perf_event *event, struct perf_event_context *ctx) { if (!event->attr.enable_on_exec) return 0; event->attr.enable_on_exec = 0; if (event->state >= PERF_EVENT_STATE_INACTIVE) return 0; perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); return 1; } /* * Enable all of a task's events that have been marked enable-on-exec. * This expects task == current. */ static void perf_event_enable_on_exec(struct perf_event_context *ctx) { struct perf_event_context *clone_ctx = NULL; enum event_type_t event_type = 0; struct perf_cpu_context *cpuctx; struct perf_event *event; unsigned long flags; int enabled = 0; local_irq_save(flags); if (WARN_ON_ONCE(current->perf_event_ctxp != ctx)) goto out; if (!ctx->nr_events) goto out; cpuctx = this_cpu_ptr(&perf_cpu_context); perf_ctx_lock(cpuctx, ctx); ctx_sched_out(ctx, EVENT_TIME); list_for_each_entry(event, &ctx->event_list, event_entry) { enabled |= event_enable_on_exec(event, ctx); event_type |= get_event_type(event); } /* * Unclone and reschedule this context if we enabled any event. */ if (enabled) { clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { ctx_sched_in(ctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); out: local_irq_restore(flags); if (clone_ctx) put_ctx(clone_ctx); } static void perf_remove_from_owner(struct perf_event *event); static void perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx); /* * Removes all events from the current task that have been marked * remove-on-exec, and feeds their values back to parent events. */ static void perf_event_remove_on_exec(struct perf_event_context *ctx) { struct perf_event_context *clone_ctx = NULL; struct perf_event *event, *next; unsigned long flags; bool modified = false; mutex_lock(&ctx->mutex); if (WARN_ON_ONCE(ctx->task != current)) goto unlock; list_for_each_entry_safe(event, next, &ctx->event_list, event_entry) { if (!event->attr.remove_on_exec) continue; if (!is_kernel_event(event)) perf_remove_from_owner(event); modified = true; perf_event_exit_event(event, ctx); } raw_spin_lock_irqsave(&ctx->lock, flags); if (modified) clone_ctx = unclone_ctx(ctx); raw_spin_unlock_irqrestore(&ctx->lock, flags); unlock: mutex_unlock(&ctx->mutex); if (clone_ctx) put_ctx(clone_ctx); } struct perf_read_data { struct perf_event *event; bool group; int ret; }; static int __perf_event_read_cpu(struct perf_event *event, int event_cpu) { u16 local_pkg, event_pkg; if ((unsigned)event_cpu >= nr_cpu_ids) return event_cpu; if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) { int local_cpu = smp_processor_id(); event_pkg = topology_physical_package_id(event_cpu); local_pkg = topology_physical_package_id(local_cpu); if (event_pkg == local_pkg) return local_cpu; } return event_cpu; } /* * Cross CPU call to read the hardware event */ static void __perf_event_read(void *info) { struct perf_read_data *data = info; struct perf_event *sub, *event = data->event; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct pmu *pmu = event->pmu; /* * If this is a task context, we need to check whether it is * the current task context of this cpu. If not it has been * scheduled out before the smp call arrived. In that case * event->count would have been updated to a recent sample * when the event was scheduled out. */ if (ctx->task && cpuctx->task_ctx != ctx) return; raw_spin_lock(&ctx->lock); if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); update_cgrp_time_from_event(event); } perf_event_update_time(event); if (data->group) perf_event_update_sibling_time(event); if (event->state != PERF_EVENT_STATE_ACTIVE) goto unlock; if (!data->group) { pmu->read(event); data->ret = 0; goto unlock; } pmu->start_txn(pmu, PERF_PMU_TXN_READ); pmu->read(event); for_each_sibling_event(sub, event) { if (sub->state == PERF_EVENT_STATE_ACTIVE) { /* * Use sibling's PMU rather than @event's since * sibling could be on different (eg: software) PMU. */ sub->pmu->read(sub); } } data->ret = pmu->commit_txn(pmu); unlock: raw_spin_unlock(&ctx->lock); } static inline u64 perf_event_count(struct perf_event *event) { return local64_read(&event->count) + atomic64_read(&event->child_count); } static void calc_timer_values(struct perf_event *event, u64 *now, u64 *enabled, u64 *running) { u64 ctx_time; *now = perf_clock(); ctx_time = perf_event_time_now(event, *now); __perf_update_times(event, ctx_time, enabled, running); } /* * NMI-safe method to read a local event, that is an event that * is: * - either for the current task, or for this CPU * - does not have inherit set, for inherited task events * will not be local and we cannot read them atomically * - must not have a pmu::count method */ int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { unsigned long flags; int event_oncpu; int event_cpu; int ret = 0; /* * Disabling interrupts avoids all counter scheduling (context * switches, timer based rotation and IPIs). */ local_irq_save(flags); /* * It must not be an event with inherit set, we cannot read * all child counters from atomic context. */ if (event->attr.inherit) { ret = -EOPNOTSUPP; goto out; } /* If this is a per-task event, it must be for current */ if ((event->attach_state & PERF_ATTACH_TASK) && event->hw.target != current) { ret = -EINVAL; goto out; } /* * Get the event CPU numbers, and adjust them to local if the event is * a per-package event that can be read locally */ event_oncpu = __perf_event_read_cpu(event, event->oncpu); event_cpu = __perf_event_read_cpu(event, event->cpu); /* If this is a per-CPU event, it must be for this CPU */ if (!(event->attach_state & PERF_ATTACH_TASK) && event_cpu != smp_processor_id()) { ret = -EINVAL; goto out; } /* If this is a pinned event it must be running on this CPU */ if (event->attr.pinned && event_oncpu != smp_processor_id()) { ret = -EBUSY; goto out; } /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ if (event_oncpu == smp_processor_id()) event->pmu->read(event); *value = local64_read(&event->count); if (enabled || running) { u64 __enabled, __running, __now; calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) *running = __running; } out: local_irq_restore(flags); return ret; } static int perf_event_read(struct perf_event *event, bool group) { enum perf_event_state state = READ_ONCE(event->state); int event_cpu, ret = 0; /* * If event is enabled and currently active on a CPU, update the * value in the event structure: */ again: if (state == PERF_EVENT_STATE_ACTIVE) { struct perf_read_data data; /* * Orders the ->state and ->oncpu loads such that if we see * ACTIVE we must also see the right ->oncpu. * * Matches the smp_wmb() from event_sched_in(). */ smp_rmb(); event_cpu = READ_ONCE(event->oncpu); if ((unsigned)event_cpu >= nr_cpu_ids) return 0; data = (struct perf_read_data){ .event = event, .group = group, .ret = 0, }; preempt_disable(); event_cpu = __perf_event_read_cpu(event, event_cpu); /* * Purposely ignore the smp_call_function_single() return * value. * * If event_cpu isn't a valid CPU it means the event got * scheduled out and that will have updated the event count. * * Therefore, either way, we'll have an up-to-date event count * after this. */ (void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1); preempt_enable(); ret = data.ret; } else if (state == PERF_EVENT_STATE_INACTIVE) { struct perf_event_context *ctx = event->ctx; unsigned long flags; raw_spin_lock_irqsave(&ctx->lock, flags); state = event->state; if (state != PERF_EVENT_STATE_INACTIVE) { raw_spin_unlock_irqrestore(&ctx->lock, flags); goto again; } /* * May read while context is not active (e.g., thread is * blocked), in that case we cannot update context time */ if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); update_cgrp_time_from_event(event); } perf_event_update_time(event); if (group) perf_event_update_sibling_time(event); raw_spin_unlock_irqrestore(&ctx->lock, flags); } return ret; } /* * Initialize the perf_event context in a task_struct: */ static void __perf_event_init_context(struct perf_event_context *ctx) { raw_spin_lock_init(&ctx->lock); mutex_init(&ctx->mutex); INIT_LIST_HEAD(&ctx->pmu_ctx_list); perf_event_groups_init(&ctx->pinned_groups); perf_event_groups_init(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); refcount_set(&ctx->refcount, 1); } static void __perf_init_event_pmu_context(struct perf_event_pmu_context *epc, struct pmu *pmu) { epc->pmu = pmu; INIT_LIST_HEAD(&epc->pmu_ctx_entry); INIT_LIST_HEAD(&epc->pinned_active); INIT_LIST_HEAD(&epc->flexible_active); atomic_set(&epc->refcount, 1); } static struct perf_event_context * alloc_perf_context(struct task_struct *task) { struct perf_event_context *ctx; ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL); if (!ctx) return NULL; __perf_event_init_context(ctx); if (task) ctx->task = get_task_struct(task); return ctx; } static struct task_struct * find_lively_task_by_vpid(pid_t vpid) { struct task_struct *task; rcu_read_lock(); if (!vpid) task = current; else task = find_task_by_vpid(vpid); if (task) get_task_struct(task); rcu_read_unlock(); if (!task) return ERR_PTR(-ESRCH); return task; } /* * Returns a matching context with refcount and pincount. */ static struct perf_event_context * find_get_context(struct task_struct *task, struct perf_event *event) { struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_cpu_context *cpuctx; unsigned long flags; int err; if (!task) { /* Must be root to operate on a CPU event: */ err = perf_allow_cpu(&event->attr); if (err) return ERR_PTR(err); cpuctx = per_cpu_ptr(&perf_cpu_context, event->cpu); ctx = &cpuctx->ctx; get_ctx(ctx); raw_spin_lock_irqsave(&ctx->lock, flags); ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); return ctx; } err = -EINVAL; retry: ctx = perf_lock_task_context(task, &flags); if (ctx) { clone_ctx = unclone_ctx(ctx); ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); if (clone_ctx) put_ctx(clone_ctx); } else { ctx = alloc_perf_context(task); err = -ENOMEM; if (!ctx) goto errout; err = 0; mutex_lock(&task->perf_event_mutex); /* * If it has already passed perf_event_exit_task(). * we must see PF_EXITING, it takes this mutex too. */ if (task->flags & PF_EXITING) err = -ESRCH; else if (task->perf_event_ctxp) err = -EAGAIN; else { get_ctx(ctx); ++ctx->pin_count; rcu_assign_pointer(task->perf_event_ctxp, ctx); } mutex_unlock(&task->perf_event_mutex); if (unlikely(err)) { put_ctx(ctx); if (err == -EAGAIN) goto retry; goto errout; } } return ctx; errout: return ERR_PTR(err); } static struct perf_event_pmu_context * find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, struct perf_event *event) { struct perf_event_pmu_context *new = NULL, *epc; void *task_ctx_data = NULL; if (!ctx->task) { /* * perf_pmu_migrate_context() / __perf_pmu_install_event() * relies on the fact that find_get_pmu_context() cannot fail * for CPU contexts. */ struct perf_cpu_pmu_context *cpc; cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); epc = &cpc->epc; raw_spin_lock_irq(&ctx->lock); if (!epc->ctx) { atomic_set(&epc->refcount, 1); epc->embedded = 1; list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; } else { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); } raw_spin_unlock_irq(&ctx->lock); return epc; } new = kzalloc(sizeof(*epc), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); if (event->attach_state & PERF_ATTACH_TASK_DATA) { task_ctx_data = alloc_task_ctx_data(pmu); if (!task_ctx_data) { kfree(new); return ERR_PTR(-ENOMEM); } } __perf_init_event_pmu_context(new, pmu); /* * XXX * * lockdep_assert_held(&ctx->mutex); * * can't because perf_event_init_task() doesn't actually hold the * child_ctx->mutex. */ raw_spin_lock_irq(&ctx->lock); list_for_each_entry(epc, &ctx->pmu_ctx_list, pmu_ctx_entry) { if (epc->pmu == pmu) { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); goto found_epc; } } epc = new; new = NULL; list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; found_epc: if (task_ctx_data && !epc->task_ctx_data) { epc->task_ctx_data = task_ctx_data; task_ctx_data = NULL; ctx->nr_task_data++; } raw_spin_unlock_irq(&ctx->lock); free_task_ctx_data(pmu, task_ctx_data); kfree(new); return epc; } static void get_pmu_ctx(struct perf_event_pmu_context *epc) { WARN_ON_ONCE(!atomic_inc_not_zero(&epc->refcount)); } static void free_epc_rcu(struct rcu_head *head) { struct perf_event_pmu_context *epc = container_of(head, typeof(*epc), rcu_head); kfree(epc->task_ctx_data); kfree(epc); } static void put_pmu_ctx(struct perf_event_pmu_context *epc) { struct perf_event_context *ctx = epc->ctx; unsigned long flags; /* * XXX * * lockdep_assert_held(&ctx->mutex); * * can't because of the call-site in _free_event()/put_event() * which isn't always called under ctx->mutex. */ if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags)) return; WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); list_del_init(&epc->pmu_ctx_entry); epc->ctx = NULL; WARN_ON_ONCE(!list_empty(&epc->pinned_active)); WARN_ON_ONCE(!list_empty(&epc->flexible_active)); raw_spin_unlock_irqrestore(&ctx->lock, flags); if (epc->embedded) return; call_rcu(&epc->rcu_head, free_epc_rcu); } static void perf_event_free_filter(struct perf_event *event); static void free_event_rcu(struct rcu_head *head) { struct perf_event *event = container_of(head, typeof(*event), rcu_head); if (event->ns) put_pid_ns(event->ns); perf_event_free_filter(event); kmem_cache_free(perf_event_cache, event); } static void ring_buffer_attach(struct perf_event *event, struct perf_buffer *rb); static void detach_sb_event(struct perf_event *event) { struct pmu_event_list *pel = per_cpu_ptr(&pmu_sb_events, event->cpu); raw_spin_lock(&pel->lock); list_del_rcu(&event->sb_list); raw_spin_unlock(&pel->lock); } static bool is_sb_event(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; if (event->parent) return false; if (event->attach_state & PERF_ATTACH_TASK) return false; if (attr->mmap || attr->mmap_data || attr->mmap2 || attr->comm || attr->comm_exec || attr->task || attr->ksymbol || attr->context_switch || attr->text_poke || attr->bpf_event) return true; return false; } static void unaccount_pmu_sb_event(struct perf_event *event) { if (is_sb_event(event)) detach_sb_event(event); } #ifdef CONFIG_NO_HZ_FULL static DEFINE_SPINLOCK(nr_freq_lock); #endif static void unaccount_freq_event_nohz(void) { #ifdef CONFIG_NO_HZ_FULL spin_lock(&nr_freq_lock); if (atomic_dec_and_test(&nr_freq_events)) tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS); spin_unlock(&nr_freq_lock); #endif } static void unaccount_freq_event(void) { if (tick_nohz_full_enabled()) unaccount_freq_event_nohz(); else atomic_dec(&nr_freq_events); } static void unaccount_event(struct perf_event *event) { bool dec = false; if (event->parent) return; if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB)) dec = true; if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.build_id) atomic_dec(&nr_build_id_events); if (event->attr.comm) atomic_dec(&nr_comm_events); if (event->attr.namespaces) atomic_dec(&nr_namespaces_events); if (event->attr.cgroup) atomic_dec(&nr_cgroup_events); if (event->attr.task) atomic_dec(&nr_task_events); if (event->attr.freq) unaccount_freq_event(); if (event->attr.context_switch) { dec = true; atomic_dec(&nr_switch_events); } if (is_cgroup_event(event)) dec = true; if (has_branch_stack(event)) dec = true; if (event->attr.ksymbol) atomic_dec(&nr_ksymbol_events); if (event->attr.bpf_event) atomic_dec(&nr_bpf_events); if (event->attr.text_poke) atomic_dec(&nr_text_poke_events); if (dec) { if (!atomic_add_unless(&perf_sched_count, -1, 1)) schedule_delayed_work(&perf_sched_work, HZ); } unaccount_pmu_sb_event(event); } static void perf_sched_delayed(struct work_struct *work) { mutex_lock(&perf_sched_mutex); if (atomic_dec_and_test(&perf_sched_count)) static_branch_disable(&perf_sched_events); mutex_unlock(&perf_sched_mutex); } /* * The following implement mutual exclusion of events on "exclusive" pmus * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled * at a time, so we disallow creating events that might conflict, namely: * * 1) cpu-wide events in the presence of per-task events, * 2) per-task events in the presence of cpu-wide events, * 3) two matching events on the same perf_event_context. * * The former two cases are handled in the allocation path (perf_event_alloc(), * _free_event()), the latter -- before the first perf_install_in_context(). */ static int exclusive_event_init(struct perf_event *event) { struct pmu *pmu = event->pmu; if (!is_exclusive_pmu(pmu)) return 0; /* * Prevent co-existence of per-task and cpu-wide events on the * same exclusive pmu. * * Negative pmu::exclusive_cnt means there are cpu-wide * events on this "exclusive" pmu, positive means there are * per-task events. * * Since this is called in perf_event_alloc() path, event::ctx * doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK * to mean "per-task event", because unlike other attach states it * never gets cleared. */ if (event->attach_state & PERF_ATTACH_TASK) { if (!atomic_inc_unless_negative(&pmu->exclusive_cnt)) return -EBUSY; } else { if (!atomic_dec_unless_positive(&pmu->exclusive_cnt)) return -EBUSY; } return 0; } static void exclusive_event_destroy(struct perf_event *event) { struct pmu *pmu = event->pmu; if (!is_exclusive_pmu(pmu)) return; /* see comment in exclusive_event_init() */ if (event->attach_state & PERF_ATTACH_TASK) atomic_dec(&pmu->exclusive_cnt); else atomic_inc(&pmu->exclusive_cnt); } static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) { if ((e1->pmu == e2->pmu) && (e1->cpu == e2->cpu || e1->cpu == -1 || e2->cpu == -1)) return true; return false; } static bool exclusive_event_installable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event *iter_event; struct pmu *pmu = event->pmu; lockdep_assert_held(&ctx->mutex); if (!is_exclusive_pmu(pmu)) return true; list_for_each_entry(iter_event, &ctx->event_list, event_entry) { if (exclusive_event_match(iter_event, event)) return false; } return true; } static void perf_addr_filters_splice(struct perf_event *event, struct list_head *head); static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending_irq); unaccount_event(event); security_perf_event_free(event); if (event->rb) { /* * Can happen when we close an event with re-directed output. * * Since we have a 0 refcount, perf_mmap_close() will skip * over us; possibly making our ring_buffer_put() the last. */ mutex_lock(&event->mmap_mutex); ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); } if (is_cgroup_event(event)) perf_detach_cgroup(event); if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) put_callchain_buffers(); } perf_event_free_bpf_prog(event); perf_addr_filters_splice(event, NULL); kfree(event->addr_filter_ranges); if (event->destroy) event->destroy(event); /* * Must be after ->destroy(), due to uprobe_perf_close() using * hw.target. */ if (event->hw.target) put_task_struct(event->hw.target); if (event->pmu_ctx) put_pmu_ctx(event->pmu_ctx); /* * perf_event_free_task() relies on put_ctx() being 'last', in particular * all task references must be cleaned up. */ if (event->ctx) put_ctx(event->ctx); exclusive_event_destroy(event); module_put(event->pmu->module); call_rcu(&event->rcu_head, free_event_rcu); } /* * Used to free events which have a known refcount of 1, such as in error paths * where the event isn't exposed yet and inherited events. */ static void free_event(struct perf_event *event) { if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1, "unexpected event refcount: %ld; ptr=%p\n", atomic_long_read(&event->refcount), event)) { /* leak to avoid use-after-free */ return; } _free_event(event); } /* * Remove user event from the owner task. */ static void perf_remove_from_owner(struct perf_event *event) { struct task_struct *owner; rcu_read_lock(); /* * Matches the smp_store_release() in perf_event_exit_task(). If we * observe !owner it means the list deletion is complete and we can * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ owner = READ_ONCE(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last * task reference we can safely take a new reference * while holding the rcu_read_lock(). */ get_task_struct(owner); } rcu_read_unlock(); if (owner) { /* * If we're here through perf_event_exit_task() we're already * holding ctx->mutex which would be an inversion wrt. the * normal lock order. * * However we can safely take this lock because its the child * ctx->mutex. */ mutex_lock_nested(&owner->perf_event_mutex, SINGLE_DEPTH_NESTING); /* * We have to re-check the event->owner field, if it is cleared * we raced with perf_event_exit_task(), acquiring the mutex * ensured they're done, and we can proceed with freeing the * event. */ if (event->owner) { list_del_init(&event->owner_entry); smp_store_release(&event->owner, NULL); } mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } } static void put_event(struct perf_event *event) { if (!atomic_long_dec_and_test(&event->refcount)) return; _free_event(event); } /* * Kill an event dead; while event:refcount will preserve the event * object, it will not preserve its functionality. Once the last 'user' * gives up the object, we'll destroy the thing. */ int perf_event_release_kernel(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; LIST_HEAD(free_list); /* * If we got here through err_alloc: free_event(event); we will not * have attached to a context yet. */ if (!ctx) { WARN_ON_ONCE(event->attach_state & (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP)); goto no_ctx; } if (!is_kernel_event(event)) perf_remove_from_owner(event); ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); /* * Mark this event as STATE_DEAD, there is no external reference to it * anymore. * * Anybody acquiring event->child_mutex after the below loop _must_ * also see this, most importantly inherit_event() which will avoid * placing more children on the list. * * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ perf_remove_from_context(event, DETACH_GROUP|DETACH_DEAD); perf_event_ctx_unlock(event, ctx); again: mutex_lock(&event->child_mutex); list_for_each_entry(child, &event->child_list, child_list) { /* * Cannot change, child events are not migrated, see the * comment with perf_event_ctx_lock_nested(). */ ctx = READ_ONCE(child->ctx); /* * Since child_mutex nests inside ctx::mutex, we must jump * through hoops. We start by grabbing a reference on the ctx. * * Since the event cannot get freed while we hold the * child_mutex, the context must also exist and have a !0 * reference count. */ get_ctx(ctx); /* * Now that we have a ctx ref, we can drop child_mutex, and * acquire ctx::mutex without fear of it going away. Then we * can re-acquire child_mutex. */ mutex_unlock(&event->child_mutex); mutex_lock(&ctx->mutex); mutex_lock(&event->child_mutex); /* * Now that we hold ctx::mutex and child_mutex, revalidate our * state, if child is still the first entry, it didn't get freed * and we can continue doing so. */ tmp = list_first_entry_or_null(&event->child_list, struct perf_event, child_list); if (tmp == child) { perf_remove_from_context(child, DETACH_GROUP); list_move(&child->child_list, &free_list); /* * This matches the refcount bump in inherit_event(); * this can't be the last reference. */ put_event(event); } mutex_unlock(&event->child_mutex); mutex_unlock(&ctx->mutex); put_ctx(ctx); goto again; } mutex_unlock(&event->child_mutex); list_for_each_entry_safe(child, tmp, &free_list, child_list) { void *var = &child->ctx->refcount; list_del(&child->child_list); free_event(child); /* * Wake any perf_event_free_task() waiting for this event to be * freed. */ smp_mb(); /* pairs with wait_var_event() */ wake_up_var(var); } no_ctx: put_event(event); /* Must be the 'last' reference */ return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); /* * Called when the last reference to the file is gone. */ static int perf_release(struct inode *inode, struct file *file) { perf_event_release_kernel(file->private_data); return 0; } static u64 __perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; u64 total = 0; *enabled = 0; *running = 0; mutex_lock(&event->child_mutex); (void)perf_event_read(event, false); total += perf_event_count(event); *enabled += event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); *running += event->total_time_running + atomic64_read(&event->child_total_time_running); list_for_each_entry(child, &event->child_list, child_list) { (void)perf_event_read(child, false); total += perf_event_count(child); *enabled += child->total_time_enabled; *running += child->total_time_running; } mutex_unlock(&event->child_mutex); return total; } u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event_context *ctx; u64 count; ctx = perf_event_ctx_lock(event); count = __perf_event_read_value(event, enabled, running); perf_event_ctx_unlock(event, ctx); return count; } EXPORT_SYMBOL_GPL(perf_event_read_value); static int __perf_read_group_add(struct perf_event *leader, u64 read_format, u64 *values) { struct perf_event_context *ctx = leader->ctx; struct perf_event *sub, *parent; unsigned long flags; int n = 1; /* skip @nr */ int ret; ret = perf_event_read(leader, true); if (ret) return ret; raw_spin_lock_irqsave(&ctx->lock, flags); /* * Verify the grouping between the parent and child (inherited) * events is still in tact. * * Specifically: * - leader->ctx->lock pins leader->sibling_list * - parent->child_mutex pins parent->child_list * - parent->ctx->mutex pins parent->sibling_list * * Because parent->ctx != leader->ctx (and child_list nests inside * ctx->mutex), group destruction is not atomic between children, also * see perf_event_release_kernel(). Additionally, parent can grow the * group. * * Therefore it is possible to have parent and child groups in a * different configuration and summing over such a beast makes no sense * what so ever. * * Reject this. */ parent = leader->parent; if (parent && (parent->group_generation != leader->group_generation || parent->nr_siblings != leader->nr_siblings)) { ret = -ECHILD; goto unlock; } /* * Since we co-schedule groups, {enabled,running} times of siblings * will be identical to those of the leader, so we only publish one * set. */ if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { values[n++] += leader->total_time_enabled + atomic64_read(&leader->child_total_time_enabled); } if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { values[n++] += leader->total_time_running + atomic64_read(&leader->child_total_time_running); } /* * Write {count,id} tuples for every sibling. */ values[n++] += perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); if (read_format & PERF_FORMAT_LOST) values[n++] = atomic64_read(&leader->lost_samples); for_each_sibling_event(sub, leader) { values[n++] += perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); if (read_format & PERF_FORMAT_LOST) values[n++] = atomic64_read(&sub->lost_samples); } unlock: raw_spin_unlock_irqrestore(&ctx->lock, flags); return ret; } static int perf_read_group(struct perf_event *event, u64 read_format, char __user *buf) { struct perf_event *leader = event->group_leader, *child; struct perf_event_context *ctx = leader->ctx; int ret; u64 *values; lockdep_assert_held(&ctx->mutex); values = kzalloc(event->read_size, GFP_KERNEL); if (!values) return -ENOMEM; values[0] = 1 + leader->nr_siblings; mutex_lock(&leader->child_mutex); ret = __perf_read_group_add(leader, read_format, values); if (ret) goto unlock; list_for_each_entry(child, &leader->child_list, child_list) { ret = __perf_read_group_add(child, read_format, values); if (ret) goto unlock; } mutex_unlock(&leader->child_mutex); ret = event->read_size; if (copy_to_user(buf, values, event->read_size)) ret = -EFAULT; goto out; unlock: mutex_unlock(&leader->child_mutex); out: kfree(values); return ret; } static int perf_read_one(struct perf_event *event, u64 read_format, char __user *buf) { u64 enabled, running; u64 values[5]; int n = 0; values[n++] = __perf_event_read_value(event, &enabled, &running); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) values[n++] = enabled; if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) values[n++] = running; if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); if (read_format & PERF_FORMAT_LOST) values[n++] = atomic64_read(&event->lost_samples); if (copy_to_user(buf, values, n * sizeof(u64))) return -EFAULT; return n * sizeof(u64); } static bool is_event_hup(struct perf_event *event) { bool no_children; if (event->state > PERF_EVENT_STATE_EXIT) return false; mutex_lock(&event->child_mutex); no_children = list_empty(&event->child_list); mutex_unlock(&event->child_mutex); return no_children; } /* * Read the performance event - simple non blocking version for now */ static ssize_t __perf_read(struct perf_event *event, char __user *buf, size_t count) { u64 read_format = event->attr.read_format; int ret; /* * Return end-of-file for a read on an event that is in * error state (i.e. because it was pinned but it couldn't be * scheduled on to the CPU at some point). */ if (event->state == PERF_EVENT_STATE_ERROR) return 0; if (count < event->read_size) return -ENOSPC; WARN_ON_ONCE(event->ctx->parent_ctx); if (read_format & PERF_FORMAT_GROUP) ret = perf_read_group(event, read_format, buf); else ret = perf_read_one(event, read_format, buf); return ret; } static ssize_t perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct perf_event *event = file->private_data; struct perf_event_context *ctx; int ret; ret = security_perf_event_read(event); if (ret) return ret; ctx = perf_event_ctx_lock(event); ret = __perf_read(event, buf, count); perf_event_ctx_unlock(event, ctx); return ret; } static __poll_t perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct perf_buffer *rb; __poll_t events = EPOLLHUP; poll_wait(file, &event->waitq, wait); if (is_event_hup(event)) return events; /* * Pin the event->rb by taking event->mmap_mutex; otherwise * perf_event_set_output() can swizzle our rb and make us miss wakeups. */ mutex_lock(&event->mmap_mutex); rb = event->rb; if (rb) events = atomic_xchg(&rb->poll, 0); mutex_unlock(&event->mmap_mutex); return events; } static void _perf_event_reset(struct perf_event *event) { (void)perf_event_read(event, false); local64_set(&event->count, 0); perf_event_update_userpage(event); } /* Assume it's not an event with inherit set. */ u64 perf_event_pause(struct perf_event *event, bool reset) { struct perf_event_context *ctx; u64 count; ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(event->attr.inherit); _perf_event_disable(event); count = local64_read(&event->count); if (reset) local64_set(&event->count, 0); perf_event_ctx_unlock(event, ctx); return count; } EXPORT_SYMBOL_GPL(perf_event_pause); /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block * in perf_event_exit_event() if it goes to exit, thus satisfying the * task existence requirements of perf_event_enable/disable. */ static void perf_event_for_each_child(struct perf_event *event, void (*func)(struct perf_event *)) { struct perf_event *child; WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->child_mutex); func(event); list_for_each_entry(child, &event->child_list, child_list) func(child); mutex_unlock(&event->child_mutex); } static void perf_event_for_each(struct perf_event *event, void (*func)(struct perf_event *)) { struct perf_event_context *ctx = event->ctx; struct perf_event *sibling; lockdep_assert_held(&ctx->mutex); event = event->group_leader; perf_event_for_each_child(event, func); for_each_sibling_event(sibling, event) perf_event_for_each_child(sibling, func); } static void __perf_event_period(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, void *info) { u64 value = *((u64 *)info); bool active; if (event->attr.freq) { event->attr.sample_freq = value; } else { event->attr.sample_period = value; event->hw.sample_period = value; } active = (event->state == PERF_EVENT_STATE_ACTIVE); if (active) { perf_pmu_disable(event->pmu); /* * We could be throttled; unthrottle now to avoid the tick * trying to unthrottle while we already re-started the event. */ if (event->hw.interrupts == MAX_INTERRUPTS) { event->hw.interrupts = 0; perf_log_throttle(event, 1); } event->pmu->stop(event, PERF_EF_UPDATE); } local64_set(&event->hw.period_left, 0); if (active) { event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(event->pmu); } } static int perf_event_check_period(struct perf_event *event, u64 value) { return event->pmu->check_period(event, value); } static int _perf_event_period(struct perf_event *event, u64 value) { if (!is_sampling_event(event)) return -EINVAL; if (!value) return -EINVAL; if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; if (perf_event_check_period(event, value)) return -EINVAL; if (!event->attr.freq && (value & (1ULL << 63))) return -EINVAL; event_function_call(event, __perf_event_period, &value); return 0; } int perf_event_period(struct perf_event *event, u64 value) { struct perf_event_context *ctx; int ret; ctx = perf_event_ctx_lock(event); ret = _perf_event_period(event, value); perf_event_ctx_unlock(event, ctx); return ret; } EXPORT_SYMBOL_GPL(perf_event_period); static const struct file_operations perf_fops; static inline int perf_fget_light(int fd, struct fd *p) { struct fd f = fdget(fd); if (!f.file) return -EBADF; if (f.file->f_op != &perf_fops) { fdput(f); return -EBADF; } *p = f; return 0; } static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event); static int perf_event_set_filter(struct perf_event *event, void __user *arg); static int perf_copy_attr(struct perf_event_attr __user *uattr, struct perf_event_attr *attr); static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg) { void (*func)(struct perf_event *); u32 flags = arg; switch (cmd) { case PERF_EVENT_IOC_ENABLE: func = _perf_event_enable; break; case PERF_EVENT_IOC_DISABLE: func = _perf_event_disable; break; case PERF_EVENT_IOC_RESET: func = _perf_event_reset; break; case PERF_EVENT_IOC_REFRESH: return _perf_event_refresh(event, arg); case PERF_EVENT_IOC_PERIOD: { u64 value; if (copy_from_user(&value, (u64 __user *)arg, sizeof(value))) return -EFAULT; return _perf_event_period(event, value); } case PERF_EVENT_IOC_ID: { u64 id = primary_event_id(event); if (copy_to_user((void __user *)arg, &id, sizeof(id))) return -EFAULT; return 0; } case PERF_EVENT_IOC_SET_OUTPUT: { int ret; if (arg != -1) { struct perf_event *output_event; struct fd output; ret = perf_fget_light(arg, &output); if (ret) return ret; output_event = output.file->private_data; ret = perf_event_set_output(event, output_event); fdput(output); } else { ret = perf_event_set_out |